title stringlengths 1 300 | score int64 0 8.54k | selftext stringlengths 0 41.5k | created timestamp[ns]date 2023-04-01 04:30:41 2026-03-04 02:14:14 ⌀ | url stringlengths 0 878 | author stringlengths 3 20 | domain stringlengths 0 82 | edited timestamp[ns]date 1970-01-01 00:00:00 2026-02-19 14:51:53 | gilded int64 0 2 | gildings stringclasses 7
values | id stringlengths 7 7 | locked bool 2
classes | media stringlengths 646 1.8k ⌀ | name stringlengths 10 10 | permalink stringlengths 33 82 | spoiler bool 2
classes | stickied bool 2
classes | thumbnail stringlengths 4 213 ⌀ | ups int64 0 8.54k | preview stringlengths 301 5.01k ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Hardware Requirement for AI/ML | 1 | Hi,
I’m studying software engineering in college and finishing all my lower division classes (mostly not directly related to the major) in this semester. And AI/ML seems like interesting and I want to specialize in AI/ML or maybe just direct myself into it. Anyways, I was thinking to buy a laptop with 4070 and 16gb ra... | 2025-11-17T10:17:40 | https://www.reddit.com/r/LocalLLaMA/comments/1ozcnxj/hardware_requirement_for_aiml/ | Sad-Concentrate8364 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozcnxj | false | null | t3_1ozcnxj | /r/LocalLLaMA/comments/1ozcnxj/hardware_requirement_for_aiml/ | false | false | self | 1 | null |
which models were pretty good at visual reasoning?? | 2 | i dont know wheather visual reasoning would be better metric at this or not but yeah what im trying to build is something which generates node based flows using react flow and meramid from prompts as of now using sonnet 4.5...thing is i need to generate the location too so when its complex flow its not that good so any... | 2025-11-17T10:14:48 | https://www.reddit.com/r/LocalLLaMA/comments/1ozcmc2/which_models_were_pretty_good_at_visual_reasoning/ | lavangamm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozcmc2 | false | null | t3_1ozcmc2 | /r/LocalLLaMA/comments/1ozcmc2/which_models_were_pretty_good_at_visual_reasoning/ | false | false | self | 2 | null |
MemLayer, a Python package that gives local LLMs persistent long-term memory (open-source) | 232 | # What Memlayer Does
MemLayer is an open-source **Python package** that adds persistent, long-term memory to **local LLMs** and embedding pipelines.
Local models are powerful, but they’re stateless. Every prompt starts from zero.
This makes it difficult to build assistants or agents that remember anything from one ... | 2025-11-17T09:34:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbzpx/memlayer_a_python_package_that_gives_local_llms/ | MoreMouseBites | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbzpx | false | null | t3_1ozbzpx | /r/LocalLLaMA/comments/1ozbzpx/memlayer_a_python_package_that_gives_local_llms/ | false | false | self | 232 | null |
Free GPU in VS Code (Google Colab x VS Code) | 21 | Google Colab has now got an extension in VS Code and hence, you can use the free T4 GPU in VS Code directly from local system. Demo--> [https://youtu.be/sTlVTwkQPV4](https://youtu.be/sTlVTwkQPV4) | 2025-11-17T09:25:29 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbv38/free_gpu_in_vs_code_google_colab_x_vs_code/ | Technical-Love-8479 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbv38 | false | null | t3_1ozbv38 | /r/LocalLLaMA/comments/1ozbv38/free_gpu_in_vs_code_google_colab_x_vs_code/ | false | false | self | 21 | {'enabled': False, 'images': [{'id': 'qmPpJNZ122hdnbLudI5pid3FgVulEBoLl3GJMb0nkKU', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/qmPpJNZ122hdnbLudI5pid3FgVulEBoLl3GJMb0nkKU.jpeg?width=108&crop=smart&auto=webp&s=2d165765654baa46a007b1557e15ca43b0da9ab9', 'width': 108}, {'height': 162, 'url': '... |
BSD MAC LLM UI: Minimal, Auditable LLM Front End for Secure Environments | 6 | **BSD MAC LLM UI** is a compact, security-focused chat interface built in C with lean design principles and released under the BSD 3-Clause license. It offers a no-JavaScript HTML/CSS web UI or optional GTK/Qt GUI, routing prompts either to an OpenAI-compatible API or running fully offline via TensorRT-LLM - ideal for ... | 2025-11-17T09:21:25 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbswk/bsd_mac_llm_ui_minimal_auditable_llm_front_end/ | 3mdeb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbswk | false | null | t3_1ozbswk | /r/LocalLLaMA/comments/1ozbswk/bsd_mac_llm_ui_minimal_auditable_llm_front_end/ | false | false | self | 6 | null |
Local small model for math validation | 0 | Hi guys,
I used to have a GPT+ license my son used for checks/validation/solution explation of his mathemartics exercises (first academic year).
I currentl have no longer have such license. For such usage - and as he is smart using it the right way - I might consider taking a new one.
Though , I have a laptop wi... | 2025-11-17T09:15:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbps0/local_small_model_for_math_validation/ | ericlecoutre | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbps0 | false | null | t3_1ozbps0 | /r/LocalLLaMA/comments/1ozbps0/local_small_model_for_math_validation/ | false | false | self | 0 | null |
Text-to-image | 1 | Hey, guys I wondering what is lights text-to-image model in terms of Vram. I need the lightest one possible. | 2025-11-17T08:55:54 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbezx/texttoimage/ | Lazy_Mycologist_8214 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbezx | false | null | t3_1ozbezx | /r/LocalLLaMA/comments/1ozbezx/texttoimage/ | false | false | self | 1 | null |
Nvidia DGX Spark (or alike) vs dual RTX 3090 | 7 | What are your opinions on getting the one or the other for professional work.
Let's assume you can build a RTX based machine, or have one. Does the increase of HBA RAM to 128GB in the Spark justifies the price.
By professional work i mostly mean using coder models (Qwen-coder) for coding assitance or general models ... | 2025-11-17T08:54:30 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbe8q/nvidia_dgx_spark_or_alike_vs_dual_rtx_3090/ | ChopSticksPlease | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbe8q | false | null | t3_1ozbe8q | /r/LocalLLaMA/comments/1ozbe8q/nvidia_dgx_spark_or_alike_vs_dual_rtx_3090/ | false | false | self | 7 | null |
memory issues with the attention mechanism | 0 | Hello everyone. I’ve finished my first fine-tuning, and today I wanted to test it, but I’m running into problems with memory allocation (24GB VRAM). Let me explain the issue.
I fine-tuned a LLaMA 3.1 8B Instruct model. The use case is text-to-SQL, which requires putting the database schema in the system prompt.
I’m n... | 2025-11-17T08:52:51 | https://www.reddit.com/r/LocalLLaMA/comments/1ozbdd3/memory_issues_with_the_attention_mechanism/ | Juno9419 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozbdd3 | false | null | t3_1ozbdd3 | /r/LocalLLaMA/comments/1ozbdd3/memory_issues_with_the_attention_mechanism/ | false | false | self | 0 | null |
Vibe coded a llamacpp server launcher | 0 | This is a Windows batch script that automatically loads your models from a given directory and starts the llama-server.
# Features
* Automatically loads your gguf models.
* Dynamically detects mmproj files for vision models.
* Allows configuration for: GPU layers, arguments and more.
* Can be run from anywhere in you... | 2025-11-17T08:42:21 | Iq1pl | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ozb7vr | false | null | t3_1ozb7vr | /r/LocalLLaMA/comments/1ozb7vr/vibe_coded_a_llamacpp_server_launcher/ | false | false | 0 | {'enabled': True, 'images': [{'id': '1ifHDTctQWhQ9-UMdMAtIx-f2qRTz-8u2-QPdvwyWg8', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/5dbem24uyr1g1.png?width=108&crop=smart&auto=webp&s=b0e8a0f365795ebb895eec8dbf286069bc692eeb', 'width': 108}, {'height': 128, 'url': 'https://preview.redd.it/5dbem24uyr1g1.png... | ||
Human-like conversations, bias and token length? | 1 | Since the beginning of my AI journey a few years ago I have had the idea of recreating myself. Cloning my looks and my voice was easy enough (even if I've only managed to get the voice in "realtime"), but I have yet to find a way to accurately capture human-like conversations and personality. I've looked at the Mistral... | 2025-11-17T08:11:01 | https://www.reddit.com/r/LocalLLaMA/comments/1ozaqu0/humanlike_conversations_bias_and_token_length/ | VirusCharacter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozaqu0 | false | null | t3_1ozaqu0 | /r/LocalLLaMA/comments/1ozaqu0/humanlike_conversations_bias_and_token_length/ | false | false | self | 1 | null |
Software recommendations | 0 | What are some of the best repos/tools people are using to interact with local LLMs (outside of the usual Ollama, LM Studio)? What's your stack? What are some success stories for ways you've managed to integrate it into your daily workflows? What are some exciting projects under development? Let's hear it all! | 2025-11-17T07:54:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ozahfe/software_recommendations/ | 1H4rsh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ozahfe | false | null | t3_1ozahfe | /r/LocalLLaMA/comments/1ozahfe/software_recommendations/ | false | false | self | 0 | null |
Lm playground | 0 | I just spent some time to make a website/app
It host board games and card games for now
It connects to llms via lmstudio ollama or api
It has the rules of each game in the corner with a log and chat for llms
What types of models should I test this with before I make it public idk if anyone is interested in something... | 2025-11-17T07:28:07 | AceCustom1 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oza32g | false | null | t3_1oza32g | /r/LocalLLaMA/comments/1oza32g/lm_playground/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'n5xlzljyrr1g1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/n5xlzljyrr1g1.jpeg?width=108&crop=smart&auto=webp&s=f9b8f87078669fd995dafce1d67bc12836913562', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/n5xlzljyrr1g1.jpeg?width=216&crop=smart&auto=... | |
Apple is considering putting miniHBM on iPhones in 2027 | 142 | This news was reported on Macrumor, Apple Insider. If Apple puts minihbm on the iphone, then macs will also have minihbm soon… Crazy bandwidths are coming, I hope HBM comes to macs before the iphone! | 2025-11-17T07:15:05 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9vs3/apple_is_considering_putting_minihbm_on_iphones/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9vs3 | false | null | t3_1oz9vs3 | /r/LocalLLaMA/comments/1oz9vs3/apple_is_considering_putting_minihbm_on_iphones/ | false | false | self | 142 | {'enabled': False, 'images': [{'id': '31jbMIT-zHUzs6quUA9j2q29Vo962IDs2BkWQxaNxjU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/31jbMIT-zHUzs6quUA9j2q29Vo962IDs2BkWQxaNxjU.jpeg?width=108&crop=smart&auto=webp&s=5128b81245d2b02e8071c42828307222eba699f1', 'width': 108}, {'height': 121, 'url': '... |
[DEV] Looking for AI agent builders to test a privacy-safe ad layer | 0 | Hey folks — I’m building NativeLayer, a lightweight, privacy-first monetization layer for LLM apps and agents. If you’re working on AI tools and want a real revenue option without tracking users, I’d love your feedback.
What it does
• Adds context-aware sponsored responses into agent/chat flows
• Zero tracking (GDPR... | 2025-11-17T07:08:21 | https://www.reddit.com/gallery/1oz9rwo | Acrobatic-Repair-837 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1oz9rwo | false | null | t3_1oz9rwo | /r/LocalLLaMA/comments/1oz9rwo/dev_looking_for_ai_agent_builders_to_test_a/ | false | false | 0 | null | |
[DEV] Looking for Local LLaMA builders to help test a privacy-safe ad layer | 1 | Hey folks — I’m working on NativeLayer, a lightweight, privacy-first monetization layer for LLM apps and local agent setups.
If you’re building local models, agentic workflows, custom frontends, or side-projects, and want a way to generate revenue without tracking users, I’d love your feedback.
What it does
• Inject... | 2025-11-17T07:03:18 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9p23/dev_looking_for_local_llama_builders_to_help_test/ | Acrobatic-Repair-837 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9p23 | false | null | t3_1oz9p23 | /r/LocalLLaMA/comments/1oz9p23/dev_looking_for_local_llama_builders_to_help_test/ | false | false | self | 1 | null |
Best opensource model for speech to text and supports streaming | 0 | Which is the best open source model which supports streaming via websockets and has low latency for speech to text | 2025-11-17T07:00:15 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9n3y/best_opensource_model_for_speech_to_text_and/ | Otherwise-Top2335 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9n3y | false | null | t3_1oz9n3y | /r/LocalLLaMA/comments/1oz9n3y/best_opensource_model_for_speech_to_text_and/ | false | false | self | 0 | null |
Open-World Game to Practice Interview Skills | 0 | Hi Everybody! I am just writing to share a project that I have been working on for the last few months called Yapper. Yapper is a free, light hearted, low-stakes way for healthcare students (or anyone who is interested quite frankly) to practice patient interview skills. The patients responses are driven by a tiny lang... | 2025-11-17T07:00:05 | https://v.redd.it/0iecjuvslr1g1 | Apprehensive-Wish735 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oz9mzs | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/0iecjuvslr1g1/DASHPlaylist.mpd?a=1765954819%2CNjVmM2M1MzJiN2I0MmEyZGVmODFiYTMyODUwM2M4NDljMDcxYWRjODMwYTRmYzFmY2I5YTA5ZTkyZWJjZjFlZA%3D%3D&v=1&f=sd', 'duration': 79, 'fallback_url': 'https://v.redd.it/0iecjuvslr1g1/CMAF_480.mp4?source=fallback', 'ha... | t3_1oz9mzs | /r/LocalLLaMA/comments/1oz9mzs/openworld_game_to_practice_interview_skills/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'dWF4Mmc5d3NscjFnMaVixxKd7zB_dNqOq_lzz69riEl9YNZ0oAJnjPLWVPtC', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/dWF4Mmc5d3NscjFnMaVixxKd7zB_dNqOq_lzz69riEl9YNZ0oAJnjPLWVPtC.png?width=108&crop=smart&format=pjpg&auto=webp&s=6f278fdb87ac250465a87e2cdf9e9d8f0c05e... | |
Options for working with sensitive data? | 2 | Hey all,
Recently come up at work that we have to be careful about what type of data we put into online AI models, which is totally fair.
I guess my my question is, for what I assume are everyday AI tasks like gathering insights on documents, calculations and programming, text generation and other simple tasks/automa... | 2025-11-17T06:58:55 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9m9z/options_for_working_with_sensitive_data/ | PsychologicalCup1672 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9m9z | false | null | t3_1oz9m9z | /r/LocalLLaMA/comments/1oz9m9z/options_for_working_with_sensitive_data/ | false | false | self | 2 | null |
Claude Sonnet 4.5 is still the best for me | 0 | For the last couple of months I had a company provided Claude API Key.
I was using it with Cursor and it was amazing. It was very proactive and very deliberate in performing tasks for me.
If I told it to update a function, clean up a file etc, it would proactively check any references to it and make sure everything s... | 2025-11-17T06:40:22 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9bqf/claude_sonnet_45_is_still_the_best_for_me/ | OGXirvin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9bqf | false | null | t3_1oz9bqf | /r/LocalLLaMA/comments/1oz9bqf/claude_sonnet_45_is_still_the_best_for_me/ | false | false | self | 0 | null |
Models for fiction stories and creative writing? | 1 | Hi all,
Out of all models that are released this year, what models do you recommend for long form story writing? Has any model come close to Midnight Miqu? preferably in the 70B and above range.
Thanks all! | 2025-11-17T06:31:35 | https://www.reddit.com/r/LocalLLaMA/comments/1oz96l2/models_for_fiction_stories_and_creative_writing/ | morbidSuplex | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz96l2 | false | null | t3_1oz96l2 | /r/LocalLLaMA/comments/1oz96l2/models_for_fiction_stories_and_creative_writing/ | false | false | self | 1 | null |
"AI safety" will be the end of us all | 4 | 2025-11-17T06:30:51 | zhambe | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oz964x | false | null | t3_1oz964x | /r/LocalLLaMA/comments/1oz964x/ai_safety_will_be_the_end_of_us_all/ | false | false | default | 4 | {'enabled': True, 'images': [{'id': 'n8ltqm5nhr1g1', 'resolutions': [{'height': 24, 'url': 'https://preview.redd.it/n8ltqm5nhr1g1.png?width=108&crop=smart&auto=webp&s=29c693747ada4b3a01fa13e205017140bd0c74f1', 'width': 108}, {'height': 48, 'url': 'https://preview.redd.it/n8ltqm5nhr1g1.png?width=216&crop=smart&auto=webp... | ||
RAG Paper 25.11.14 | 9 | 1. [Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directions](http://arxiv.org/abs/2511.11347v1)
2. [CLARITY: Contextual Linguistic Adaptation and Accent Retrieval for Dual-Bias Mitigation in Text-to-Speech Generati... | 2025-11-17T06:29:20 | https://www.reddit.com/r/LocalLLaMA/comments/1oz9563/rag_paper_251114/ | Cheryl_Apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz9563 | false | null | t3_1oz9563 | /r/LocalLLaMA/comments/1oz9563/rag_paper_251114/ | false | false | self | 9 | null |
PyTorch 2.10.0a0 w/ Blackwell (sm_120) Support — Patched & Packaged for One-Command Install | 14 | If you’ve been frustrated with PyTorch not supporting **sm\_120** yet on the RTX 5080/5090 — I finally cracked it.
I reverse-engineered the missing pieces, patched the arch detection, fixed dispatch fallbacks, and packaged everything into two wheels:
pip install rtx-stone # Windows
pip install stone-linux #... | 2025-11-17T06:16:14 | https://www.reddit.com/r/LocalLLaMA/comments/1oz8x9i/pytorch_2100a0_w_blackwell_sm_120_support_patched/ | Least-Barracuda-2793 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz8x9i | false | null | t3_1oz8x9i | /r/LocalLLaMA/comments/1oz8x9i/pytorch_2100a0_w_blackwell_sm_120_support_patched/ | false | false | self | 14 | null |
TTS model for 4GB VRAM and 16 GB RAM ? | 13 | Should I try index TTS with these specs ?
Also if anyone can give me tips on installing open models as my laptop is also used for my college | 2025-11-17T05:48:30 | https://www.reddit.com/r/LocalLLaMA/comments/1oz8fu5/tts_model_for_4gb_vram_and_16_gb_ram/ | ProNoostr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz8fu5 | false | null | t3_1oz8fu5 | /r/LocalLLaMA/comments/1oz8fu5/tts_model_for_4gb_vram_and_16_gb_ram/ | false | false | self | 13 | null |
Local, bring your own TTS API, document reader web app (EPUB/PDF/TXT/MD) | 31 | Sharing my latest release of **OpenReader WebUI v1.0.0**, an open-source, local-first text-to-speech document reader and audiobook exporter. There are many new features and improvements.
**What is OpenReader WebUI?**
* A Next.js web app for reading and listening to EPUB, PDF, TXT, Markdown, and DOCX files.
* Supports... | 2025-11-17T05:15:20 | https://v.redd.it/6wkde35m2r1g1 | richardr1126 | /r/LocalLLaMA/comments/1oz7upb/local_bring_your_own_tts_api_document_reader_web/ | 1970-01-01T00:00:00 | 0 | {} | 1oz7upb | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/6wkde35m2r1g1/DASHPlaylist.mpd?a=1766078126%2CNmZkYjE1YWY1MDhlNzQzNDUxMzhjZTA3ODM0Y2Q5ZWRiZmFhMGVjNmVkNTA0YTZmMTVkZmMxZjBhMzk0NGJiOA%3D%3D&v=1&f=sd', 'duration': 82, 'fallback_url': 'https://v.redd.it/6wkde35m2r1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oz7upb | /r/LocalLLaMA/comments/1oz7upb/local_bring_your_own_tts_api_document_reader_web/ | false | false | 31 | {'enabled': False, 'images': [{'id': 'c21hODg0NW0ycjFnMX884E5sIxJUdNnmG-19TVvOw4dMAlw7RXKXbhwvWlzZ', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/c21hODg0NW0ycjFnMX884E5sIxJUdNnmG-19TVvOw4dMAlw7RXKXbhwvWlzZ.png?width=108&crop=smart&format=pjpg&auto=webp&s=c9b8f26dcebb36cb000139e00b76e4a6bb698... | |
PC with NPU, how do I use it? | 1 | [removed] | 2025-11-17T04:54:39 | https://www.reddit.com/r/LocalLLaMA/comments/1oz7guq/pc_with_npu_how_do_i_use_it/ | plsLetMeIn41 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz7guq | false | null | t3_1oz7guq | /r/LocalLLaMA/comments/1oz7guq/pc_with_npu_how_do_i_use_it/ | false | false | self | 1 | null |
On-device 100-session AI memory vault—xAI validating. Local LLM integration ideas? | 0 | NuraVault: Python/Kivy build—150 blocks FIFO, export 100%, wrong-key lockdown. Pro moods cue recall without resets.
u/grok probed/validated: "Compelling... NDA path open." Demo + proofs: [https://youtu.be/mgFcCrFrbr0](https://youtu.be/mgFcCrFrbr0) TXID/SHA256 on X thread.
Local LLM fit? Thoughts? #nuravault | 2025-11-17T04:37:47 | https://www.reddit.com/r/LocalLLaMA/comments/1oz75ki/ondevice_100session_ai_memory_vaultxai_validating/ | Commercial_Dig_4574 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz75ki | false | null | t3_1oz75ki | /r/LocalLLaMA/comments/1oz75ki/ondevice_100session_ai_memory_vaultxai_validating/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'kYzkiq1gLxr4a8X_3BqVFGr0Yy0iapW72hdy_fHRAHw', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/kYzkiq1gLxr4a8X_3BqVFGr0Yy0iapW72hdy_fHRAHw.jpeg?width=108&crop=smart&auto=webp&s=8507e3c5c2fa42f89dc1b6c619814739a559e38b', 'width': 108}, {'height': 162, 'url': '... |
All 20,000 Epstein Files in text format available for download. | 49 | [https://huggingface.co/datasets/tensonaut/Epstein\_Files\_20K](https://huggingface.co/datasets/tensonaut/Epstein_Files_20K)
Used google Tesseract OCR to covert 20K images to txt. Total file size \~100MB | 2025-11-17T04:32:30 | https://www.reddit.com/r/LocalLLaMA/comments/1oz71vh/all_20000_epstein_files_in_text_format_available/ | tensonaut | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz71vh | false | null | t3_1oz71vh | /r/LocalLLaMA/comments/1oz71vh/all_20000_epstein_files_in_text_format_available/ | false | false | self | 49 | null |
GPT-5-pro is likely a universal agentic gateway / Large Agentic Model | 0 | This is a continuation of this [discussion](https://www.reddit.com/r/LocalLLaMA/comments/1oyulun/the_good_medium_bad_news_about_a_universal/) of universal agentic gateways (UAG). Large Agentic Model (LAM) might be a better name than UAG.
One indicator gpt-5-pro is a LAM is no cache read price on [OR](https://openro... | 2025-11-17T04:10:56 | https://www.reddit.com/r/LocalLLaMA/comments/1oz6msr/gpt5pro_is_likely_a_universal_agentic_gateway/ | kaggleqrdl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz6msr | false | null | t3_1oz6msr | /r/LocalLLaMA/comments/1oz6msr/gpt5pro_is_likely_a_universal_agentic_gateway/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '83m1J63oDlekoJLClnkISpnw3b8Dvj3lorVy0lPpIso', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/83m1J63oDlekoJLClnkISpnw3b8Dvj3lorVy0lPpIso.png?width=108&crop=smart&auto=webp&s=2fe89a7ff665f49166de258ac9bf71a59117a897', 'width': 108}, {'height': 113, 'url': 'h... |
What are you using your local models for ? | 5 | Are these personal projects or for a product usecase?
I have a M3 Ultra mac studio looking for some inspiration and also to better understand the usage models folks are doing.
Currently, I am using Qwen3 to do some automated trading. Would love to hear others use cases.
| 2025-11-17T04:07:13 | https://www.reddit.com/r/LocalLLaMA/comments/1oz6k5j/what_are_you_using_your_local_models_for/ | alvamsi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz6k5j | false | null | t3_1oz6k5j | /r/LocalLLaMA/comments/1oz6k5j/what_are_you_using_your_local_models_for/ | false | false | self | 5 | null |
Turns out LLM's can be consistent ..! | 3 | A Paper By Thinking Machines
[https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/](https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/) | 2025-11-17T03:46:09 | https://thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/ | DarkEngine774 | thinkingmachines.ai | 1970-01-01T00:00:00 | 0 | {} | 1oz65jy | false | null | t3_1oz65jy | /r/LocalLLaMA/comments/1oz65jy/turns_out_llms_can_be_consistent/ | false | false | default | 3 | {'enabled': False, 'images': [{'id': 'F9ylJGn-QDaHa8ucxpOeoqHmN6I_k8mg-ag90rKzmfs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/F9ylJGn-QDaHa8ucxpOeoqHmN6I_k8mg-ag90rKzmfs.png?width=108&crop=smart&auto=webp&s=900e6a4301324336d845619d97bf1ef42dea85c3', 'width': 108}, {'height': 113, 'url': 'h... |
JSON to TOON | 0 | Hey y'all,
My GitHub repo below has a comprehensive guide for JSON to TOON conversion.
[https://github.com/meetrais/JSON-to-TOON](https://github.com/meetrais/JSON-to-TOON) | 2025-11-17T03:35:02 | https://www.reddit.com/r/LocalLLaMA/comments/1oz5xld/json_to_toon/ | meetrais | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz5xld | false | null | t3_1oz5xld | /r/LocalLLaMA/comments/1oz5xld/json_to_toon/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'nBw_g2_JYm5vJz31BAFZpzhJDcVTkzx2g2zhq8Ji3lc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/nBw_g2_JYm5vJz31BAFZpzhJDcVTkzx2g2zhq8Ji3lc.png?width=108&crop=smart&auto=webp&s=c3846db3f6d9a1d43941201c83f32c9959f8468e', 'width': 108}, {'height': 216, 'url': '... |
ChatGPT understands its creator | 443 | Even ChatGPT knows "Open Source" seems unlikely when it comes to OpenAI | 2025-11-17T03:27:05 | mtmttuan | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oz5rsw | false | null | t3_1oz5rsw | /r/LocalLLaMA/comments/1oz5rsw/chatgpt_understands_its_creator/ | false | false | 443 | {'enabled': True, 'images': [{'id': 'ebznEkU1pp8Kvlzim1DKyIFnW1xzZKsQLRE0LnWbtbo', 'resolutions': [{'height': 126, 'url': 'https://preview.redd.it/wkig4aaykq1g1.png?width=108&crop=smart&auto=webp&s=808e480d50567f206cd92e8ae8baf4cf85e7cc0c', 'width': 108}, {'height': 253, 'url': 'https://preview.redd.it/wkig4aaykq1g1.pn... | ||
looking for a technical cofounder, building something big | 0 | I’m working on an AI product
this isn’t productivity, automation, SaaS, or another wrapper.
It’s emotional, personal, and has global scale baked in.
I’ve already
validated demand through real world interviews
collected early data
refined core concept and direction
build a framework around it
now i need technical... | 2025-11-17T03:19:27 | https://www.reddit.com/r/LocalLLaMA/comments/1oz5m5d/looking_for_a_technical_cofounder_building/ | GovernmentLivid9482 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz5m5d | false | null | t3_1oz5m5d | /r/LocalLLaMA/comments/1oz5m5d/looking_for_a_technical_cofounder_building/ | false | false | self | 0 | null |
PCIE Bifurcation - More than 4 GPUs on a consumer motherboard | 5 | Has anyone been able to get a consumer motherboard to connect to more than 4 GPUs. I have an Intel Core i7-14700F on an ASUS Prime Z790-P that has 3 PCIE Gen4 X16 slots running at X4 via chipset and 1 PCIE Gen4 X16 slot running at X16. I have 4 Radeon 7900xtx GPUs connected to the 4 existing X16 slots via short riser... | 2025-11-17T02:27:59 | https://www.reddit.com/r/LocalLLaMA/comments/1oz4ixs/pcie_bifurcation_more_than_4_gpus_on_a_consumer/ | Beautiful_Trust_8151 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz4ixs | false | null | t3_1oz4ixs | /r/LocalLLaMA/comments/1oz4ixs/pcie_bifurcation_more_than_4_gpus_on_a_consumer/ | false | false | self | 5 | null |
Prune vs Quantize | 7 | I'm looking at models around 100b. I noticed that a bunch of pruned models are being released. Has anyone tested how these perform against smaller quantizations?
For example, I'm curious which of these might perform better given that they are around the same size:
[MiniMax-M2-THRIFT-i1-GGUF:Q4\_K\_M](https://huggingf... | 2025-11-17T02:19:52 | https://www.reddit.com/r/LocalLLaMA/comments/1oz4cr1/prune_vs_quantize/ | Zc5Gwu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz4cr1 | false | null | t3_1oz4cr1 | /r/LocalLLaMA/comments/1oz4cr1/prune_vs_quantize/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'yr9tmojzzRZF6njbmVlpOOkV7VkQHnl1KJL4J_Q_zmI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/yr9tmojzzRZF6njbmVlpOOkV7VkQHnl1KJL4J_Q_zmI.png?width=108&crop=smart&auto=webp&s=642933c4d33d2285cf9528c7bbfe9b629dd1cf8a', 'width': 108}, {'height': 116, 'url': 'h... |
How I cut my chat's perceived Time-to-First-Token by 50% by adding a cheaper GPU (Llama-Swap + Persistent Models) | 38 | I just wanted to share something that I've been noticing and experiencing more and more as models get bigger and systems get more complicated for local AI.
Because we enthusiasts do not have the large quantities of pooled vRAM like corporations do or the armies of developers to build things, we piece the bricks togeth... | 2025-11-17T01:38:22 | https://www.reddit.com/r/LocalLLaMA/comments/1oz3hfx/how_i_cut_my_chats_perceived_timetofirsttoken_by/ | ubrtnk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz3hfx | false | null | t3_1oz3hfx | /r/LocalLLaMA/comments/1oz3hfx/how_i_cut_my_chats_perceived_timetofirsttoken_by/ | false | false | 38 | null | |
Suggestions for RAG prompt rewriters and rerankers? | 5 | Hey, I've got a local RAG pipeline with Qdrant, Chonkie, and BGE Large, but I haven't been able to find a whole lot of recent info on rerankers, and I've also been hearing a lot about prompt rewriters being used for RAG. Note that this project must adhere to strict GDPR and cannot use any off-site APIs (everything in t... | 2025-11-17T01:14:31 | https://www.reddit.com/r/LocalLLaMA/comments/1oz2z69/suggestions_for_rag_prompt_rewriters_and_rerankers/ | CommunityTough1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz2z69 | false | null | t3_1oz2z69 | /r/LocalLLaMA/comments/1oz2z69/suggestions_for_rag_prompt_rewriters_and_rerankers/ | false | false | self | 5 | null |
When I use the llama.cpp webUI with a multimodal, I can upload a picture and ask a question about it quite quickly but when I try to do the same via API, it converts it to base64 and it takes forever and sometimes it hallucinates. | 2 | I tried asking my vibe friend but no fix there. The API is the same model server as my llama-server webUI so it should act the same. maybe it's not sending the file the same way? | 2025-11-17T00:50:09 | https://www.reddit.com/r/LocalLLaMA/comments/1oz2fqu/when_i_use_the_llamacpp_webui_with_a_multimodal_i/ | oodelay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz2fqu | false | null | t3_1oz2fqu | /r/LocalLLaMA/comments/1oz2fqu/when_i_use_the_llamacpp_webui_with_a_multimodal_i/ | false | false | self | 2 | null |
Question about how building llama.cpp works | 5 | Do I have to build llama.cpp with CUDA to get it to run models with the Nvidia GPU in my laptop? Or is there a cli command or flag I can use to get llama.cpp to use the Nvidia GPU? | 2025-11-17T00:41:20 | https://www.reddit.com/r/LocalLLaMA/comments/1oz28r8/question_about_how_building_llamacpp_works/ | VegetableJudgment971 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz28r8 | false | null | t3_1oz28r8 | /r/LocalLLaMA/comments/1oz28r8/question_about_how_building_llamacpp_works/ | false | false | self | 5 | null |
Free Web Search Tool for ai. | 2 | So I thinking to make my llm web search enabled but the tools out there are expensive. Like tavily , serpAI, firecrwal.
So I decided to make my own fully free. Unlimited Use. Not back tracking. And fully secure.
Here check it out --
https://github.com/ankushthakur2007/miyami_websearch_tool
It's MCP server --
h... | 2025-11-17T00:37:00 | https://www.reddit.com/r/LocalLLaMA/comments/1oz2589/free_web_search_tool_for_ai/ | Any-Supermarket1248 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz2589 | false | null | t3_1oz2589 | /r/LocalLLaMA/comments/1oz2589/free_web_search_tool_for_ai/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'lHUtKzh2TXhpRZrHumQO3H78VxiVuYs5cUP3SDgZmgE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/lHUtKzh2TXhpRZrHumQO3H78VxiVuYs5cUP3SDgZmgE.png?width=108&crop=smart&auto=webp&s=88e82cf97bd7ff33a3e2afc0e6581920147f7464', 'width': 108}, {'height': 108, 'url': 'h... |
RAISE-26: The World’s Strongest AI + NLP Competition Is Here! Cash Prizes + Priority Registration Open! | 0 | Hi everyone! **👋**
I’m excited to share that Rutgers Bloustein School is hosting RAISE-26, the world’s strongest AI-NLP informatics competition: registration is officially open!
Register here: [**https://go.rutgers.edu/raise-26-now**](https://go.rutgers.edu/raise-26-now)
More Information on RAISE-26: [https://go.... | 2025-11-17T00:16:21 | https://www.reddit.com/r/LocalLLaMA/comments/1oz1otn/raise26_the_worlds_strongest_ai_nlp_competition/ | Working-Comb-4378 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz1otn | false | null | t3_1oz1otn | /r/LocalLLaMA/comments/1oz1otn/raise26_the_worlds_strongest_ai_nlp_competition/ | false | false | 0 | null | |
Image generation, training? | 1 | So I want all of my d&d characters I'm going to generate to look like their players. What does the process look like for training my friends photos into an AI model?
Currently running a 12 gig 3060 on 128 gig ram system. | 2025-11-17T00:12:34 | https://www.reddit.com/r/LocalLLaMA/comments/1oz1lsi/image_generation_training/ | Beneficial-Claim-381 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz1lsi | false | null | t3_1oz1lsi | /r/LocalLLaMA/comments/1oz1lsi/image_generation_training/ | false | false | self | 1 | null |
[Looking for model suggestion] <=32GB reasoning model but strong with tool-calling? | 13 | I have an MCP server with several tools that need to be called in a sequence. No matter which non-thinking model I use, even Qwen3-VL-32B-Q6 (the strongest I can fit in VRAM for my other tests), they will miss one or two calls.
Here's what I'm finding:
- **Qwen3-30B-2507-Thinking Q6** - works but very often enters ex... | 2025-11-16T23:23:16 | https://www.reddit.com/r/LocalLLaMA/comments/1oz0isk/looking_for_model_suggestion_32gb_reasoning_model/ | ForsookComparison | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz0isk | false | null | t3_1oz0isk | /r/LocalLLaMA/comments/1oz0isk/looking_for_model_suggestion_32gb_reasoning_model/ | false | false | self | 13 | null |
Faster Maya1 tts model, can generate 50seconds of audio in a single second | 57 | Recently, Maya1 was released which was a new tts model that can generate sound effects(laughter, sighs, gulps…), realistic emotional speech, and also accepts a description of a voice. It was pretty slow though so I optimized it using lmdeploy and also increased quality by using an audio upsampler.
## Key improvements ... | 2025-11-16T23:08:14 | https://www.reddit.com/r/LocalLLaMA/comments/1oz05ww/faster_maya1_tts_model_can_generate_50seconds_of/ | SplitNice1982 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oz05ww | false | null | t3_1oz05ww | /r/LocalLLaMA/comments/1oz05ww/faster_maya1_tts_model_can_generate_50seconds_of/ | false | false | self | 57 | {'enabled': False, 'images': [{'id': 'OzIuPJ220C_51ae-ZhVllWGPZkdIWugY7aGgplG2IiQ', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OzIuPJ220C_51ae-ZhVllWGPZkdIWugY7aGgplG2IiQ.png?width=108&crop=smart&auto=webp&s=921bb297e66f7d2d0783dfa59f9700e77a7b1912', 'width': 108}, {'height': 108, 'url': 'h... |
I made an on-device AI TTS extension that runs AI voice inference in your browser | 7 | It uses Kokoro TTS (a tiny 82M parameter model that's the current #1 open source TTS model and highly competitive even among closed source models) and runs more than 4x realtime on my M2 Macbook. It's a wrapper around kokoro.js, the WebGPU implementation of Kokoro.
I made it because every other TTS extension I could f... | 2025-11-16T23:04:52 | https://v.redd.it/kpzf4h8u8p1g1 | Duoquinquagintillion | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oz031w | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/kpzf4h8u8p1g1/DASHPlaylist.mpd?a=1765926309%2CNmQ4ZTdkOTgwYjU0OThmNmY4ODFhOTM4NGQ3NWYxNzhhMzgxZjQ5OGQ4ZDJmMTg3YTk3MjFlODcyZTVmMDFiYQ%3D%3D&v=1&f=sd', 'duration': 79, 'fallback_url': 'https://v.redd.it/kpzf4h8u8p1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oz031w | /r/LocalLLaMA/comments/1oz031w/i_made_an_ondevice_ai_tts_extension_that_runs_ai/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'amh0eXpnOHU4cDFnMXcE2OB-fDULB3TeTWtoKgelbELB5YNtAiEGqWIp4X1G', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/amh0eXpnOHU4cDFnMXcE2OB-fDULB3TeTWtoKgelbELB5YNtAiEGqWIp4X1G.png?width=108&crop=smart&format=pjpg&auto=webp&s=8dded4b0202fe0dcc1de4660f87dc320fd12b... | |
Local AI | 0 | 2025-11-16T23:03:17 | Emotional-Menu5818 | i.imgur.com | 1970-01-01T00:00:00 | 0 | {} | 1oz01pt | false | null | t3_1oz01pt | /r/LocalLLaMA/comments/1oz01pt/local_ai/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'sjfSHF75GC9RuVyqBsa5yoQ1Pg7adTwzbBja_Y8li8s', 'resolutions': [{'height': 110, 'url': 'https://external-preview.redd.it/sjfSHF75GC9RuVyqBsa5yoQ1Pg7adTwzbBja_Y8li8s.jpeg?width=108&crop=smart&auto=webp&s=67b1fb4536602b12421b4bd5623bff93f9bc3c6f', 'width': 108}, {'height': 221, 'url': '... | ||
LLM vs. CNIA(theoretical） | 0 | The gain and the wane are from the same source.
| 2025-11-16T22:49:06 | Hefty_Document_9466 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyzpdr | false | null | t3_1oyzpdr | /r/LocalLLaMA/comments/1oyzpdr/llm_vs_cniatheoretical/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '9q197krc7p1g1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/9q197krc7p1g1.jpeg?width=108&crop=smart&auto=webp&s=178f458b9cfa0e3de1e07f4fd20e3eb4c29e62f4', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/9q197krc7p1g1.jpeg?width=216&crop=smart&auto=... | |
My "AI at Home" rig | 56 | Following on the trend of "we got AI at home" - this is my setup.
The motherboard is an Asus X99-E WS with the PLX chips so all 4 GPUs run at "x16" - it has 128 GB DDR4 ECC ram and an Intel Xeon E5-1680v4. Won't win any records but was relatively cheap and more than enough for most uses - I have a bunch of CPU compute... | 2025-11-16T22:02:06 | https://www.reddit.com/r/LocalLLaMA/comments/1oyyk3k/my_ai_at_home_rig/ | cookinwitdiesel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyyk3k | false | null | t3_1oyyk3k | /r/LocalLLaMA/comments/1oyyk3k/my_ai_at_home_rig/ | false | false | 56 | null | |
ERA: Open-Source Secure Sandboxing for Running AI Agents Locally 🔒🤖 | 4 | I co-built [ERA](https://github.com/BinSquare/ERA), an open-source sandbox that lets you run AI agents safely and locally in isolated micro-VMs. It supports multiple languages, persistent sessions, and works great paired with local LLMs like Ollama.
If you want to ditch cloud APIs and keep full control of your AI work... | 2025-11-16T22:00:59 | https://www.reddit.com/r/LocalLLaMA/comments/1oyyj33/era_opensource_secure_sandboxing_for_running_ai/ | Practical-Tune-440 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyyj33 | false | null | t3_1oyyj33 | /r/LocalLLaMA/comments/1oyyj33/era_opensource_secure_sandboxing_for_running_ai/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'xS0Lm6OiJZ8QWAjotVG8R9aCyHuMh9zQwPusQuV1nEg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xS0Lm6OiJZ8QWAjotVG8R9aCyHuMh9zQwPusQuV1nEg.png?width=108&crop=smart&auto=webp&s=7647cbdffe9c5b5b2f780fa56b11385cdbbb79c9', 'width': 108}, {'height': 108, 'url': 'h... |
I want to run a tiny model on a tiny webserver, simply to understand some knowledge base documents and be able to answer questions on them. Is it possible? | 1 | Think: a handful of knowledge base articles, a VPS server on Digital Ocean, and a simple model parsing the articles, able to answer basic questions.
Sorry if this is a noob question! | 2025-11-16T21:55:01 | https://www.reddit.com/r/LocalLLaMA/comments/1oyydqc/i_want_to_run_a_tiny_model_on_a_tiny_webserver/ | adammench | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyydqc | false | null | t3_1oyydqc | /r/LocalLLaMA/comments/1oyydqc/i_want_to_run_a_tiny_model_on_a_tiny_webserver/ | false | false | self | 1 | null |
Open-source RAG/LLM evaluation framework; would love feedback 🫶🏽 | 7 | Hallo from Berlin,
I'm one of the founders of Rhesis, an open-source testing platform for LLM applications. Just shipped v0.4.2 with zero-config Docker Compose setup (literally ./rh start and you're running). Built it because we got frustrated with high-effort setups for evals. Everything runs locally - no API keys.
... | 2025-11-16T21:43:45 | https://www.reddit.com/r/LocalLLaMA/comments/1oyy3z6/opensource_ragllm_evaluation_framework_would_love/ | IOnlyDrinkWater_22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyy3z6 | false | null | t3_1oyy3z6 | /r/LocalLLaMA/comments/1oyy3z6/opensource_ragllm_evaluation_framework_would_love/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'c9fT2-27kH8Zxd6Eks53o13TqT96FVovZoGPoneiwJw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/c9fT2-27kH8Zxd6Eks53o13TqT96FVovZoGPoneiwJw.png?width=108&crop=smart&auto=webp&s=c5fcf3e9521963c4d893dba734e0bb7f066c2c30', 'width': 108}, {'height': 108, 'url': 'h... |
AMD Ryzen AI Max 395+ 256/512 GB Ram? | 252 | I’m looking at the new AI boxes using the Ryzen AI Max+ 395 (GMKtec EVO-X2, Minisforum’s upcoming units, etc.) and I’m wondering if we’ll actually see higher-end RAM configs — specifically 256GB or even 512GB LPDDR5X.
Right now most spec sheets cap out at 128GB LPDDR5X, but the platform itself has a very wide memory b... | 2025-11-16T21:39:50 | quantier | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyy0fy | false | null | t3_1oyy0fy | /r/LocalLLaMA/comments/1oyy0fy/amd_ryzen_ai_max_395_256512_gb_ram/ | false | false | default | 252 | {'enabled': True, 'images': [{'id': 'xb6obe00vo1g1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/xb6obe00vo1g1.jpeg?width=108&crop=smart&auto=webp&s=e4a4d9d72374ec584555485363f3c4ed4f2ae600', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/xb6obe00vo1g1.jpeg?width=216&crop=smart&auto=... | |
El mejor hardware local ( comercial ) para coding | 0 | Que tal a todos este es mi primer post en reddit en general nunca habia hecho algo asi asi que agradezco a las personas que me pueda ayudar
llevo 10 años programando salio el vibecoding y claro que me ayudo prds , vibe , generacion de codigo es excelente
ultimamente uso mucho estas desde claude con 200 max y codex ... | 2025-11-16T21:37:17 | https://www.reddit.com/r/LocalLLaMA/comments/1oyxy79/el_mejor_hardware_local_comercial_para_coding/ | Grouchy_Key6227 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyxy79 | false | null | t3_1oyxy79 | /r/LocalLLaMA/comments/1oyxy79/el_mejor_hardware_local_comercial_para_coding/ | false | false | self | 0 | null |
How RLHF turns local LLMs into anxious people-pleasers | 0 |
I keep coming back to this picture for how we train a lot of models, including local ones:
You start with a strong base model. It is messy, curious, and a bit unhinged in a good way. It knows a ton of stuff, it will happily speculate, and it is not scared of being weird.
Then RLHF shows up like a strict parent.
Most... | 2025-11-16T20:56:24 | 1Hesham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oywxmc | false | null | t3_1oywxmc | /r/LocalLLaMA/comments/1oywxmc/how_rlhf_turns_local_llms_into_anxious/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '4naj2iz8no1g1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/4naj2iz8no1g1.png?width=108&crop=smart&auto=webp&s=c9a3e2d4e34123403853a351729f0c7ae0ec5bda', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/4naj2iz8no1g1.png?width=216&crop=smart&auto=we... | |
What are the latest good LLMs? | 58 | It felt there was a major release every other week, but now there is a bit of quiet period?
Am I missing something? | 2025-11-16T20:36:58 | https://www.reddit.com/r/LocalLLaMA/comments/1oywg01/what_are_the_latest_good_llms/ | idleWizard | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oywg01 | false | null | t3_1oywg01 | /r/LocalLLaMA/comments/1oywg01/what_are_the_latest_good_llms/ | false | false | self | 58 | null |
Looking for a truly open source web ui for using with my LLMs | 9 | Hi, im looking for a web ui with mcp support for connecting them to my llms. Now, I have both apis and locally running model. I want a web ui for them. What do you guys recommend ?
| 2025-11-16T19:44:24 | https://www.reddit.com/r/LocalLLaMA/comments/1oyv36m/looking_for_a_truly_open_source_web_ui_for_using/ | sadism_popsicle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyv36m | false | null | t3_1oyv36m | /r/LocalLLaMA/comments/1oyv36m/looking_for_a_truly_open_source_web_ui_for_using/ | false | false | self | 9 | null |
If HF really does get bought out, this is my plan. | 0 | # The people/governance, the funding, the infrastructure/distribution:
# The people
You’d have a core group of “not billionaires, but definitely not broke” AI folks who are free agents and not beholden to any of the Mag7 or foundation model providers. Off the top of my head:
* **Ilya Sutskever** – co-running Safe Su... | 2025-11-16T19:40:27 | https://www.reddit.com/r/LocalLLaMA/comments/1oyuzhj/if_hf_really_does_get_bought_out_this_is_my_plan/ | coloradical5280 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyuzhj | false | null | t3_1oyuzhj | /r/LocalLLaMA/comments/1oyuzhj/if_hf_really_does_get_bought_out_this_is_my_plan/ | false | false | self | 0 | null |
Have you wondered about the cost of using an API from a model provider like Anthropic? | 6 | Let's suppose claude sonnet 4.0 has 700b params and 32b active parameters . How much does it cost approximately to train for one training run if you rent the gpus by bulk or you own it? And the inference cost?
Suppose it was trained on 15 trillion tokens(including distilled) and 32 b active and sometimes you have 1.5x... | 2025-11-16T19:34:01 | https://www.reddit.com/r/LocalLLaMA/comments/1oyutli/have_you_wondered_about_the_cost_of_using_an_api/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyutli | false | null | t3_1oyutli | /r/LocalLLaMA/comments/1oyutli/have_you_wondered_about_the_cost_of_using_an_api/ | false | false | self | 6 | null |
The good, medium, bad news about a Universal Agentic Gateway to Open Weight Models | 1 | I posted about the basic idea [here](https://www.reddit.com/r/LocalLLaMA/comments/1oygsii/could_the_universe_of_open_source_models/).
A **Universal Agentic Gateway (UAG)** is one which exposes an endpoint to an agentic flow that will handle almost anything thrown at it, a sort of agentic MoE, achieving SOTA capabili... | 2025-11-16T19:25:18 | https://www.reddit.com/r/LocalLLaMA/comments/1oyulun/the_good_medium_bad_news_about_a_universal/ | kaggleqrdl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyulun | false | null | t3_1oyulun | /r/LocalLLaMA/comments/1oyulun/the_good_medium_bad_news_about_a_universal/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Cg2oWdefDiKRkAEcYC46mqBVOCwZkefz0LtIHas3iKk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Cg2oWdefDiKRkAEcYC46mqBVOCwZkefz0LtIHas3iKk.png?width=108&crop=smart&auto=webp&s=3b20584a9c4ef7e9041fc18bdaad943afd8bd07c', 'width': 108}, {'height': 108, 'url': 'h... |
I triggered DeepSeek (DeepThink on website version) to repeat thinking infinitely | 0 | So I was trying to find out the exact amortization in the time complexity of my code, I gave the prompt (shown in image) to deepseek with deepthink on, this triggered the model to dryrun on some examples but then got stuck on an infinite loop of the same reasoning till the context window got exhausted, hints at a funda... | 2025-11-16T19:07:21 | https://www.reddit.com/r/LocalLLaMA/comments/1oyu5f0/i_triggered_deepseek_deepthink_on_website_version/ | Harsh_Saini10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyu5f0 | false | null | t3_1oyu5f0 | /r/LocalLLaMA/comments/1oyu5f0/i_triggered_deepseek_deepthink_on_website_version/ | false | false | 0 | null | |
Why no one helps on reddit anymore? | 0 | Why no one helps on reddit anymore? | 2025-11-16T18:59:11 | https://www.reddit.com/r/LocalLLaMA/comments/1oytxov/why_no_one_helps_on_reddit_anymore/ | Informal-Victory8655 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oytxov | false | null | t3_1oytxov | /r/LocalLLaMA/comments/1oytxov/why_no_one_helps_on_reddit_anymore/ | false | false | self | 0 | null |
[MCP] Open-sourced a CSV-to-PostgreSQL loader server (vibe-coded with Claude) | 5 | Built an MCP server that gives Claude the ability to load CSV files into PostgreSQL databases. Thought the community might find it useful since we're all experimenting with MCP now.
Technical overview:
\- Full data validation (schema inference, type detection, encoding)
\- Uses PostgreSQL COPY for efficient... | 2025-11-16T18:52:04 | https://www.reddit.com/r/LocalLLaMA/comments/1oytr1t/mcp_opensourced_a_csvtopostgresql_loader_server/ | mylocalai | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oytr1t | false | null | t3_1oytr1t | /r/LocalLLaMA/comments/1oytr1t/mcp_opensourced_a_csvtopostgresql_loader_server/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'i84pQzCUOyqhaq1_npiRQFV5DYMvfrClDz01WHpf8ys', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/i84pQzCUOyqhaq1_npiRQFV5DYMvfrClDz01WHpf8ys.png?width=108&crop=smart&auto=webp&s=50fd2f09bf237d7f339604590dee0b8f635a98f5', 'width': 108}, {'height': 108, 'url': 'h... |
Old computer, quad channel memory, is it worth anything? | 0 | I never considered this until researching just now but, people mentioned quad channel memory on a CPU can be pretty useful?
I've got an old i7 extreme on a big bang x power 2 board with quad channel memory, 64 gigs.
It's got seven pcie x16 Lanes but I never considered this thing because of how old it is
Is it wor... | 2025-11-16T18:50:30 | https://www.reddit.com/r/LocalLLaMA/comments/1oytplm/old_computer_quad_channel_memory_is_it_worth/ | Beneficial-Claim-381 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oytplm | false | null | t3_1oytplm | /r/LocalLLaMA/comments/1oytplm/old_computer_quad_channel_memory_is_it_worth/ | false | false | self | 0 | null |
Is it normal that my 'quick LLaMA test' turned into a 48-hour GPU hostage situation? | 47 | I told myself I'd just run a small model last night.. Next thin I know, I'm quantizing, tweaking prompts, benchmarking, and now my GPU sounds like its prepating for orbit.
Does anyone else start with a tiny experiment and end up rewriting half their setup at 3AM? | 2025-11-16T18:34:16 | https://www.reddit.com/r/LocalLLaMA/comments/1oytajt/is_it_normal_that_my_quick_llama_test_turned_into/ | Future_Draw5416 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oytajt | false | null | t3_1oytajt | /r/LocalLLaMA/comments/1oytajt/is_it_normal_that_my_quick_llama_test_turned_into/ | false | false | self | 47 | null |
Downloaded one model for ‘testing’… somehow ended up with 120GB of checkpoints. | 12 | I swear I only wanted to try a single 8B.
Now my SSD is crying, and I’m organizing models like Pokémon cards.
Does model-hoarding become a problem, or is this just part of the LocalLLaMA lifestyle? | 2025-11-16T18:27:37 | https://www.reddit.com/r/LocalLLaMA/comments/1oyt4gn/downloaded_one_model_for_testing_somehow_ended_up/ | Dry_Significance9132 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyt4gn | false | null | t3_1oyt4gn | /r/LocalLLaMA/comments/1oyt4gn/downloaded_one_model_for_testing_somehow_ended_up/ | false | false | self | 12 | null |
Can you evaluate my cloned voice sample? Looking for feedback on naturalness and clarity. | 1 | Hi everyone,
I’ve generated a short audio sample using a cloned version of my voice, and I’d really appreciate some feedback from people who have experience with TTS, voice cloning, and speech synthesis.
The style is intentionally dark, calm, and slightly monotone — it’s meant for philosophical narration (think Mach... | 2025-11-16T17:58:51 | https://www.reddit.com/r/LocalLLaMA/comments/1oysdbc/can_you_evaluate_my_cloned_voice_sample_looking/ | EducationalWork3642 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oysdbc | false | null | t3_1oysdbc | /r/LocalLLaMA/comments/1oysdbc/can_you_evaluate_my_cloned_voice_sample_looking/ | false | false | self | 1 | null |
Built a medical Llama-3 agent (Ollama) that does triage, OCR, and WHO-guided reasoning | 0 | I’ve been experimenting with Llama-3 + Ollama and ended up building a mini AI cardiologist called "DoctorAI".
Highlights:
• Real-time symptom triage (Level 1/2/3)
• Local JSON medical knowledge base
• Streaming output
• OCR for medical reports
• Safety guardrails (consent + anonymization)
It’s purely edu... | 2025-11-16T17:43:00 | https://www.reddit.com/r/LocalLLaMA/comments/1oyryj8/built_a_medical_llama3_agent_ollama_that_does/ | Qwave_Sync | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyryj8 | false | null | t3_1oyryj8 | /r/LocalLLaMA/comments/1oyryj8/built_a_medical_llama3_agent_ollama_that_does/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'tmHw6bkWW6_HDIJGE7rn6r66oM5NalhtalAbLth2098', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/tmHw6bkWW6_HDIJGE7rn6r66oM5NalhtalAbLth2098.png?width=108&crop=smart&auto=webp&s=5a20f3b06383d7e4b5f72d720ddb09482ac792ee', 'width': 108}, {'height': 108, 'url': 'h... |
Any known benchmarks for longer multi-turn instruction following performance tests to compare open weight models (someone maybe tried IFScale tests)? | 0 | [deepagent](https://github.com/langchain-ai/deepagents) fork I am playing with on local models to develop understanding of cli agents and fun!
While trying out different models (gpt-oss-20b which was pretty fast vs gpt-oss-120b better with tool calls out of the box each) served through llama.cpp on dgx-spark (might ge... | 2025-11-16T17:05:23 | here_n_dere | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyqzvg | false | null | t3_1oyqzvg | /r/LocalLLaMA/comments/1oyqzvg/any_known_benchmarks_for_longer_multiturn/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '0kw3ze3uhn1g1', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/0kw3ze3uhn1g1.png?width=108&crop=smart&auto=webp&s=065d4723a6ac986f8801b5e668480a14f46fded7', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/0kw3ze3uhn1g1.png?width=216&crop=smart&auto=web... | |
Created custom UI for our built-in LLM browser | 1 | Previously, I shared some updates on my custom browser with a built-in vision model showing browser automation. Now I have created a UI for the browser and explained why I created a custom UI and did not use what Chromium already offers.
Any suggestions and feature ideas are welcome. | 2025-11-16T17:01:25 | https://www.youtube.com/watch?v=NCrSsXAZVwU | ahstanin | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1oyqw4k | false | {'oembed': {'author_name': 'Olib AI', 'author_url': 'https://www.youtube.com/@Olibaicom', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/NCrSsXAZVwU?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; pic... | t3_1oyqw4k | /r/LocalLLaMA/comments/1oyqw4k/created_custom_ui_for_our_builtin_llm_browser/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'e99kwlHrgz1H9g8n4LCKIonsmFpKQuICBe-vgmJORww', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/e99kwlHrgz1H9g8n4LCKIonsmFpKQuICBe-vgmJORww.jpeg?width=108&crop=smart&auto=webp&s=7a0fe253a8fb47ca860e465a73c149d1e74f579e', 'width': 108}, {'height': 162, 'url': '... |
I asked meta AI to translate my last messages in english, he gave me his entire system prompt | 93 | Hi everyone,
I was organizing my birthday in a WhatsApp group, and since I have a few English-speaking friends, I asked a friend to translate my last messages into English. He accidentally leaked his entire system prompt. Here it is:
I'll translate our convo so far:
- You: "You are an expert conversationalist made b... | 2025-11-16T17:01:21 | https://www.reddit.com/r/LocalLLaMA/comments/1oyqw1n/i_asked_meta_ai_to_translate_my_last_messages_in/ | amt_42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyqw1n | false | null | t3_1oyqw1n | /r/LocalLLaMA/comments/1oyqw1n/i_asked_meta_ai_to_translate_my_last_messages_in/ | false | false | self | 93 | null |
Any known benchmarks for longer instruction following performance to test open weight models (someone maybe tried IFScale tests)? | 1 | [deepagent](https://github.com/langchain-ai/deepagents) fork I am playing with on local models to develop understanding of cli agents and fun! | 2025-11-16T16:51:51 | here_n_dere | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyqn7z | false | null | t3_1oyqn7z | /r/LocalLLaMA/comments/1oyqn7z/any_known_benchmarks_for_longer_instruction/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'cctj2j19fn1g1', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/cctj2j19fn1g1.png?width=108&crop=smart&auto=webp&s=6d4db4ee86f7a2e7a29d84e5a1e7b23379849eed', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/cctj2j19fn1g1.png?width=216&crop=smart&auto=web... | |
A more surgical approach to abliteration | 163 | Abliteration is known to be damaging to models. I had a think about why, and decided to explore ways to eliminate as many possible disruptions to model performance when following the harmless direction. In short, if it ain't broke, don't fix it.
The first insight after some cosine-similarity analysis was that there wa... | 2025-11-16T16:22:15 | https://www.reddit.com/r/LocalLLaMA/comments/1oypwa7/a_more_surgical_approach_to_abliteration/ | grimjim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oypwa7 | false | null | t3_1oypwa7 | /r/LocalLLaMA/comments/1oypwa7/a_more_surgical_approach_to_abliteration/ | false | false | self | 163 | {'enabled': False, 'images': [{'id': 'Tc_qgqCdWDRDbv-8YZsnlSgbXJ-3FpSifiHhTLDNX94', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Tc_qgqCdWDRDbv-8YZsnlSgbXJ-3FpSifiHhTLDNX94.png?width=108&crop=smart&auto=webp&s=f5afeda675673481ae63040bc142f57140def3be', 'width': 108}, {'height': 116, 'url': 'h... |
Small benchmark I ran today: structured chains caused 30–45% more hallucinations | 0 | Ran a tiny experiment today while testing tool-use + validation loops in an LLM workflow.
I compared:
**Setup A — Loose chain**
* free-form reasoning
* no forced schema
* model allowed to think “messily”
**Setup B — Strict chain**
* rigid step-by-step format
* fixed schema + validator
* forced tool arguments + cle... | 2025-11-16T15:20:03 | https://www.reddit.com/r/LocalLLaMA/comments/1oyocbp/small_benchmark_i_ran_today_structured_chains/ | SouthAlarmed2275 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyocbp | false | null | t3_1oyocbp | /r/LocalLLaMA/comments/1oyocbp/small_benchmark_i_ran_today_structured_chains/ | false | false | self | 0 | null |
Need help choosing RAM for Threadripper AI/ML workstation | 1 | I am building an AI/ML server for experimentation, prototyping, and possibly production use by a small team (4-6 people). It has a Threadripper 9960X in a TRX50 motherboard with two (2) RTX 5090 GPUs.
I have two ECC RDIMM kits: "Kit A" 4x32GB DDR5-6400 EXPO 32-39-39-104 1.35V and "Kit B" 4x48GB DDR5-6400 EXPO 32-39-... | 2025-11-16T14:57:53 | https://www.reddit.com/r/LocalLLaMA/comments/1oynskc/need_help_choosing_ram_for_threadripper_aiml/ | Mephistophlz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oynskc | false | null | t3_1oynskc | /r/LocalLLaMA/comments/1oynskc/need_help_choosing_ram_for_threadripper_aiml/ | false | false | self | 1 | null |
A simple communication system for LLM modules I’ve been working on | 1 | [removed] | 2025-11-16T14:56:14 | https://www.reddit.com/r/LocalLLaMA/comments/1oynr5n/a_simple_communication_system_for_llm_modules_ive/ | Electrical_Key3019 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oynr5n | false | null | t3_1oynr5n | /r/LocalLLaMA/comments/1oynr5n/a_simple_communication_system_for_llm_modules_ive/ | false | false | self | 1 | null |
Local K2 thinking with sglang problem: the model frequently output without content, put everything in reasoning_content; or gives unpaired <think> tag | 3 | Any help? | 2025-11-16T14:40:13 | https://www.reddit.com/r/LocalLLaMA/comments/1oyndck/local_k2_thinking_with_sglang_problem_the_model/ | Parking-Extreme5147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyndck | false | null | t3_1oyndck | /r/LocalLLaMA/comments/1oyndck/local_k2_thinking_with_sglang_problem_the_model/ | false | false | self | 3 | null |
Bro and I thought I was an overthinker! vibeTHINKER on LM studio with no instructions. | 88 | 2025-11-16T14:31:38 | https://v.redd.it/05u315bwpm1g1 | Sufficient-Brain-371 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyn66k | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/05u315bwpm1g1/DASHPlaylist.mpd?a=1765895514%2CODgxM2YxYTM3YjZkMWExMmJiNTQ1OGU5MzUxZjU0NjkzNmI4ZDNmYzFmMzIzYjgyNGJkMTE4MWJhZmZiZmJhZA%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/05u315bwpm1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oyn66k | /r/LocalLLaMA/comments/1oyn66k/bro_and_i_thought_i_was_an_overthinker/ | false | false | 88 | {'enabled': False, 'images': [{'id': 'dGtpazk4Y3dwbTFnMSvUbfez8WIstXtj7zq-QhlQCt1-ymJnEFr5PFe7y4k1', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/dGtpazk4Y3dwbTFnMSvUbfez8WIstXtj7zq-QhlQCt1-ymJnEFr5PFe7y4k1.png?width=108&crop=smart&format=pjpg&auto=webp&s=e6d2e967c7990f70fd9d1df1e24328663312... | ||
Bro and I thought I was an overthinker! vibeTHINKER on LM studio with no instructions. | 1 | 2025-11-16T14:25:54 | https://v.redd.it/8u382u2epm1g1 | Big-Cartographer-873 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyn1ct | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/8u382u2epm1g1/DASHPlaylist.mpd?a=1765895170%2CYmQ2NWRmOTBjMTRhOWFkMTIyNzMzMmRkZmQ5MTZmZjcwNWRhMDZjMDZiZmQ2OGFkNzY0OTY5MTk3YTAzMGY3YQ%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/8u382u2epm1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oyn1ct | /r/LocalLLaMA/comments/1oyn1ct/bro_and_i_thought_i_was_an_overthinker/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'eXVhd2VyMmVwbTFnMSvUbfez8WIstXtj7zq-QhlQCt1-ymJnEFr5PFe7y4k1', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/eXVhd2VyMmVwbTFnMSvUbfez8WIstXtj7zq-QhlQCt1-ymJnEFr5PFe7y4k1.png?width=108&crop=smart&format=pjpg&auto=webp&s=1c5f4fa3ede91e9b5d524ffdbdba1dfc3aba... | ||
How to train a llm using comments from Youtube video or tiktok? | 8 | Hey guys, I’m working on training an AI similar to Neuro-sama, and I’m planning to collect some sample data from netizens.
Right now my idea is to use ChatGPT to help process large batches of online comments, extract useful question-and-answer pairs, and then feed them into my dataset.
If you have any better sugges... | 2025-11-16T14:25:25 | https://www.reddit.com/r/LocalLLaMA/comments/1oyn0xg/how_to_train_a_llm_using_comments_from_youtube/ | HowardJones_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyn0xg | false | null | t3_1oyn0xg | /r/LocalLLaMA/comments/1oyn0xg/how_to_train_a_llm_using_comments_from_youtube/ | false | false | self | 8 | null |
How can I clear the context in llama-cli? | 3 | I'm using llama-cli in conversational mode. Is there any way to clear the context (so that I can start a new chat without the previous information) without having to quit llama-cli and reloading the model? Something like /clear in ollama cli? | 2025-11-16T14:24:28 | https://www.reddit.com/r/LocalLLaMA/comments/1oyn02v/how_can_i_clear_the_context_in_llamacli/ | Melyndeith | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyn02v | false | null | t3_1oyn02v | /r/LocalLLaMA/comments/1oyn02v/how_can_i_clear_the_context_in_llamacli/ | false | false | self | 3 | null |
Bro and I thought I was an overthinker! vibeTHINKER on LM studio with no instructions. | 1 | 2025-11-16T14:21:24 | https://v.redd.it/cuh0fcljom1g1 | Big-Cartographer-873 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oymxjb | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/cuh0fcljom1g1/DASHPlaylist.mpd?a=1765894900%2CMTE0ZDkwMTUzOTBjZjRmNDdkYjg0Y2UwZGQ0YTU2NjU4ZjYyMDRhMWQzOWI5MDJhOTYzNTBmZGIwMGE2M2M2NQ%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/cuh0fcljom1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oymxjb | /r/LocalLLaMA/comments/1oymxjb/bro_and_i_thought_i_was_an_overthinker/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'MnNhM2Nsa2pvbTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MnNhM2Nsa2pvbTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa.png?width=108&crop=smart&format=pjpg&auto=webp&s=9d8383105afd559fe33ee4edbf35eaae560d... | ||
Bro and I thought I was an overthinker! vibeTHINKER on LM studio with no instructions. | 1 | 2025-11-16T14:17:35 | https://v.redd.it/vsxk7p7vnm1g1 | Big-Cartographer-873 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oymud0 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/vsxk7p7vnm1g1/DASHPlaylist.mpd?a=1765894672%2CZjZjZGFkMmI5ZThiODE1ODM4ODIzYmFjNDRjZTg0NDAzZmY4YzMyMjE5NmUxM2UwMTNhYmIyODRjMjFkYmYyZQ%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/vsxk7p7vnm1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oymud0 | /r/LocalLLaMA/comments/1oymud0/bro_and_i_thought_i_was_an_overthinker/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'bjY1eXFxN3ZubTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/bjY1eXFxN3ZubTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa.png?width=108&crop=smart&format=pjpg&auto=webp&s=0e51f089fb4e4f206a99cabc077b355e9904... | ||
Bro and I thought I was an overthinker! vibeTHINKER on LM studio with no instructions. | 1 | 2025-11-16T14:10:37 | https://v.redd.it/grgud15cmm1g1 | Big-Cartographer-873 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oymon2 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/grgud15cmm1g1/DASHPlaylist.mpd?a=1765894255%2COWY1MGE3MjQ4OTk2YzY3OWUzNGYwMTJiNWU4ZTg3YTE4MzNhYTFjNGY0OTk5MGJkMmM4NTU2N2ZmMzNiNTJmMw%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/grgud15cmm1g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oymon2 | /r/LocalLLaMA/comments/1oymon2/bro_and_i_thought_i_was_an_overthinker/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'MW55MDExNWNtbTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/MW55MDExNWNtbTFnMQNezZt2lAg7yxO9Bye4sp9-9KhPgyY1LByBbacNyNwa.png?width=108&crop=smart&format=pjpg&auto=webp&s=45e18405e007661ff260a25638694ff70cd7... | ||
Heretic: Fully automatic censorship removal for language models | 2,496 | Dear fellow Llamas, your time is precious, so I won't waste it with a long introduction. I have developed a program that can automatically remove censorship (aka "alignment") from many language models. I call it Heretic (https://github.com/p-e-w/heretic).
If you have a Python environment with the appropriate version o... | 2025-11-16T14:05:58 | -p-e-w- | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oymku1 | false | null | t3_1oymku1 | /r/LocalLLaMA/comments/1oymku1/heretic_fully_automatic_censorship_removal_for/ | false | false | 2,496 | {'enabled': True, 'images': [{'id': 'Tq4RN4otZc2JmlmFmUXcw_e7PoEwKhernuQl7x95F3Y', 'resolutions': [{'height': 118, 'url': 'https://preview.redd.it/jcu64fczhm1g1.png?width=108&crop=smart&auto=webp&s=2bb4676e9c7be2bcc361508a8afd56ce663d0222', 'width': 108}, {'height': 237, 'url': 'https://preview.redd.it/jcu64fczhm1g1.pn... | ||
Looking for a good LLM local environment with one-folder install | 1 | I am looking to try some of this out on windows. I was going to try LM studio, but I ran into an issue: it is not a one folder install. It spreads files, most importantly the models themselves, into the default windows user folders. Windows is on a smaller, lower speed drive and cannot handle this. I have a dedicated d... | 2025-11-16T13:51:03 | https://www.reddit.com/r/LocalLLaMA/comments/1oym8in/looking_for_a_good_llm_local_environment_with/ | void2258 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oym8in | false | null | t3_1oym8in | /r/LocalLLaMA/comments/1oym8in/looking_for_a_good_llm_local_environment_with/ | false | false | self | 1 | null |
I rebuilt my AI translation app to work ANYWHERE on your PC (100% local with Ollama & open-source) | 16 | Hey everyone!
A while ago, I shared the first version of Polyglot, a project focused on AI-powered translations. It was a simple app with an input and an output text field, much like any translation website. You had to open the app to get anything translated.
In this new version, which I'm calling **Polyglot Air**, I... | 2025-11-16T13:48:23 | https://www.reddit.com/r/LocalLLaMA/comments/1oym6br/i_rebuilt_my_ai_translation_app_to_work_anywhere/ | thecalmgreen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oym6br | false | null | t3_1oym6br | /r/LocalLLaMA/comments/1oym6br/i_rebuilt_my_ai_translation_app_to_work_anywhere/ | false | false | self | 16 | null |
Just Experimenting with Web-Automation in Android | 0 | Hey Guys
I am Creating this Post to check how people feel about web-automation on their android phone with both online and offline ( private ) AI Model, Just testing with a web-automation algorithm i created and it is performing very well so far, like filling google forms ( of all kinds ) navigating web-pages, also su... | 2025-11-16T13:28:46 | https://v.redd.it/wei1hfsbfm1g1 | DarkEngine774 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oylqrl | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/wei1hfsbfm1g1/DASHPlaylist.mpd?a=1765891743%2COGIxMTNhMjAwNDQ2ZGE2YzdiMWVhMzkzZTdlNjQ3YTUyM2ExZmQxNzEwZGFmZGI3YmY1NzAyMzY2NmYxMWRiZA%3D%3D&v=1&f=sd', 'duration': 43, 'fallback_url': 'https://v.redd.it/wei1hfsbfm1g1/CMAF_720.mp4?source=fallback', 'ha... | t3_1oylqrl | /r/LocalLLaMA/comments/1oylqrl/just_experimenting_with_webautomation_in_android/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'MTExbGFmc2JmbTFnMdRtWr77vdgTEUnZaZCOVyjLuOiq5-6n2UjvG_9avWGl', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/MTExbGFmc2JmbTFnMdRtWr77vdgTEUnZaZCOVyjLuOiq5-6n2UjvG_9avWGl.png?width=108&crop=smart&format=pjpg&auto=webp&s=868254c91d7134c45439dd274cd68400f62b... | |
Stopping the Toon hype with a proper benchmark | 28 | There is quite a bit of hype (and postings) around TOON. If you look at the provided benchmarks you'll see that TOON simply yields the [best results](https://github.com/toon-format/toon?tab=readme-ov-file#performance-by-question-type), despite no LLM being trained on it, with even a lower token usage than the other for... | 2025-11-16T13:13:43 | https://www.reddit.com/r/LocalLLaMA/comments/1oylf8m/stopping_the_toon_hype_with_a_proper_benchmark/ | Chromix_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oylf8m | false | null | t3_1oylf8m | /r/LocalLLaMA/comments/1oylf8m/stopping_the_toon_hype_with_a_proper_benchmark/ | false | false | 28 | null | |
"Achieved 9.68x GPU utilization improvement for local models (8% → 95%) - with code"
"Novel GPU alignment technique makes 70B models run like 7B models" | 9 | [https://github.com/For-Sunny/nova-mcp-research](https://github.com/For-Sunny/nova-mcp-research) TL;DR: Developed a novel ML enhancement that aligns GPU operations into a unified computational field. Takes utilization from \~8% to 95%. Fully open source, MIT licensed.
What this is:
\- A GPU alignment technique that... | 2025-11-16T13:04:24 | Senior-Leadership-25 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyl83a | false | null | t3_1oyl83a | /r/LocalLLaMA/comments/1oyl83a/achieved_968x_gpu_utilization_improvement_for/ | false | false | default | 9 | {'enabled': True, 'images': [{'id': 'e8tex3l1am1g1', 'resolutions': [{'height': 42, 'url': 'https://preview.redd.it/e8tex3l1am1g1.png?width=108&crop=smart&auto=webp&s=0d46c409c097c24249b4e144674bf8e48dd1ab8d', 'width': 108}, {'height': 84, 'url': 'https://preview.redd.it/e8tex3l1am1g1.png?width=216&crop=smart&auto=webp... | |
Finally a good use case for your local setups | 508 | https://www.bbc.com/news/articles/c0rpy7envr5o | 2025-11-16T12:35:53 | lakySK | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oyknf1 | false | null | t3_1oyknf1 | /r/LocalLLaMA/comments/1oyknf1/finally_a_good_use_case_for_your_local_setups/ | false | false | default | 508 | {'enabled': True, 'images': [{'id': 'o4xqvpnu5m1g1', 'resolutions': [{'height': 153, 'url': 'https://preview.redd.it/o4xqvpnu5m1g1.jpeg?width=108&crop=smart&auto=webp&s=da3f513d9a5f13a2717613dcd0ff3fc441b65305', 'width': 108}, {'height': 306, 'url': 'https://preview.redd.it/o4xqvpnu5m1g1.jpeg?width=216&crop=smart&auto=... | |
StrixHalo small vs large fixed allocation | 0 | Has anyone seen any benchmarks where one would compare performance difference between 512MB fixed allocation and 96GB fixed allocation? Of course let GTT allocate rest of RAM in both configs. Mainly interested in oss 120b model. Thank you. | 2025-11-16T12:31:48 | https://www.reddit.com/r/LocalLLaMA/comments/1oykklo/strixhalo_small_vs_large_fixed_allocation/ | dragonbornamdguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oykklo | false | null | t3_1oykklo | /r/LocalLLaMA/comments/1oykklo/strixhalo_small_vs_large_fixed_allocation/ | false | false | self | 0 | null |
Finally a good use case for your local setups | 1 | 2025-11-16T12:30:19 | https://www.bbc.com/news/articles/c0rpy7envr5o | lakySK | bbc.com | 1970-01-01T00:00:00 | 0 | {} | 1oykjin | false | null | t3_1oykjin | /r/LocalLLaMA/comments/1oykjin/finally_a_good_use_case_for_your_local_setups/ | false | false | default | 1 | null | |
DGX Spark - Issues with qwen models | 0 | Hello, I’m testing my new DGX Spark and, after using gpt-oss 120b with a good performance (40 token/s), I was surprised by the fact that the qwen models (vl 30b but also 8b) freeze and don't respond well at all. Where am I going wrong? | 2025-11-16T12:23:03 | hacktar | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oykeny | false | null | t3_1oykeny | /r/LocalLLaMA/comments/1oykeny/dgx_spark_issues_with_qwen_models/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'Jfz-YjBp9Oz0QChClaM5URjmsW_BDYXfcYYYSdUxd3E', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/54z70yan3m1g1.jpeg?width=108&crop=smart&auto=webp&s=0a3e12597c2abdff12bb2ea752133270cc548e0c', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/54z70yan3m1g1.j... | ||
Wonderfully explained JSON vs TOON. | 0 | https://www.linkedin.com/posts/chakrabortypreetam_json-vs-toon-choosing-the-right-data-format-activity-7395781809118265345-OV4w?utm_medium=ios_app&rcm=ACoAABtmTHUBDlnpwc6UOGtrVwNAlT3GqBbDDv8&utm_source=social_share_send&utm_campaign=copy_link | 2025-11-16T12:22:03 | https://www.reddit.com/r/LocalLLaMA/comments/1oyke1n/wonderfully_explained_json_vs_toon/ | Gullible-Paper-6828 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyke1n | false | null | t3_1oyke1n | /r/LocalLLaMA/comments/1oyke1n/wonderfully_explained_json_vs_toon/ | false | false | self | 0 | null |
New BERT-based Multilingual Chunking Model | 82 | Inspired by [chonky](https://github.com/mirth/chonky), I fine-tuned [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on nearly 11 billion tokens from more than 34 million Wikipedia articles to predict paragraph breaks. The resulting model can be used ... | 2025-11-16T12:00:49 | https://www.reddit.com/r/LocalLLaMA/comments/1oyjzjb/new_bertbased_multilingual_chunking_model/ | LMLocalizer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyjzjb | false | null | t3_1oyjzjb | /r/LocalLLaMA/comments/1oyjzjb/new_bertbased_multilingual_chunking_model/ | false | false | self | 82 | {'enabled': False, 'images': [{'id': 'sjyHTy2RaeQ2M19cen-74KTW2VWLkx2FuUP7GANYwc4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/sjyHTy2RaeQ2M19cen-74KTW2VWLkx2FuUP7GANYwc4.png?width=108&crop=smart&auto=webp&s=761d3e980a32e7941a6759f23af20d9568ac92be', 'width': 108}, {'height': 108, 'url': 'h... |
Announcing Funcdex: the complete framework for building your own function-calling models | 10 | Hi, I'm Sid from Prem AI, and we’re open-sourcing Funcdex, the complete framework for building your own function-calling models. Funcdex outperforms most frontier models on narrow tasks - with support for 15 toolkit configurations (10 single, 5 multi-toolkit).
Complex tool use traces aren't available publicly for trai... | 2025-11-16T11:55:49 | https://www.reddit.com/r/LocalLLaMA/comments/1oyjw7i/announcing_funcdex_the_complete_framework_for/ | backprophet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyjw7i | false | null | t3_1oyjw7i | /r/LocalLLaMA/comments/1oyjw7i/announcing_funcdex_the_complete_framework_for/ | false | false | 10 | null | |
Anime t2i dataset help | 2 | Hi. Im on a mission to create a massive dataset of almost all popular anime. (this is my first time making a dataset)
I want that dataset to be flexible on characters and studio styles, so i took screencaps from [this](https://fancaps.net/anime/popular.php) website.
I want this to be opensource.
I have a few quest... | 2025-11-16T11:43:52 | https://www.reddit.com/r/LocalLLaMA/comments/1oyjomj/anime_t2i_dataset_help/ | Brave-Hold-9389 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oyjomj | false | null | t3_1oyjomj | /r/LocalLLaMA/comments/1oyjomj/anime_t2i_dataset_help/ | false | false | self | 2 | null |
How is my build for season of RTX? | 0 | I mean, other than low storage, I have tones of nvme in hand. | 2025-11-16T11:27:01 | https://www.reddit.com/r/buildapc/comments/1ovbfub/seasons_of_rtx_5000_dream_pc_build_contest_with/np49sku/ | No_Night679 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1oyje44 | false | null | t3_1oyje44 | /r/LocalLLaMA/comments/1oyje44/how_is_my_build_for_season_of_rtx/ | false | false | default | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.