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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Best moe models for 4090: how to keep vram low without losing quality? | 0 | I'm currently self-hosting GPT-OSS 120b (mxfp4) with llama.cpp and offloading just the attention layers to GPU. It works ok - not super fast, but the quality of responses is good enough. Since I'm using offloading, it requires me to always keep in VRAM \~7.5 GB of the model. I'm following this guide - [https://old.redd... | 2026-01-12T14:38:26 | https://www.reddit.com/r/LocalLLaMA/comments/1qawkdt/best_moe_models_for_4090_how_to_keep_vram_low/ | AdParty3888 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qawkdt | false | null | t3_1qawkdt | /r/LocalLLaMA/comments/1qawkdt/best_moe_models_for_4090_how_to_keep_vram_low/ | false | false | self | 0 | null |
Best open coding model for 128GB RAM? [2026] | 9 | Hello,
What would be your suggestions for an open model to run locally with 128 GB RAM? devstral-small-2-24b-instruct-2512@8bit and max context, or another model? | 2026-01-12T14:30:07 | https://www.reddit.com/r/LocalLLaMA/comments/1qawd0z/best_open_coding_model_for_128gb_ram_2026/ | Acrobatic_Cat_3448 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qawd0z | false | null | t3_1qawd0z | /r/LocalLLaMA/comments/1qawd0z/best_open_coding_model_for_128gb_ram_2026/ | false | false | self | 9 | null |
z.ai prepping for glm-image soon - here is what we know so far | 93 | GLM-Image supports both text-to-image and image-to-image generation within a single model
Text-to-image: generates high-detail images from textual descriptions, with particularly strong performance in information-dense scenarios.
Image-to-image: supports a wide range of tasks, including image editing, style tra... | 2026-01-12T14:28:22 | https://www.reddit.com/r/LocalLLaMA/comments/1qawbjj/zai_prepping_for_glmimage_soon_here_is_what_we/ | MrAlienOverLord | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qawbjj | false | null | t3_1qawbjj | /r/LocalLLaMA/comments/1qawbjj/zai_prepping_for_glmimage_soon_here_is_what_we/ | false | false | self | 93 | {'enabled': False, 'images': [{'id': 'P4z_SkrIKX5pS_yEph4NfCumh3uEz9HzrURsqI1fz6A', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/P4z_SkrIKX5pS_yEph4NfCumh3uEz9HzrURsqI1fz6A.png?width=108&crop=smart&auto=webp&s=6bd043ec9beb305e45d98f5f7d446403ef64519c', 'width': 108}, {'height': 116, 'url': 'h... |
MiniMax Coding Plan - $2/month AI API that works with Cursor, Claude Code, Cline (+ 10% off) | 0 |
Hey everyone,
Wanted to share a deal I found for those using AI coding assistants.
\*\*What is it?\*\*
MiniMax has a "Coding Plan" - unlimited API access to their M2.1 model for $2/month (starter tier). It works with basically every AI coding tool:
\- Cursor
\- Claude Code
\- Cline
\- Roo Code
\- Open... | 2026-01-12T14:19:40 | https://www.reddit.com/r/LocalLLaMA/comments/1qaw3pd/minimax_coding_plan_2month_ai_api_that_works_with/ | TheHentaiCulture | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaw3pd | false | null | t3_1qaw3pd | /r/LocalLLaMA/comments/1qaw3pd/minimax_coding_plan_2month_ai_api_that_works_with/ | false | false | self | 0 | null |
How to make good RAG with spreadsheets and other tabular data such as SQL? | 1 | The issue is that I have various types of spreadsheets and tabular data on multiple subjects across several pages, so it's quite complex. I'm looking for something 100% local. Any response would be appreciated. | 2026-01-12T14:16:05 | https://www.reddit.com/r/LocalLLaMA/comments/1qaw0jw/how_to_make_good_rag_with_spreadsheets_and_other/ | Ga_0512 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaw0jw | false | null | t3_1qaw0jw | /r/LocalLLaMA/comments/1qaw0jw/how_to_make_good_rag_with_spreadsheets_and_other/ | false | false | self | 1 | null |
Coding LLM Model | 2 | Hy guys, I just bought An macbook 4 pro 48gb ram, what would be the best code model to run on it locally? Thanks! | 2026-01-12T13:52:02 | https://www.reddit.com/r/LocalLLaMA/comments/1qavfcg/coding_llm_model/ | plugshawtycft | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qavfcg | false | null | t3_1qavfcg | /r/LocalLLaMA/comments/1qavfcg/coding_llm_model/ | false | false | self | 2 | null |
[Release] Eva-4B: Specialized Financial Evasion Detection (Based on Qwen3-4B). Outperforms GPT-5.2 on domain benchmarks. | 181 | Hi r/LocalLLaMA,
I'm excited to share **Eva-4B,** a specialized 4B parameter model designed to detect evasive answers in corporate earnings call Q&A sessions.
**What it does:**
It classifies answers into \`direct\`, \`intermediate\`, or \`fully\_evasive\` (using the Rasiah framework). It helps identify when executi... | 2026-01-12T13:26:39 | Awkward_Run_9982 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qautxm | false | null | t3_1qautxm | /r/LocalLLaMA/comments/1qautxm/release_eva4b_specialized_financial_evasion/ | false | false | default | 181 | {'enabled': True, 'images': [{'id': 'bawipxvf6xcg1', 'resolutions': [{'height': 73, 'url': 'https://preview.redd.it/bawipxvf6xcg1.png?width=108&crop=smart&auto=webp&s=24b76b41e479e402f9a3072de64c826929b9bf62', 'width': 108}, {'height': 146, 'url': 'https://preview.redd.it/bawipxvf6xcg1.png?width=216&crop=smart&auto=web... | |
We built a privacy oriented, local-first and transparent context IDE. No subscriptions. | 4 | Hi r/LocalLLaMA,
We have been around for a while. We noticed subscription fatigue around AI and agent tools, and we wanted less of a black box in which we don't know how our context is being sent into the cloud.
With that in mind, we are spending time to build **Ollie IDE**.
**The Philosophy:**
* **"Glass-Box" Tran... | 2026-01-12T13:25:15 | https://www.reddit.com/gallery/1qausr4 | Ollie_IDE | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qausr4 | false | null | t3_1qausr4 | /r/LocalLLaMA/comments/1qausr4/we_built_a_privacy_oriented_localfirst_and/ | false | false | 4 | null | |
Battle of AI Gateways: Rust vs. Python for AI Infrastructure: Bridging a 3,400x Performance Gap | 0 | 2026-01-12T13:00:45 | https://vidai.uk/blog/rust-python-vidai | Guna1260 | vidai.uk | 1970-01-01T00:00:00 | 0 | {} | 1qau8wx | false | null | t3_1qau8wx | /r/LocalLLaMA/comments/1qau8wx/battle_of_ai_gateways_rust_vs_python_for_ai/ | false | false | default | 0 | null | |
nvidia/nemotron-speech-streaming-en-0.6b | 4 | Has anyone used nvidia/nemotron-speech-streaming-en-0.6b ?
How is it?
Noticed it dropped recently and seems efficient | 2026-01-12T12:42:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qatvsc/nvidianemotronspeechstreamingen06b/ | SlowFail2433 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qatvsc | false | null | t3_1qatvsc | /r/LocalLLaMA/comments/1qatvsc/nvidianemotronspeechstreamingen06b/ | false | false | self | 4 | null |
GLM-4.7 218B REAP model by Cerebras | 79 | [https://huggingface.co/cerebras/GLM-4.7-REAP-218B-A32B](https://huggingface.co/cerebras/GLM-4.7-REAP-218B-A32B)
Curious to see how the quantized versions will perform. | 2026-01-12T12:33:52 | https://www.reddit.com/r/LocalLLaMA/comments/1qatpgb/glm47_218b_reap_model_by_cerebras/ | ResearchWheel5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qatpgb | false | null | t3_1qatpgb | /r/LocalLLaMA/comments/1qatpgb/glm47_218b_reap_model_by_cerebras/ | false | false | self | 79 | {'enabled': False, 'images': [{'id': '5hX6_0eraUgqUctJmYcs6QnTfCtzJuohSgWkU8_UCSk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/5hX6_0eraUgqUctJmYcs6QnTfCtzJuohSgWkU8_UCSk.png?width=108&crop=smart&auto=webp&s=1a1e119b8f95e5095f595631bdf125d7c1c3d002', 'width': 108}, {'height': 116, 'url': 'h... |
Building a free K-10 education platform - seeking advice on transitioning from Google AI Studio to local LLMs | 1 | Hey everyone,
I need your help in improving a gratis access K-10 education platform. I think this community's expertise is exactly what I need.
**The project:** I've built an educational platform for Grades 1-10 aimed at students who can't afford tutoring or premium EdTech subscriptions. Currently it runs on Google A... | 2026-01-12T12:32:51 | https://www.reddit.com/r/LocalLLaMA/comments/1qatop7/building_a_free_k10_education_platform_seeking/ | ordin8forgood | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qatop7 | false | null | t3_1qatop7 | /r/LocalLLaMA/comments/1qatop7/building_a_free_k10_education_platform_seeking/ | false | false | self | 1 | null |
I kept breaking multi-agent systems on shared state, so I built a small OSS thing. Looking for a few builders to test. | 2 | I have been building multi agent systems for a while and kept running into the same issue. Once agents are split across processes or services, shared state becomes fragile. Retries overwrite things, handoffs break, and debugging turns into digging through logs.
I ended up building a small open source, self hosted proj... | 2026-01-12T11:50:51 | https://www.reddit.com/r/LocalLLaMA/comments/1qasvdm/i_kept_breaking_multiagent_systems_on_shared/ | Temporary-Tap-7323 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qasvdm | false | null | t3_1qasvdm | /r/LocalLLaMA/comments/1qasvdm/i_kept_breaking_multiagent_systems_on_shared/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'vgA_pk1rOZOOdU_a3MTzPOFnHBmux9oPwAGEMGsNuIU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/vgA_pk1rOZOOdU_a3MTzPOFnHBmux9oPwAGEMGsNuIU.png?width=108&crop=smart&auto=webp&s=003b50f3da10cc7e84912b6bd35bd822f7595f64', 'width': 108}, {'height': 108, 'url': 'h... |
Which are the exacto-like providers? | 0 | What are the reliable providers you use with OSS models? I mean which don't use bad quantization other tricks?
I looked at OpenRouter's exacto models and these are the providers selected them. Can they all be trusted for quality / quantization?
- deepinfra
- novita
- groq
- z-ai
- moonshotai
- atlas-cloud
- baseten | 2026-01-12T11:02:35 | https://www.reddit.com/r/LocalLLaMA/comments/1qas0r8/which_are_the_exactolike_providers/ | hyperknot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qas0r8 | false | null | t3_1qas0r8 | /r/LocalLLaMA/comments/1qas0r8/which_are_the_exactolike_providers/ | false | false | self | 0 | null |
What if the Universe has a Backend? Introducing the Index Resonance (RI) Framework. | 0 | The RI Model (Index Resonance) is a philosophical and mathematical framework describing the "source code" of the Universe. RI explains how data is processed "under the hood" of existence. Presenting the 9 Fundamental Laws:#Metaphysics#Philosophy#RIModel | 2026-01-12T11:00:02 | https://www.reddit.com/gallery/1qarywq | Erikqamalyan1 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qarywq | false | null | t3_1qarywq | /r/LocalLLaMA/comments/1qarywq/what_if_the_universe_has_a_backend_introducing/ | false | false | 0 | null | |
Supertonic 2 TTS available on Hugging Face! | 62 | demo: [https://huggingface.co/spaces/Supertone/supertonic-2](https://huggingface.co/spaces/Supertone/supertonic-2)
model: [https://huggingface.co/Supertone/supertonic-2](https://huggingface.co/Supertone/supertonic-2)
Now in 5 languages (EN, KO, ES, PT, FR), generates 1 sec of audio in 0.006 sec. | 2026-01-12T10:59:17 | https://v.redd.it/cgp59yzfgwcg1 | paf1138 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qarygi | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/cgp59yzfgwcg1/DASHPlaylist.mpd?a=1770807569%2CMzBlYzQ0ZTQ5ZjkwODQzM2VmMGZjMjgzOGY2NDA0MTJiZDEyMmNkZjRkMTc4NjFhZTQzZTUxMGQ2ZGFlY2Y1ZA%3D%3D&v=1&f=sd', 'duration': 9, 'fallback_url': 'https://v.redd.it/cgp59yzfgwcg1/CMAF_1080.mp4?source=fallback', 'ha... | t3_1qarygi | /r/LocalLLaMA/comments/1qarygi/supertonic_2_tts_available_on_hugging_face/ | false | false | 62 | {'enabled': False, 'images': [{'id': 'bW0xNzkxMGdnd2NnMUnVCiAxQGnt1ilbiC_caBfY1exLsRF9vnxWGz-1gEiE', 'resolutions': [{'height': 93, 'url': 'https://external-preview.redd.it/bW0xNzkxMGdnd2NnMUnVCiAxQGnt1ilbiC_caBfY1exLsRF9vnxWGz-1gEiE.png?width=108&crop=smart&format=pjpg&auto=webp&s=da2f1da131d96d3c8b8d8627ece2d728f2be8... | |
SCAM EXPOSED: Blackbox AI "Pro Max" ($40/mo) is FAKE. I tested all 5 top models - here is the proof. | 0 | I subscribed to the Blackbox AI "Pro Max" plan ($40/month) to get access to the latest frontier models like **Claude Opus 4.5**, **Gemini 3 Pro**, and **GPT-5.2**.
After noticing the quality was low, I ran a systematic audit of every single "Pro" model using specific "knowledge cutoff" tests.
**The Result:** NOT A SI... | 2026-01-12T10:55:34 | https://www.reddit.com/gallery/1qarw69 | frankierave889 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qarw69 | false | null | t3_1qarw69 | /r/LocalLLaMA/comments/1qarw69/scam_exposed_blackbox_ai_pro_max_40mo_is_fake_i/ | false | false | 0 | null | |
SCAM EXPOSED: Blackbox AI "Pro Max" ($40/mo) is FAKE. I tested all 5 top models - here is the proof. | 1 | 2026-01-12T10:53:45 | https://www.reddit.com/gallery/1qarv1u | frankierave889 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qarv1u | false | null | t3_1qarv1u | /r/LocalLLaMA/comments/1qarv1u/scam_exposed_blackbox_ai_pro_max_40mo_is_fake_i/ | false | false | 1 | null | ||
What I use for my MCP Server | 0 | Apparently this thing has only two downloads and I am one of them. Anyway this thing is basically responsible for the backend of my server.
I just know it works. Don't ask me how
Don't ask me any more questions about open sourcing my code or what MCP server I use. The answer is 127.0.0.1 lol
Shout out to whoever m... | 2026-01-12T10:29:15 | https://v.redd.it/6qm5e7l7bwcg1 | Serious_Molasses313 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qargb4 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/6qm5e7l7bwcg1/DASHPlaylist.mpd?a=1770805778%2CMzE2NDJhYTA3Yzc5ZTM2ZWUwNjAyYmEyOTM3NThlZGI4NjYzMjVhOTcxYWU0OTllNzBlMDUxODNjZDRlMmY4Yg%3D%3D&v=1&f=sd', 'duration': 85, 'fallback_url': 'https://v.redd.it/6qm5e7l7bwcg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1qargb4 | /r/LocalLLaMA/comments/1qargb4/what_i_use_for_my_mcp_server/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'cXhtcjM0bTdid2NnMblUwx_jfxc-ZEGTmtiGzsVIWHhptPO8baqLaVylwbet', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/cXhtcjM0bTdid2NnMblUwx_jfxc-ZEGTmtiGzsVIWHhptPO8baqLaVylwbet.png?width=108&crop=smart&format=pjpg&auto=webp&s=7a2cacb6e0d3639dfbd06950073d5e9757e0... | |
Is anyone offering compute to finetune a Unique GPT-OSS models? Trying to build an MLA Diffusion Language model. | 15 | I’m currently experimenting with GPT-OSS, inspired by many recent MLA/Diffusion model, I’m trying to convert GPT-OSS into an MLA diffusion model. Mostly trying to implement and get it working with inference on an H100 and has been using whatever I can on vast.ai 8x RTX PRO 6000/8x B200 or any other places that has comp... | 2026-01-12T09:45:14 | https://www.reddit.com/r/LocalLLaMA/comments/1qaqqqn/is_anyone_offering_compute_to_finetune_a_unique/ | Ok_Difference_4483 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaqqqn | false | null | t3_1qaqqqn | /r/LocalLLaMA/comments/1qaqqqn/is_anyone_offering_compute_to_finetune_a_unique/ | false | false | self | 15 | null |
Here's my opinion on Mac Studio vs RTX 5090. Do you think otherwise? If yes, lets discuss. | 0 | 2026-01-12T09:21:19 | https://theneuralpost.com/2025/12/16/mac-studio-vs-nvidia-rtx-5090-the-ultimate-local-ai-hardware-battle/ | Puzzled_Definition14 | theneuralpost.com | 1970-01-01T00:00:00 | 0 | {} | 1qaqdhg | false | null | t3_1qaqdhg | /r/LocalLLaMA/comments/1qaqdhg/heres_my_opinion_on_mac_studio_vs_rtx_5090_do_you/ | false | false | default | 0 | null | |
local ai agnet on gtx 1080ti pycharm+lmstudio | 0 | 2026-01-12T08:27:26 | https://www.youtube.com/watch?v=MAXAaa4Md0M | Legion10008 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1qapjf1 | false | {'oembed': {'author_name': 'Combo_Ai', 'author_url': 'https://www.youtube.com/@comboai1000', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/MAXAaa4Md0M?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; ... | t3_1qapjf1 | /r/LocalLLaMA/comments/1qapjf1/local_ai_agnet_on_gtx_1080ti_pycharmlmstudio/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'B8DaNUP4oAnjEBKbBie4OYnvbKUw0DP5t1jHTK8rQ6o', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/B8DaNUP4oAnjEBKbBie4OYnvbKUw0DP5t1jHTK8rQ6o.jpeg?width=108&crop=smart&auto=webp&s=4f4ec61e627dc5e3b4d3f626d59ddbe69b34bdf4', 'width': 108}, {'height': 162, 'url': '... | |
stable pcie 5.0 long (>0.5m) riser cable or something else ? | 1 | 2026-01-12T07:46:54 | https://www.reddit.com/r/LocalLLaMA/comments/1qaowbc/stable_pcie_50_long_05m_riser_cable_or_something/ | Comfortable-Plate467 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaowbc | false | null | t3_1qaowbc | /r/LocalLLaMA/comments/1qaowbc/stable_pcie_50_long_05m_riser_cable_or_something/ | false | false | 1 | null | ||
Can i use my 4070 laptop to finetune llms, like lama 3.1 8b or bigger? | 0 | I have a laptop and its specs are
4070
I7 14650
16gb ram
If i cant, what is the best setup i can do to finetune freely?, is it colab or is there better options? | 2026-01-12T07:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/1qaopjs/can_i_use_my_4070_laptop_to_finetune_llms_like/ | Beyond_Birthday_13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaopjs | false | null | t3_1qaopjs | /r/LocalLLaMA/comments/1qaopjs/can_i_use_my_4070_laptop_to_finetune_llms_like/ | false | false | self | 0 | null |
Remote Code Execution in OpenCode, update now | 5 | 2026-01-12T07:14:36 | https://cy.md/opencode-rce/ | rm-rf-rm | cy.md | 1970-01-01T00:00:00 | 0 | {} | 1qaodvw | false | null | t3_1qaodvw | /r/LocalLLaMA/comments/1qaodvw/remote_code_execution_in_opencode_update_now/ | false | false | default | 5 | null | |
Accessibility app idea (I don't know if it exists, maybe someone can make it a reality) | 0 | A few days ago, I was in a bookstore when a blind customer arrived. It struck me how challenging it can be for someone who is blind and alone with only their guide dog—to accomplish something as simple as buying a specific-expensive pen.
(It was Christmas, so he was likely buying the pen as a gift for the person who... | 2026-01-12T07:08:59 | Shockbum | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qaoai0 | false | null | t3_1qaoai0 | /r/LocalLLaMA/comments/1qaoai0/accessibility_app_idea_i_dont_know_if_it_exists/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'afu-33QcVvWIBuX7jIdp0ESAk5ki-uWrTIM85voETds', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/qm8hrshr9vcg1.jpeg?width=108&crop=smart&auto=webp&s=5a4afeb20194d8ad53c3bc00a1d1c69d1ff127cd', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/qm8hrshr9vcg1.jp... | ||
Agentic ProbLLMs: Exploiting AI Computer-Use and Coding Agents (youtube) -- "local" can make people complacent on security, but if you push code to github, worth a watch, even if you don't use AI coding tools. | 14 | Good talk at 39C3 Conference [https://www.youtube.com/watch?v=8pbz5y7\_WkM](https://www.youtube.com/watch?v=8pbz5y7_WkM)
Nothing novel, no breaking news here, but a nice tight overview of the landscape, with a great overview of AgentHopper, which is basically a virus framework spread by coding agents via your local en... | 2026-01-12T06:54:41 | https://www.reddit.com/r/LocalLLaMA/comments/1qao1ra/agentic_probllms_exploiting_ai_computeruse_and/ | coloradical5280 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qao1ra | false | null | t3_1qao1ra | /r/LocalLLaMA/comments/1qao1ra/agentic_probllms_exploiting_ai_computeruse_and/ | false | false | self | 14 | {'enabled': False, 'images': [{'id': '-3NG7BoqxhxmGk7_Bwf_jUUTWYKldvibiGAcijSuTDM', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/-3NG7BoqxhxmGk7_Bwf_jUUTWYKldvibiGAcijSuTDM.jpeg?width=108&crop=smart&auto=webp&s=bb333eaf097695f63ddcc0474f2f6535ac52bbe5', 'width': 108}, {'height': 162, 'url': '... |
Dual GPU King 95+x870e Taichi lite | 0 | If anyone is interested in my setup and how I got more performance from a second gpu.. | 2026-01-12T06:21:42 | https://www.reddit.com/r/LocalLLaMA/comments/1qanh5x/dual_gpu_king_95x870e_taichi_lite/ | sloth_cowboy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qanh5x | false | null | t3_1qanh5x | /r/LocalLLaMA/comments/1qanh5x/dual_gpu_king_95x870e_taichi_lite/ | false | false | self | 0 | null |
China's AGI-Next Roundtable: Leaders from Zhipu, Kimi, Qwen, and Tencent discuss the future of AI | 92 | [Automated RL Data Synthesis for Agentic Tasks](https://preview.redd.it/kz6g7cqbzucg1.png?width=1832&format=png&auto=webp&s=5a62aa25fda324c86227bec8cf9cb17e34aec18d)
[Kimi Linear: An Expressive, Efficient Attention Architecture](https://preview.redd.it/jen154uhzucg1.png?width=1878&format=png&auto=webp&s=fca4b8b2357da3... | 2026-01-12T06:04:40 | https://www.reddit.com/r/LocalLLaMA/comments/1qan6bb/chinas_aginext_roundtable_leaders_from_zhipu_kimi/ | nekofneko | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qan6bb | false | null | t3_1qan6bb | /r/LocalLLaMA/comments/1qan6bb/chinas_aginext_roundtable_leaders_from_zhipu_kimi/ | false | false | 92 | null | |
Simple app to compare OpenAI, Gemini, and Anthropic responses | 0 | 2026-01-12T05:57:14 | https://www.reddit.com/r/LocalLLaMA/comments/1qan19l/simple_app_to_compare_openai_gemini_and_anthropic/ | Prashant-Lakhera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qan19l | false | null | t3_1qan19l | /r/LocalLLaMA/comments/1qan19l/simple_app_to_compare_openai_gemini_and_anthropic/ | false | false | 0 | null | ||
MiniMax-M2.1 vs GLM-4.5-Air is the bigger really the better (coding)? | 27 | So I managed to get both MiniMax-M2.1 and GLM-4.5-Air running locally with 48GB vram and 128GB ram.
\- MiniMax-M2.1-UD-Q4\_K\_XL
\- GLM-4.5-Air-UD-Q6\_K\_XL
Both with 100k context q8\_0 KV, and both get simmilar speed: \~11 to \~6tps when context is mostly filled. Minimax has slightly slower prompt processing than G... | 2026-01-12T05:45:01 | https://www.reddit.com/r/LocalLLaMA/comments/1qamt9a/minimaxm21_vs_glm45air_is_the_bigger_really_the/ | ChopSticksPlease | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qamt9a | false | null | t3_1qamt9a | /r/LocalLLaMA/comments/1qamt9a/minimaxm21_vs_glm45air_is_the_bigger_really_the/ | false | false | self | 27 | null |
Emulating style of an author | 0 | Looking for ways to emulate an author’s writing style with an LLM without fine tuning. Prompt plus examples works briefly but drifts on longer outputs. The agent also gets ~200–300 tokens of factual context from a web search that it has to write the article from. Curious what people have done to keep the voice consiste... | 2026-01-12T05:30:03 | https://www.reddit.com/r/LocalLLaMA/comments/1qamj6k/emulating_style_of_an_author/ | Different-Activity-4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qamj6k | false | null | t3_1qamj6k | /r/LocalLLaMA/comments/1qamj6k/emulating_style_of_an_author/ | false | false | self | 0 | null |
Looking for feedback on Mac mini server settings for Ollama | 0 | Hi there,
Been following this community for quite some time but finally had a reason to make my first post!
I setup Ollama on my M4 Pro Mac mini to play around with LLMs a few months ago, and ended up with a few workflows that are actually quite helpful. I'd like to make sure my local Ollama instance is running depe... | 2026-01-12T05:01:01 | https://www.reddit.com/r/LocalLLaMA/comments/1qalz0x/looking_for_feedback_on_mac_mini_server_settings/ | zachrattner | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qalz0x | false | null | t3_1qalz0x | /r/LocalLLaMA/comments/1qalz0x/looking_for_feedback_on_mac_mini_server_settings/ | false | false | self | 0 | null |
Tool for converting Confluence docs to LLM-friendly Markdown (for RAG pipelines) | 1 | If you're building RAG over corporate Confluence documentation, you might hit this annoying issue:
Confluence's exported .doc files aren't real Word documents - they're MIME-encoded HTML. LangChain's UnstructuredWordDocumentLoader, docx parsers, and most extraction tools fail on them.
I built a preprocessing tool to ... | 2026-01-12T04:47:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qalpru/tool_for_converting_confluence_docs_to/ | aqueebqadri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qalpru | false | null | t3_1qalpru | /r/LocalLLaMA/comments/1qalpru/tool_for_converting_confluence_docs_to/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'Wtv7VKJjhN7LtrTgskRC9lTk9jukzPJo2dSkvzELR2Q', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Wtv7VKJjhN7LtrTgskRC9lTk9jukzPJo2dSkvzELR2Q.png?width=108&crop=smart&auto=webp&s=6a54da6a3038cdb676914064fba03e1d255fe11a', 'width': 108}, {'height': 108, 'url': 'h... |
Just launched Plano v0.4 - a unified data plane supporting polyglot AI development | 1 | [removed] | 2026-01-12T04:07:19 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qakvzt | false | null | t3_1qakvzt | /r/LocalLLaMA/comments/1qakvzt/just_launched_plano_v04_a_unified_data_plane/ | false | false | default | 1 | null | ||
One Shot Pass@1 Benchmarking | 1 | \[P\] I benchmarked 11 LLMs using 25 handcrafted math & logic puzzles. One puzzle broke every single model.
I got tired of benchmarks that let models retry 100 times (pass@k), or use abstract API harnesses that don’t reflect how real users interact with these systems.
So I built my own.
Vault of Echoes is a da... | 2026-01-12T03:24:57 | https://www.reddit.com/r/LocalLLaMA/comments/1qak08c/one_shot_pass1_benchmarking/ | Hot_Inspection_9528 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qak08c | false | null | t3_1qak08c | /r/LocalLLaMA/comments/1qak08c/one_shot_pass1_benchmarking/ | false | false | self | 1 | null |
Local LLM + Internet Search Capability = WOW | 221 | Am on Qwen 3, asked about the training date and it said 2024. Alright, guess that's the thing I need to live with. Just need to constantly lookup HF for updated LLM which fits my cute 16gb vram.
Then someone said always ground your local AI with internet searches. A quick search = LM studio duckduckgo plugin
Within 1... | 2026-01-12T03:21:41 | https://www.reddit.com/r/LocalLLaMA/comments/1qajxrg/local_llm_internet_search_capability_wow/ | alex_godspeed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qajxrg | false | null | t3_1qajxrg | /r/LocalLLaMA/comments/1qajxrg/local_llm_internet_search_capability_wow/ | false | false | self | 221 | null |
Advice for a tool that blocks dangerous terminal commands from AI coding assistants | 8 | Hey there,
I'm building a Mac app that intercepts dangerous terminal commands before they execute. The goal is to catch things like rm -rf or git reset --hard when AI coding tools (Claude Code, Cursor, etc.) accidentally run something destructive.
The idea came after Claude deleted my src/ folder while "clean... | 2026-01-12T02:46:57 | https://www.reddit.com/r/LocalLLaMA/comments/1qaj6je/advice_for_a_tool_that_blocks_dangerous_terminal/ | spacepings | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaj6je | false | null | t3_1qaj6je | /r/LocalLLaMA/comments/1qaj6je/advice_for_a_tool_that_blocks_dangerous_terminal/ | false | false | self | 8 | null |
how do I get ubuntu to not allocate vram on an amd r9700 pro: 519/32624 MB | 2 | rocm-smi is showing:
+------------------------------------------------------------------------------+
| AMD-SMI 26.2.0+021c61fc amdgpu version: 6.14.0-37 ROCm version: 7.1.1 |
| VBIOS version: 023.008.000.068.000001 |
| Platform: Linux Baremetal ... | 2026-01-12T02:40:23 | https://www.reddit.com/r/LocalLLaMA/comments/1qaj1di/how_do_i_get_ubuntu_to_not_allocate_vram_on_an/ | jdchmiel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaj1di | false | null | t3_1qaj1di | /r/LocalLLaMA/comments/1qaj1di/how_do_i_get_ubuntu_to_not_allocate_vram_on_an/ | false | false | self | 2 | null |
How I scraped 100,000 fishing posts to find a secret spot with vector DBs and LLMs | 28 | I caught a 5 pound bass by doing this lol, and the article should be a pretty cool intro to scraping. It's also the reason I have a bunch of massive bass fishing reports sitting on my mac
Typical LLM tools for scraping aren't economical work at this scale, so this was all manual and surprisingly fun. | 2026-01-12T02:11:08 | https://www.meter.sh/blog/how-i-scraped-100k-fishing-posts | Ready-Interest-1024 | meter.sh | 1970-01-01T00:00:00 | 0 | {} | 1qaiekr | false | null | t3_1qaiekr | /r/LocalLLaMA/comments/1qaiekr/how_i_scraped_100000_fishing_posts_to_find_a/ | false | false | default | 28 | null |
Personal Intelligence | 0 | "OSINT" with GPT OSS and Qwen VL 4B | 2026-01-12T02:04:40 | https://v.redd.it/udo0t4ssotcg1 | Serious_Molasses313 | /r/LocalLLaMA/comments/1qai9gg/personal_intelligence/ | 1970-01-01T00:00:00 | 0 | {} | 1qai9gg | false | null | t3_1qai9gg | /r/LocalLLaMA/comments/1qai9gg/personal_intelligence/ | false | false | default | 0 | null |
Which GPU(s) to buy for $45k? | 0 | I am working on building a machine for building local LLMs. Please what GPUs to buy for this. My budget for spending on GPUs in 45k USD. Thanks | 2026-01-12T02:02:36 | https://www.reddit.com/r/LocalLLaMA/comments/1qai7rs/which_gpus_to_buy_for_45k/ | kob123fury | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qai7rs | false | null | t3_1qai7rs | /r/LocalLLaMA/comments/1qai7rs/which_gpus_to_buy_for_45k/ | false | false | self | 0 | null |
I built Muninn, an open-source proxy for AI coding agents like Claude Code. | 0 | I built Muninn, an open-source proxy for AI coding agents like Claude Code.
The basic idea: instead of stuffing your entire codebase into the context window, Muninn lets the LLM explore your code programmatically using tools (grep, read files, search symbols).
How it works:
\- Router: A fast classifier (runs on G... | 2026-01-12T01:59:09 | https://github.com/colliery-io/muninn | Fit-Presentation-591 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1qai4ul | false | null | t3_1qai4ul | /r/LocalLLaMA/comments/1qai4ul/i_built_muninn_an_opensource_proxy_for_ai_coding/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'KmPO0fNjTUzcDLL2tlK2ChA5sbepGS_SnkLInoXLiG8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KmPO0fNjTUzcDLL2tlK2ChA5sbepGS_SnkLInoXLiG8.png?width=108&crop=smart&auto=webp&s=50320a0402b1cd92629d51716df9a4add95d64e7', 'width': 108}, {'height': 108, 'url': 'h... |
Tool for generating LLM datasets | 1 | [removed] | 2026-01-12T01:48:34 | https://www.reddit.com/r/LocalLLaMA/comments/1qahw8c/tool_for_generating_llm_datasets/ | Express_Seesaw_8418 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qahw8c | false | null | t3_1qahw8c | /r/LocalLLaMA/comments/1qahw8c/tool_for_generating_llm_datasets/ | false | false | self | 1 | null |
Tool for generating LLM datasets | 1 | [removed] | 2026-01-12T01:45:34 | https://www.reddit.com/r/LocalLLaMA/comments/1qahtro/tool_for_generating_llm_datasets/ | Express_Seesaw_8418 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qahtro | false | null | t3_1qahtro | /r/LocalLLaMA/comments/1qahtro/tool_for_generating_llm_datasets/ | false | false | self | 1 | null |
Tool for generating LLM datasets (just launched) | 1 | [removed] | 2026-01-12T01:43:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qahsj5/tool_for_generating_llm_datasets_just_launched/ | Express_Seesaw_8418 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qahsj5 | false | null | t3_1qahsj5 | /r/LocalLLaMA/comments/1qahsj5/tool_for_generating_llm_datasets_just_launched/ | false | false | self | 1 | null |
How do I research speech to speech models? | 0 | Let's say for example I want to make a recording and make it sound like Sasuke from Naruto, or Trump. I'm trying to look up options, but I don't know the lingo. For images, for example, I know that there are a lot of ways of running stable diffusion locally, and that if I want to make an image of a specific character, ... | 2026-01-12T01:13:34 | https://www.reddit.com/r/LocalLLaMA/comments/1qah3zq/how_do_i_research_speech_to_speech_models/ | frigidice363 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qah3zq | false | null | t3_1qah3zq | /r/LocalLLaMA/comments/1qah3zq/how_do_i_research_speech_to_speech_models/ | false | false | self | 0 | null |
GLM-4.7 can Replace Opus 4.5 and G3 | 1 | [removed] | 2026-01-12T01:05:40 | https://www.reddit.com/r/LocalLLaMA/comments/1qagxbl/glm47_can_replace_opus_45_and_g3/ | Impressive-Olive8372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qagxbl | false | null | t3_1qagxbl | /r/LocalLLaMA/comments/1qagxbl/glm47_can_replace_opus_45_and_g3/ | false | false | self | 1 | null |
GLM-4.7 can Replace Opus 4.5 and G3 | 1 | [removed] | 2026-01-12T01:04:28 | https://www.reddit.com/r/LocalLLaMA/comments/1qagwb2/glm47_can_replace_opus_45_and_g3/ | Impressive-Olive8372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qagwb2 | false | null | t3_1qagwb2 | /r/LocalLLaMA/comments/1qagwb2/glm47_can_replace_opus_45_and_g3/ | false | false | self | 1 | null |
GLM-4.7 can Replace Opus 4.5 and gemini 3 | 1 | [removed] | 2026-01-12T01:02:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qagv2f/glm47_can_replace_opus_45_and_gemini_3/ | Impressive-Olive8372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qagv2f | false | null | t3_1qagv2f | /r/LocalLLaMA/comments/1qagv2f/glm47_can_replace_opus_45_and_gemini_3/ | false | false | 1 | null | |
Qwen cutoff date makes our current reality too dystopian to be credible | 281 | I provided some recent news articles from reputable sources and some wikipedia and Qwen flatout refuses to believe any of it. Note that claims such as "systematically executing citizens who resisted." were never in the prompt or the sources! / Qwen-3-80B
Today at 01:30
Understood. Here is the list, stripped of refere... | 2026-01-12T00:38:33 | https://www.reddit.com/r/LocalLLaMA/comments/1qagaaq/qwen_cutoff_date_makes_our_current_reality_too/ | Swimming_Cover_9686 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qagaaq | false | null | t3_1qagaaq | /r/LocalLLaMA/comments/1qagaaq/qwen_cutoff_date_makes_our_current_reality_too/ | false | false | self | 281 | null |
Hunyuan MT-1.5 Demo | 33 | Recently, Hunyuan released a new translation model called [MT-1.5](https://huggingface.co/tencent/HY-MT1.5-7B).
It seems like there is no public demo (at least without signup), so I hosted the Q8\_0 version with llama.cpp and a basic frontend to play around with different languages.
I am pretty impressed by the 7B mo... | 2026-01-12T00:26:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qag0nf/hunyuan_mt15_demo/ | finanzwegwerf20 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qag0nf | false | null | t3_1qag0nf | /r/LocalLLaMA/comments/1qag0nf/hunyuan_mt15_demo/ | false | false | self | 33 | {'enabled': False, 'images': [{'id': 'VSVTZL0u39kj1Rt8FJu3a5nTaIYOY7QPC3Xw6R-dwvw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/VSVTZL0u39kj1Rt8FJu3a5nTaIYOY7QPC3Xw6R-dwvw.png?width=108&crop=smart&auto=webp&s=d7c0b66e08004befb670aa6ea919715c92dae63e', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone using “JSON Patch” (RFC 6902) to fix only broken parts of LLM JSON outputs? | 0 | Hi folks — I’m building a pipeline where an LLM extracts a large structured JSON (100+ items) from documents. I run a deterministic validator (schema + business invariants). When validation fails, I currently ask another LLM call to “fix it”… but it re-outputs the entire JSON, which:
• wastes tokens
• risks mutating ... | 2026-01-12T00:25:52 | https://www.reddit.com/r/LocalLLaMA/comments/1qafzs9/anyone_using_json_patch_rfc_6902_to_fix_only/ | Professional_Term579 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qafzs9 | false | null | t3_1qafzs9 | /r/LocalLLaMA/comments/1qafzs9/anyone_using_json_patch_rfc_6902_to_fix_only/ | false | false | self | 0 | null |
4x RTX 6000 Pro LACT Config | 4 | Took a little tuning but I was able to get this config working for LACT with my Blackwells on a single 1600 Watt GPU.
This likely can still be optimized but should serve as a good starting point for anyone else running 4 Blackwell GPUs from one 1600W PSU
version: 5
daemon:
log_level: info
admin_... | 2026-01-12T00:16:07 | https://www.reddit.com/r/LocalLLaMA/comments/1qafrp8/4x_rtx_6000_pro_lact_config/ | I-cant_even | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qafrp8 | false | null | t3_1qafrp8 | /r/LocalLLaMA/comments/1qafrp8/4x_rtx_6000_pro_lact_config/ | false | false | self | 4 | null |
Best practices for running a CPU-only RAG chatbot in production? | 0 | Hi r/LocalLLaMA 👋
My company is planning to deploy a **production RAG-based chatbot that must run entirely on CPU** (no GPUs available in deployment). I’m looking for **general guidance and best practices** from people who’ve done this in real-world setups.
# What we’re trying to solve
* Question-answering chatbot ... | 2026-01-11T23:54:30 | https://www.reddit.com/r/LocalLLaMA/comments/1qaf985/best_practices_for_running_a_cpuonly_rag_chatbot/ | Acceptable_Young_167 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaf985 | false | null | t3_1qaf985 | /r/LocalLLaMA/comments/1qaf985/best_practices_for_running_a_cpuonly_rag_chatbot/ | false | false | self | 0 | null |
Unstable Video Understanding in Gemini 3 Pro API | 1 | [removed] | 2026-01-11T23:19:02 | https://www.reddit.com/r/LocalLLaMA/comments/1qaefca/unstable_video_understanding_in_gemini_3_pro_api/ | Feisty_Complaint_683 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaefca | false | null | t3_1qaefca | /r/LocalLLaMA/comments/1qaefca/unstable_video_understanding_in_gemini_3_pro_api/ | false | false | self | 1 | null |
I vibe-coded a "System 2" Agentic Terminal (Local Reflection + Audit Logs), but I only have 6GB VRAM. I need you to test it on real local hardware. | 0 | **Repo:** [https://github.com/Prof-Harita/terminaI](https://github.com/Prof-Harita/terminaI)
I’ve been frustrated that most "AI Terminals" (Warp, Cursor) are just SaaS wrappers that stream your shell history to the cloud. I wanted an operator that runs **locally**, uses my own endpoints (perfect for **Ollama**), and a... | 2026-01-11T23:18:43 | Embarrassed-Mail267 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qaef36 | false | null | t3_1qaef36 | /r/LocalLLaMA/comments/1qaef36/i_vibecoded_a_system_2_agentic_terminal_local/ | false | false | nsfw | 0 | {'enabled': True, 'images': [{'id': 'm5nvcsugzscg1', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/m5nvcsugzscg1.gif?width=108&crop=smart&format=png8&s=97bfbfe8e80863dc3801060ca31a10977473566a', 'width': 108}, {'height': 124, 'url': 'https://preview.redd.it/m5nvcsugzscg1.gif?width=216&crop=smart&format... | |
Patch applying models? | 1 | What are the best models for applying a patch? I mean for example GPT 5.2 regularly returns code in a "git diff" format, which cannot be applied by normal CLI tools like patch as they are not perfectly formatted.
I can of course call Sonnet 4.5 on these patches and have them applied knowing the context of the full con... | 2026-01-11T23:17:36 | https://www.reddit.com/r/LocalLLaMA/comments/1qaee2d/patch_applying_models/ | hyperknot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaee2d | false | null | t3_1qaee2d | /r/LocalLLaMA/comments/1qaee2d/patch_applying_models/ | false | false | self | 1 | null |
Help find the combination of Voice assistant/companion + text to speech+ auto conversation advancement + websearch | 2 | **Ok, first of all be gentle if you are going to scold me.**
I feel like im all over the place still trying to make heads or tales of the AI technology and was just able to pick pieces here and there.
While i appreciate all the efforts done by communities like this, i still feel lost.
I've been searching for a while... | 2026-01-11T22:57:13 | https://www.reddit.com/r/LocalLLaMA/comments/1qadvu0/help_find_the_combination_of_voice/ | NineBiscuit | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qadvu0 | false | null | t3_1qadvu0 | /r/LocalLLaMA/comments/1qadvu0/help_find_the_combination_of_voice/ | false | false | self | 2 | null |
I think coding agent tools are not the (local) way | 0 | Disclaimer: not a dev and I love talking about stuff I do not really know.
I was reading that:
https://www.anthropic.com/engineering/advanced-tool-use
.. and thinking: really?? These experts implemented such stuff so late?! They really seem to want to push their models capabilities by trying not to parasite their c... | 2026-01-11T22:39:49 | https://www.reddit.com/r/LocalLLaMA/comments/1qadg8a/i_think_coding_agent_tools_are_not_the_local_way/ | Leflakk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qadg8a | false | null | t3_1qadg8a | /r/LocalLLaMA/comments/1qadg8a/i_think_coding_agent_tools_are_not_the_local_way/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '0ymN9mKePsRSOq0uZR5v730sv6sf6hU8RlP5DcrzGOM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/0ymN9mKePsRSOq0uZR5v730sv6sf6hU8RlP5DcrzGOM.png?width=108&crop=smart&auto=webp&s=409e253029e1dda5b5af6b2223c4c50aa2124bd1', 'width': 108}, {'height': 113, 'url': 'h... |
STELLA - A simple linux shell agent experiment | 8 | I am experimenting with LangChain/Ollama and I have created this simple shell (bash) agent. It has four tools: run local/remote commands (ssh), read/write files. It has command sanitization (avoids getting caught in interactive commands) confirmation for running risky commands / sudo. Interactive and non interactive m... | 2026-01-11T22:26:42 | https://www.reddit.com/gallery/1qad4i4 | petyussz | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qad4i4 | false | null | t3_1qad4i4 | /r/LocalLLaMA/comments/1qad4i4/stella_a_simple_linux_shell_agent_experiment/ | false | false | 8 | null | |
[2512.14982] Prompt Repetition Improves Non-Reasoning LLMs | 13 | 2026-01-11T22:19:43 | https://arxiv.org/abs/2512.14982 | Thrumpwart | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1qacy7z | false | null | t3_1qacy7z | /r/LocalLLaMA/comments/1qacy7z/251214982_prompt_repetition_improves_nonreasoning/ | false | false | default | 13 | null | |
Deepseek OCRs wrong years | 2 | 2026-01-11T22:18:05 | https://www.reddit.com/r/LocalLLaMA/comments/1qacwq6/deepseek_ocrs_wrong_years/ | danboldis | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qacwq6 | false | null | t3_1qacwq6 | /r/LocalLLaMA/comments/1qacwq6/deepseek_ocrs_wrong_years/ | false | false | 2 | null | ||
Organize and auto-rename image files with a local LLaMA/LLaVA GUI | 2 | This is a major update to an open-source desktop file organization tool I’ve been maintaining - AI File Sorter 1.5.
The focus of this release is local image content analysis and rename workflows, while keeping everything fully offline and under user control. Runs on Windows, macOS, and Linux.
Designed for people who ... | 2026-01-11T21:46:36 | https://www.reddit.com/r/LocalLLaMA/comments/1qac3qg/organize_and_autorename_image_files_with_a_local/ | ph0tone | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qac3qg | false | null | t3_1qac3qg | /r/LocalLLaMA/comments/1qac3qg/organize_and_autorename_image_files_with_a_local/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'NpkG83HCUQepjUodBoPD_KhiDtaFEoMS2DSQTy1CMmA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/NpkG83HCUQepjUodBoPD_KhiDtaFEoMS2DSQTy1CMmA.png?width=108&crop=smart&auto=webp&s=b5507e1783686cf51ec649d23bab13d32ae216c1', 'width': 108}, {'height': 108, 'url': 'h... | |
Model Comparison: GLM-4.7 vs DeepSeek-R1 on detecting logical false equivalencies in structured analogies. | 1 | 2026-01-11T21:38:13 | https://www.reddit.com/gallery/1qabw10 | DowntownAd7954 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qabw10 | false | null | t3_1qabw10 | /r/LocalLLaMA/comments/1qabw10/model_comparison_glm47_vs_deepseekr1_on_detecting/ | false | false | 1 | null | ||
Contrast Test: GLM-4.7 (Chinese SOTA) correctly identifies the "Diabetes Analogy" logic failure, while DeepSeek-R1 defends it. | 1 | [removed] | 2026-01-11T21:18:20 | https://www.reddit.com/r/LocalLLaMA/comments/1qabdg3/contrast_test_glm47_chinese_sota_correctly/ | DowntownAd7954 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qabdg3 | false | null | t3_1qabdg3 | /r/LocalLLaMA/comments/1qabdg3/contrast_test_glm47_chinese_sota_correctly/ | false | false | self | 1 | null |
I prayed that China success with their chip game | 47 | Jensen Huang seems like a nice guy but his strategy has been very rushless when come to business and it frustrated me a bit.
\- Get rid of NVLink
\- Limited production for high VRAM GPU
Same stuff with all of the Western chip companies. It seems like nowaday they just make and sell stuff to each others cause of... | 2026-01-11T21:16:44 | https://www.reddit.com/r/LocalLLaMA/comments/1qabbww/i_prayed_that_china_success_with_their_chip_game/ | pbad1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qabbww | false | null | t3_1qabbww | /r/LocalLLaMA/comments/1qabbww/i_prayed_that_china_success_with_their_chip_game/ | false | false | self | 47 | null |
Control LLM from iOS | 0 | Hi, I've a macbook and an iphone. I'm trying to chat with the LLM on my macbook and have it run commands (like execute this bash script, git push, etc). All I'm able to find are chat clients that use third-party llm providers (chatgpt, claude, etc) but can't actually run commands, which kinda defeats the point.
Maybe ... | 2026-01-11T21:13:00 | https://www.reddit.com/r/LocalLLaMA/comments/1qab8ea/control_llm_from_ios/ | PickleSavings1626 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qab8ea | false | null | t3_1qab8ea | /r/LocalLLaMA/comments/1qab8ea/control_llm_from_ios/ | false | false | self | 0 | null |
Someone finally broke down the "Diabetes Analogy" lie with pure logic. Why can't corporate AI admit this? | 0 | Analyze the User's Request: Topic: The medical analogy "Mental illness is like diabetes." Comparison Basis: Strictly on diagnostic biomarkers (Insulin/Glucose vs. DSM criteria). Core Question: Does the lack of objective pathology in psychiatry render this a logical false equivalence, or is it scientifically sound? Deco... | 2026-01-11T21:06:29 | https://www.reddit.com/r/LocalLLaMA/comments/1qab28o/someone_finally_broke_down_the_diabetes_analogy/ | DowntownAd7954 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qab28o | false | null | t3_1qab28o | /r/LocalLLaMA/comments/1qab28o/someone_finally_broke_down_the_diabetes_analogy/ | false | false | self | 0 | null |
Agentic judge models | 4 | Has anyone found a good solution for agentic judge models that judge the outputs of other LLMs?
Something in the 4-9B range would be ideal maybe but bigger is okay
Can the tiny 1-3B models do this or are they too small?
Are there any good github repos on this topic? | 2026-01-11T21:05:57 | https://www.reddit.com/r/LocalLLaMA/comments/1qab1rx/agentic_judge_models/ | SlowFail2433 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qab1rx | false | null | t3_1qab1rx | /r/LocalLLaMA/comments/1qab1rx/agentic_judge_models/ | false | false | self | 4 | null |
LLM trained from scratch on 1800s London texts (1.2B params, 90GB dataset) | 957 | Hi everyone, I wanted to share an update on my open source project called TimeCapsuleLLM, I train language models from scratch using data from a single time period and location to reduce modern bias.
The newest model is trained only on texts published in London between 1800-1875. There is no fine tuning, no modern dat... | 2026-01-11T21:00:37 | https://www.reddit.com/r/LocalLLaMA/comments/1qaawts/llm_trained_from_scratch_on_1800s_london_texts/ | Remarkable-Trick-177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaawts | false | null | t3_1qaawts | /r/LocalLLaMA/comments/1qaawts/llm_trained_from_scratch_on_1800s_london_texts/ | false | false | 957 | null | |
The RI Model (Index Resonance) is a philosophical and mathematical framework describing the "source code" of the Universe. While RI explains how data is processed "under the hood". Here are the 9 fundamental laws: from the Law of the Basis to Energy Fixation. | 0 | 2026-01-11T20:59:46 | https://www.reddit.com/gallery/1qaaw03 | erikqamalyan | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qaaw03 | false | null | t3_1qaaw03 | /r/LocalLLaMA/comments/1qaaw03/the_ri_model_index_resonance_is_a_philosophical/ | false | false | 0 | null | ||
Slop machines still | 0 | I've been using LLMs **A LOT** for learning over the last few years.
I thought I didn't have issues with hallucinations because I know I don't give up until I actually understand something and it makes sense to me.
But recently I was exploring a subject and I realised I have to be extra careful when prompting. You mi... | 2026-01-11T20:57:26 | https://www.reddit.com/r/LocalLLaMA/comments/1qaatwa/slop_machines_still/ | Either-Job-341 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaatwa | false | null | t3_1qaatwa | /r/LocalLLaMA/comments/1qaatwa/slop_machines_still/ | false | false | self | 0 | null |
LLM trained from scratch on 1800s London texts (1.2B params, 90GB dataset) | 1 | Hi everyone, I wanted to share an update on my open source project called TimeCapsuleLLM, I train language models from scratch using data from a single time period and location to reduce modern bias.
The newest model is trained only on texts published in London between 1800-1875. There is no fine tuning, no modern dat... | 2026-01-11T20:54:31 | https://www.reddit.com/r/LocalLLaMA/comments/1qaarcj/llm_trained_from_scratch_on_1800s_london_texts/ | Remarkable-Trick-177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaarcj | false | null | t3_1qaarcj | /r/LocalLLaMA/comments/1qaarcj/llm_trained_from_scratch_on_1800s_london_texts/ | false | false | self | 1 | null |
It's a very good time to get a 5060ti 16GB | 50 | 16GB vram is enough for ZIT, Qwen-Image-2512 and LTX-2 (tested!). Seems like Image Gen and Vid Gen models are aiming for this range of 16GB VRAM.
Gamers hate this card appearantly, all of them go for the 5070, so max VRAM/$ value (I think this have better value than a used 3090).
RAM price going up, Nvidia might ... | 2026-01-11T20:52:45 | https://www.reddit.com/r/LocalLLaMA/comments/1qaaps7/its_a_very_good_time_to_get_a_5060ti_16gb/ | pbad1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaaps7 | false | null | t3_1qaaps7 | /r/LocalLLaMA/comments/1qaaps7/its_a_very_good_time_to_get_a_5060ti_16gb/ | false | false | self | 50 | null |
Benchmarks of Radeon 780M iGPU with shared 128GB DDR5 RAM running various MoE models under Llama.cpp | 18 | I've been looking for a budget system capable of running the later MoE models for basic one-shot queries. Main goal was finding something energy efficient to keep online 24/7 without racking up an exorbitant electricity bill.
I eventually settled on a refurbished Minisforum UM890 Pro which at the time, September, seem... | 2026-01-11T20:51:53 | https://www.reddit.com/r/LocalLLaMA/comments/1qaap05/benchmarks_of_radeon_780m_igpu_with_shared_128gb/ | AzerbaijanNyan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaap05 | false | null | t3_1qaap05 | /r/LocalLLaMA/comments/1qaap05/benchmarks_of_radeon_780m_igpu_with_shared_128gb/ | false | false | self | 18 | null |
LLM trained from scratch on 1800s London texts (1.2B params, 90GB dataset) | 1 | hello | 2026-01-11T20:51:27 | https://www.reddit.com/r/LocalLLaMA/comments/1qaaomq/llm_trained_from_scratch_on_1800s_london_texts/ | Remarkable-Trick-177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaaomq | false | null | t3_1qaaomq | /r/LocalLLaMA/comments/1qaaomq/llm_trained_from_scratch_on_1800s_london_texts/ | false | false | self | 1 | null |
Training a language model from scratch on 19th century London texts | 1 | [removed] | 2026-01-11T20:50:13 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qaanie | false | null | t3_1qaanie | /r/LocalLLaMA/comments/1qaanie/training_a_language_model_from_scratch_on_19th/ | false | false | default | 1 | null | ||
Fine tune | 1 | Hey eveyrone, I'm new in Fine Tuning model, can someone explain me how to do it ? I have some models and I want to fine tune them with datasets. Can someone help me please ? Btw someone told me that lm studio is a good software to fine tune model.
Thanks | 2026-01-11T20:47:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qaalez/fine_tune/ | youyou0812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaalez | false | null | t3_1qaalez | /r/LocalLLaMA/comments/1qaalez/fine_tune/ | false | false | self | 1 | null |
hi | 1 | [deleted] | 2026-01-11T20:47:51 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qaalao | false | null | t3_1qaalao | /r/LocalLLaMA/comments/1qaalao/hi/ | false | false | default | 1 | null | ||
Training an LLM from scratch on only 1800s London text - 1.2B params, 90GB dataset | 1 | [removed] | 2026-01-11T20:42:21 | https://www.reddit.com/r/LocalLLaMA/comments/1qaaga1/training_an_llm_from_scratch_on_only_1800s_london/ | Remarkable-Trick-177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qaaga1 | false | null | t3_1qaaga1 | /r/LocalLLaMA/comments/1qaaga1/training_an_llm_from_scratch_on_only_1800s_london/ | false | false | self | 1 | null |
LG's K-Exaone breaks into global top 10 AI rankings, tops South Korea | 18 | 2026-01-11T20:23:20 | https://m.koreaherald.com/article/10652980 | self-fix | m.koreaherald.com | 1970-01-01T00:00:00 | 0 | {} | 1qa9z13 | false | null | t3_1qa9z13 | /r/LocalLLaMA/comments/1qa9z13/lgs_kexaone_breaks_into_global_top_10_ai_rankings/ | false | false | default | 18 | {'enabled': False, 'images': [{'id': 'zsdIgzCA4Co7FIGifQyqSsmD_BRUFvhPhc7XFBhC0gc', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/zsdIgzCA4Co7FIGifQyqSsmD_BRUFvhPhc7XFBhC0gc.png?width=108&crop=smart&auto=webp&s=9740a1c4207c2bee416ec8dcbccb1d4e907f129f', 'width': 108}, {'height': 129, 'url': 'h... | |
Does anyone know what Nvidia's release cadence/schedule is? | 1 | 2026-01-11T20:07:34 | kr_tech | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa9k2t | false | null | t3_1qa9k2t | /r/LocalLLaMA/comments/1qa9k2t/does_anyone_know_what_nvidias_release/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Q8-dttQ_8X23XadPEl8ZAhQhtp5obcF-DJQuYTkuqy0', 'resolutions': [{'height': 22, 'url': 'https://preview.redd.it/xjmpzsag1scg1.png?width=108&crop=smart&auto=webp&s=7663689a7cac4615144fa55abe17f5bedba9dfe6', 'width': 108}, {'height': 45, 'url': 'https://preview.redd.it/xjmpzsag1scg1.png?... | |||
Dual Strix Halo: No Frankenstein setup, no huge power bill, big LLMs | 99 | *Processing img 0vkkozxhyrcg1...*
Software on Strix Halo is reaching a point where it can be used, even with networking two of these PCs and taking advantage of both iGPUs and their 256GB of quad channel DDR5-8000 memory. It requires some research still, I can highly recommend the [Strix Halo wiki](https://strixhalo.w... | 2026-01-11T20:00:56 | https://www.reddit.com/r/LocalLLaMA/comments/1qa9dha/dual_strix_halo_no_frankenstein_setup_no_huge/ | Zyj | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa9dha | false | null | t3_1qa9dha | /r/LocalLLaMA/comments/1qa9dha/dual_strix_halo_no_frankenstein_setup_no_huge/ | false | false | self | 99 | null |
Best AI setup for intelligent srt subtitles translation | 0 | Okay so basically I'm trying to translate tons of srt files (cations subtitles) from one language to another and I'm trying to do it intelligently sentence by sentence and not line by line.
My hardware:
CPU 5900x
RAM 64gb + (up to 80gb)
GPU 4070 12GB VRAM
I've tried various versions of deepseek such as 7b, 8b... | 2026-01-11T19:37:18 | https://www.reddit.com/r/LocalLLaMA/comments/1qa8r31/best_ai_setup_for_intelligent_srt_subtitles/ | CaterpillarOne6711 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa8r31 | false | null | t3_1qa8r31 | /r/LocalLLaMA/comments/1qa8r31/best_ai_setup_for_intelligent_srt_subtitles/ | false | false | self | 0 | null |
Having issues with LM Studio | 0 | I need help please.
I have LM Studio 0.3.37 for Windows installed with 3 LLMs and all is well.
Issue is that I would like to have the LLMs go online for more information. It is telling me to look for a "world" icon but there is none anywhere nor in any menu.
There are plugins that are supposed to let the LLM go onl... | 2026-01-11T19:28:48 | https://www.reddit.com/r/LocalLLaMA/comments/1qa8iwq/having_issues_with_lm_studio/ | cmdrmcgarrett | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa8iwq | false | null | t3_1qa8iwq | /r/LocalLLaMA/comments/1qa8iwq/having_issues_with_lm_studio/ | false | false | self | 0 | null |
Harbor - your entire LLM stack | 1 | **What is this?**
A single CLI and a companion Desktop App to manage 100+ LLM-related services. Inference backends, WebUIs, and services that make local LLMs useful.
[https://github.com/av/harbor](https://github.com/av/harbor) | 2026-01-11T18:38:01 | https://v.redd.it/5upng22flrcg1 | Everlier | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa758a | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/5upng22flrcg1/DASHPlaylist.mpd?a=1770748700%2CYjBlNjNiZmMwZTI0ZmI3MWNkNDQ3OTM3MTcyMGM3YTgwZjZmNGYxMTFhY2E1YTBmMGJjNThlYWE2Y2YzYmY4YQ%3D%3D&v=1&f=sd', 'duration': 26, 'fallback_url': 'https://v.redd.it/5upng22flrcg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1qa758a | /r/LocalLLaMA/comments/1qa758a/harbor_your_entire_llm_stack/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'bTJyOWplMWZscmNnMSjzHEgGc-VQ8Vod2034nme6jK2lafQN66FwfoZMihDa', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bTJyOWplMWZscmNnMSjzHEgGc-VQ8Vod2034nme6jK2lafQN66FwfoZMihDa.png?width=108&crop=smart&format=pjpg&auto=webp&s=44cd6f1e240fbb5975604a3bfad2211f838c2... | |
LM Studio slow download speeds | 1 | I have no idea what to do anymore. For some reason, my LM Studio download speeds are slow as fuck. It's like it's capped at 7MB/s.
When I pause and unpause a download, it reaches the max speed (50mb/s) for like 2 seconds and then it throttles to 10mb/s and then 7mb/s. I have no idea what to do anymore.
My netw... | 2026-01-11T18:32:49 | https://www.reddit.com/r/LocalLLaMA/comments/1qa7045/lm_studio_slow_download_speeds/ | Socializandopa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa7045 | false | null | t3_1qa7045 | /r/LocalLLaMA/comments/1qa7045/lm_studio_slow_download_speeds/ | false | false | self | 1 | null |
Has anyone tried managing RAG pipelines via a CLI instead of frameworks? | 0 | I came across an open-source project called ragctl that takes an unusual approach to RAG.
Instead of adding another abstraction layer or framework, it treats RAG pipelines more like infrastructure:
- CLI-driven workflows
- explicit, versioned components
- focus on reproducibility and inspection rather than... | 2026-01-11T18:25:59 | https://www.reddit.com/r/LocalLLaMA/comments/1qa6t9i/has_anyone_tried_managing_rag_pipelines_via_a_cli/ | ApartmentHappy9030 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa6t9i | false | null | t3_1qa6t9i | /r/LocalLLaMA/comments/1qa6t9i/has_anyone_tried_managing_rag_pipelines_via_a_cli/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'mPrhODNatlHJohfD5BS6zdfyOUEUPC8BSn5fcxbMYYo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mPrhODNatlHJohfD5BS6zdfyOUEUPC8BSn5fcxbMYYo.png?width=108&crop=smart&auto=webp&s=5c13d048dcd433b191c714b545e1a597a157d3f7', 'width': 108}, {'height': 108, 'url': 'h... |
Attractor Mapping: Force Your Model to Actually Say Something | 0 | Hey everyone,
I've been working on a system for a simple AI debate platform, just to see if I could get a model to debate with itself using different system prompts.
I found that no matter what I tried, the system would always end up producing various shades of "blockchain enabled community focused" etc etc. Th... | 2026-01-11T18:09:04 | https://www.reddit.com/r/LocalLLaMA/comments/1qa6d36/attractor_mapping_force_your_model_to_actually/ | InvertedVantage | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa6d36 | false | null | t3_1qa6d36 | /r/LocalLLaMA/comments/1qa6d36/attractor_mapping_force_your_model_to_actually/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'HpdXyWqQDPYRbzGE02TbozuQerVqNatnLxHggCLnbsY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/HpdXyWqQDPYRbzGE02TbozuQerVqNatnLxHggCLnbsY.png?width=108&crop=smart&auto=webp&s=80b95a9d2e92296759442b1f2d2c16e90d59ecca', 'width': 108}, {'height': 108, 'url': 'h... |
I built a Cursor for Computer Use automation that runs 4 agents in parallel locally | 2 | Hey all, built this IDE to create deterministic computer use workflows that runs locally, it's free, open source.
Any idea what kind of workflow you do regularly you would automate on your computer?
PS: workflow presented just for demo purpose, it's against linkedin rules | 2026-01-11T17:52:43 | https://v.redd.it/8wesrny6brcg1 | louis3195 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa5x9x | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/8wesrny6brcg1/DASHPlaylist.mpd?a=1770745984%2CZTU4ZjYyM2FmODM3NDY5YjAzMmQ0NDNiMWM4YmYxNThjMzdjNGQxNmZkYmY0YTA1NDk1ZTdlYmVmMDExODI4Mw%3D%3D&v=1&f=sd', 'duration': 121, 'fallback_url': 'https://v.redd.it/8wesrny6brcg1/CMAF_1080.mp4?source=fallback', '... | t3_1qa5x9x | /r/LocalLLaMA/comments/1qa5x9x/i_built_a_cursor_for_computer_use_automation_that/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'Nms2NDBiejZicmNnMUBeqWUqXhA9W8PjQEfgUyoH1b9HCQAgyXzrDNbhEGeY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Nms2NDBiejZicmNnMUBeqWUqXhA9W8PjQEfgUyoH1b9HCQAgyXzrDNbhEGeY.png?width=108&crop=smart&format=pjpg&auto=webp&s=7783d0234d49a18f4ee19a73cd3ac38ad0e2a... | |
Do you think my idea is feasible? What do you think of this idea? | 0 | **My tech stack is essentially a 'DeAI with a Physical Anchor.' It consists of three layers:"**
**1. The Swarm (Federated Compute):** \> A peer-to-peer network of local SLMs. We use **Federated Learning** to share 'experience signals' (gradients) without ever exchanging raw data. This allows independent models to gain... | 2026-01-11T17:47:42 | https://www.reddit.com/r/LocalLLaMA/comments/1qa5seq/do_you_think_my_idea_is_feasible_what_do_you/ | BoringLuck7545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa5seq | false | null | t3_1qa5seq | /r/LocalLLaMA/comments/1qa5seq/do_you_think_my_idea_is_feasible_what_do_you/ | false | false | self | 0 | null |
From WoW benders and hangovers to a 165-tool autonomous AI agent in 6 days (with zero coding skills) | 0 | Hey everyone,
I wanted to share something that honestly surprised the hell out of me over the last week. This isn’t a "success story" or a coding flex — mostly because I genuinely can’t code in any traditional sense. It’s more of a case study in what happens when technical and psychological barriers collapse at the sa... | 2026-01-11T17:47:30 | https://www.reddit.com/r/LocalLLaMA/comments/1qa5s71/from_wow_benders_and_hangovers_to_a_165tool/ | Neat_Play9128 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa5s71 | false | null | t3_1qa5s71 | /r/LocalLLaMA/comments/1qa5s71/from_wow_benders_and_hangovers_to_a_165tool/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'LgyfwxwQAGDzMtCxhRiJdwfO-2ebjnFA0-64tQ3kVhM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/LgyfwxwQAGDzMtCxhRiJdwfO-2ebjnFA0-64tQ3kVhM.png?width=108&crop=smart&auto=webp&s=3848324a5ff19a63d4554a2fd76300e5edfe84a0', 'width': 108}, {'height': 108, 'url': 'h... |
Running language models where they don't belong | 1 | [removed] | 2026-01-11T17:29:27 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1qa5amt | false | null | t3_1qa5amt | /r/LocalLLaMA/comments/1qa5amt/running_language_models_where_they_dont_belong/ | false | false | default | 1 | null | ||
Tired of manual GGUF conversion? Built a Gradio GUI that handles HF downloads, LoRA merging, quantization, and llama.cpp launching | 0 | Hey r/LocalLLaMA! 👋
I got tired of manually converting models to GGUF and constantly forgetting the llama.cpp quantize commands, so I built a tool that does it all with a GUI.
## What it does:
✅ Downloads any HuggingFace model (or converts your fine-tuned checkpoints)
✅ Auto-detects and merges LoRA adapters
✅ Shows ... | 2026-01-11T17:24:20 | https://www.reddit.com/r/LocalLLaMA/comments/1qa55qe/tired_of_manual_gguf_conversion_built_a_gradio/ | PinGUY | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1qa55qe | false | null | t3_1qa55qe | /r/LocalLLaMA/comments/1qa55qe/tired_of_manual_gguf_conversion_built_a_gradio/ | false | false | self | 0 | null |
Running language models where they don't belong | 1 | [removed] | 2026-01-11T17:19:20 | Brief_Argument8155 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa50uz | false | null | t3_1qa50uz | /r/LocalLLaMA/comments/1qa50uz/running_language_models_where_they_dont_belong/ | false | false | nsfw | 1 | {'enabled': True, 'images': [{'id': 'RmIh4uI05yH8IxVYAVkItA-Kpk1MJI-akv7KN0faqdM', 'resolutions': [{'height': 94, 'url': 'https://preview.redd.it/fru2dh2f7rcg1.gif?width=108&crop=smart&format=png8&s=b42e6c2098142e65015f310a0d1f737a1f774b3c', 'width': 108}, {'height': 189, 'url': 'https://preview.redd.it/fru2dh2f7rcg1.g... | |
Pushing language models where they don't belong | 1 | [removed] | 2026-01-11T17:15:01 | Brief_Argument8155 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa4wox | false | null | t3_1qa4wox | /r/LocalLLaMA/comments/1qa4wox/pushing_language_models_where_they_dont_belong/ | false | false | nsfw | 1 | {'enabled': True, 'images': [{'id': 'dbmgkrur6rcg1', 'resolutions': [{'height': 94, 'url': 'https://preview.redd.it/dbmgkrur6rcg1.gif?width=108&crop=smart&format=png8&s=ca0ae995883637ed2ab1a197855daccbc93021e9', 'width': 108}, {'height': 189, 'url': 'https://preview.redd.it/dbmgkrur6rcg1.gif?width=216&crop=smart&format... | |
Pushing language models where they don't belong | 1 | [removed] | 2026-01-11T17:12:13 | Brief_Argument8155 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1qa4txi | false | null | t3_1qa4txi | /r/LocalLLaMA/comments/1qa4txi/pushing_language_models_where_they_dont_belong/ | false | false | nsfw | 1 | {'enabled': True, 'images': [{'id': 'z9cqzzka6rcg1', 'resolutions': [{'height': 94, 'url': 'https://preview.redd.it/z9cqzzka6rcg1.gif?width=108&crop=smart&format=png8&s=02c63e83481bfcfca6e43d8a2b8f7ab2632a6f6b', 'width': 108}, {'height': 189, 'url': 'https://preview.redd.it/z9cqzzka6rcg1.gif?width=216&crop=smart&format... | |
Open Models Are Now Frontier Models | 21 | CES 2026 | 2026-01-11T17:08:24 | https://www.youtube.com/watch?v=mCcXwBdQpf8 | jacek2023 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1qa4q8m | false | {'oembed': {'author_name': 'NVIDIA Developer', 'author_url': 'https://www.youtube.com/@NVIDIADeveloper', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/mCcXwBdQpf8?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media;... | t3_1qa4q8m | /r/LocalLLaMA/comments/1qa4q8m/open_models_are_now_frontier_models/ | false | false | default | 21 | {'enabled': False, 'images': [{'id': 'ANuVteKDUN2HVuOpqEJfoAjatmVKSVbeCa4mmOeNlZ4', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/ANuVteKDUN2HVuOpqEJfoAjatmVKSVbeCa4mmOeNlZ4.jpeg?width=108&crop=smart&auto=webp&s=0ec65fb93822e1a2d91e711f308d6ddd5a6395d3', 'width': 108}, {'height': 162, 'url': '... |
Pushing language models where they don't belong | 1 | [removed] | 2026-01-11T17:07:42 | https://www.reddit.com/gallery/1qa4pkl | Brief_Argument8155 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1qa4pkl | false | null | t3_1qa4pkl | /r/LocalLLaMA/comments/1qa4pkl/pushing_language_models_where_they_dont_belong/ | false | false | nsfw | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.