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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
GPT-OSS DPO/RL fine-tuning, anyone? | 13 | I am quite surprised that I can't find a single example of GPT-OSS fine-tuning with DPO or RL. Anyone tried? I wanted to see some benchmarks before putting time into it. | 2025-10-26T08:04:48 | https://www.reddit.com/r/LocalLLaMA/comments/1ogezrx/gptoss_dporl_finetuning_anyone/ | Few_Art_4147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogezrx | false | null | t3_1ogezrx | /r/LocalLLaMA/comments/1ogezrx/gptoss_dporl_finetuning_anyone/ | false | false | self | 13 | null |
🚀 Sleepless Agent — Turn Your Unused Claude Credits into an Autonomous AgentOS | 0 | Ever looked at your Claude credits and thought… *“man, I’m not even using half of these”?*
What if you could turn that unused compute into something **that works while you sleep**?
That’s what [**Sleepless Agent**](https://github.com/context-machine-lab/sleepless-agent) is about —
an **AgentOS built on Claude Code... | 2025-10-26T07:59:30 | https://www.reddit.com/r/LocalLLaMA/comments/1ogewpr/sleepless_agent_turn_your_unused_claude_credits/ | TimeLover935 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogewpr | false | null | t3_1ogewpr | /r/LocalLLaMA/comments/1ogewpr/sleepless_agent_turn_your_unused_claude_credits/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '2FRCu2CArXZwRYiKx5Eo4r_5lMuwpDwZ_7Tp8zKmb-Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/2FRCu2CArXZwRYiKx5Eo4r_5lMuwpDwZ_7Tp8zKmb-Y.png?width=108&crop=smart&auto=webp&s=87c9910c7357d283025922570df4c802f60cf270', 'width': 108}, {'height': 108, 'url': 'h... |
Hey everyone! Positive update: I've successfully fine-tuned my model! I also have something to ask you all. | 9 | I successfully completed the first fine-tuning on my model! (It's a big model, so there were a lot of trials and errors, lol.)
I'm moving on to the second phase of tuning, which will include **multi-turn dialogue**, **persona**, a bit of **technical Q&A**, and **self-talk/monologues**! (The initial beta test was succe... | 2025-10-26T07:56:23 | https://www.reddit.com/r/LocalLLaMA/comments/1ogev2y/hey_everyone_positive_update_ive_successfully/ | Patience2277 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogev2y | false | null | t3_1ogev2y | /r/LocalLLaMA/comments/1ogev2y/hey_everyone_positive_update_ive_successfully/ | false | false | self | 9 | null |
Matt Shumer's back at it with another shitpost (guy from the Reflection "model" fiasco) | 0 | 2025-10-26T06:40:17 | https://www.pcgamer.com/gaming-industry/tech-investor-declares-ai-games-are-going-to-be-amazing-posts-an-ai-generated-demo-of-a-god-awful-shooter-as-proof/ | LinkSea8324 | pcgamer.com | 1970-01-01T00:00:00 | 0 | {} | 1ogdp0i | false | null | t3_1ogdp0i | /r/LocalLLaMA/comments/1ogdp0i/matt_shumers_back_at_it_with_another_shitpost_guy/ | false | false | 0 | {'enabled': False, 'images': [{'id': '4QQW5LxIaTMVMbv_q1sR40FtsYQi46hhHDr2D3I2Lfo', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/4QQW5LxIaTMVMbv_q1sR40FtsYQi46hhHDr2D3I2Lfo.jpeg?width=108&crop=smart&auto=webp&s=953cfebbb246fa33e3589c0d5c29c854187cb4bc', 'width': 108}, {'height': 121, 'url': '... | ||
Claude 4.x models incorrectly routed to 3.5 Sonnet | 0 | I'm experiencing a critical issue with Claude 4.x models through the API. Both Opus 4.1 and Sonnet 4.5 are incorrectly identifying themselves as Claude 3.5 Sonnet, and demonstrating significantly degraded performance compared to expected capabilities.
Performance testing reveals:
- Opus 4.1: Failed to ... | 2025-10-26T05:44:54 | https://www.reddit.com/r/LocalLLaMA/comments/1ogctiy/claude_4x_models_incorrectly_routed_to_35_sonnet/ | tkenaz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogctiy | false | null | t3_1ogctiy | /r/LocalLLaMA/comments/1ogctiy/claude_4x_models_incorrectly_routed_to_35_sonnet/ | false | false | self | 0 | null |
Why does AI assume every technical question is from a moron? | 0 | It doesn't matter what AI/LLM I talk to. I waste time explaining my technical expertise instead of getting the technical answers I ask for. Every damned one of them, especially local AI, automatically assumes I'm the dumb ass town idiot asking about something I shouldn't mess with. It's infuriating, insulting, and cond... | 2025-10-26T05:37:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ogcp1z/why_does_ai_assume_every_technical_question_is/ | Savantskie1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogcp1z | false | null | t3_1ogcp1z | /r/LocalLLaMA/comments/1ogcp1z/why_does_ai_assume_every_technical_question_is/ | false | false | self | 0 | null |
re:search | 0 | The concept of discussing information openly and honestly has been lost.
Put your LLM down.
I am pleading with you to read this.
I am not trying to sell anything.
I am not trying to prove anything.
I just want to share something.
The most important thing has always been proving my worth to others.
I am only hu... | 2025-10-26T04:51:10 | https://www.reddit.com/r/LocalLLaMA/comments/1ogbxm1/research/ | Ok_Priority_4635 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogbxm1 | false | null | t3_1ogbxm1 | /r/LocalLLaMA/comments/1ogbxm1/research/ | false | false | self | 0 | null |
What UI is best for doing all kind of stuff? | 3 | I've been doing a lot of T2I and some T2V stuff, like training, making workflows, playing with extensions and different tools, etc..
never went deep into LLMs but I want to do that, Which UI(s) is the ideal for this? I wanna test models, training and agents for local usage, integrate with n8n and stuff, creating chars... | 2025-10-26T04:26:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ogbieg/what_ui_is_best_for_doing_all_kind_of_stuff/ | Suimeileo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogbieg | false | null | t3_1ogbieg | /r/LocalLLaMA/comments/1ogbieg/what_ui_is_best_for_doing_all_kind_of_stuff/ | false | false | self | 3 | null |
The Age of Specialization: Why AI Must Fractalize to Generalize | 1 | [removed] | 2025-10-26T04:15:22 | https://www.reddit.com/r/LocalLLaMA/comments/1ogbbrx/the_age_of_specialization_why_ai_must_fractalize/ | ottoborden | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogbbrx | false | null | t3_1ogbbrx | /r/LocalLLaMA/comments/1ogbbrx/the_age_of_specialization_why_ai_must_fractalize/ | false | false | self | 1 | null |
Behavior of agentic coding at the local level? | 8 | I've been using my local Ollama instance with Continue in VSCode for a while as a second-opinion tool, and have wondered about some of the commercial code tools and how they differ. I've come to really appreciate Claude Code's workflow, to-do list management, and overall effectiveness. I've seen tools for connecting it... | 2025-10-26T03:47:20 | https://www.reddit.com/r/LocalLLaMA/comments/1ogatwe/behavior_of_agentic_coding_at_the_local_level/ | SocietyTomorrow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogatwe | false | null | t3_1ogatwe | /r/LocalLLaMA/comments/1ogatwe/behavior_of_agentic_coding_at_the_local_level/ | false | false | self | 8 | null |
MiniMax: MiniMax M2 seems to VERY, VERY good | 63 | Generally use GLM4.6 , been at a few problems most of the week, today thres these at MiniMax: MiniMax M2 and it sorted them with no fuss......Very impressed | 2025-10-26T03:39:02 | https://www.reddit.com/r/LocalLLaMA/comments/1ogaohi/minimax_minimax_m2_seems_to_very_very_good/ | klippers | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogaohi | false | null | t3_1ogaohi | /r/LocalLLaMA/comments/1ogaohi/minimax_minimax_m2_seems_to_very_very_good/ | false | false | self | 63 | null |
Is it normal for models all to use the same names for stories? | 1 | This is an annoying issue that I keep running across but still funny, whenever I do science fiction or horror, all the models love using the names thorne and vance. For a woman, its usally elara vance, and any story featuring a scientist/doctor is usually thomas thorne. Why is that?
I mostly use Cydonia, which is an a... | 2025-10-26T03:18:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ogaan3/is_it_normal_for_models_all_to_use_the_same_names/ | AI_Renaissance | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ogaan3 | false | null | t3_1ogaan3 | /r/LocalLLaMA/comments/1ogaan3/is_it_normal_for_models_all_to_use_the_same_names/ | false | false | self | 1 | null |
All the models seem to love using the same names. | 71 | In particular thorne and vance when doing horror or science fiction, for a woman its almost always elara vance, has anyone else experienced this? | 2025-10-26T03:13:40 | https://www.reddit.com/r/LocalLLaMA/comments/1oga7um/all_the_models_seem_to_love_using_the_same_names/ | AI_Renaissance | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oga7um | false | null | t3_1oga7um | /r/LocalLLaMA/comments/1oga7um/all_the_models_seem_to_love_using_the_same_names/ | false | false | self | 71 | null |
chatllm.cpp supports LLaDA2.0-mini-preview | 7 | ***LLaDA2.0-mini-preview*** *is a diffusion language model featuring a 16BA1B Mixture-of-Experts (MoE) architecture. As an enhanced, instruction-tuned iteration of the LLaDA series, it is optimized for practical applications.*
https://preview.redd.it/6duebltjcdxf1.png?width=1098&format=png&auto=webp&s=92eb42d5346ea7... | 2025-10-26T02:43:31 | https://www.reddit.com/r/LocalLLaMA/comments/1og9nzd/chatllmcpp_supports_llada20minipreview/ | foldl-li | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og9nzd | false | null | t3_1og9nzd | /r/LocalLLaMA/comments/1og9nzd/chatllmcpp_supports_llada20minipreview/ | false | false | 7 | null | |
How good is Ling-1T? | 39 | Apparently there's been a new model by Ant Group (InclusionAI) that is an open-weight non-thinking model with 1000B parameters. According to their article their performance is better than paid models. Has anyone run this yet? | 2025-10-26T02:35:28 | Aware_Magician7958 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1og9ije | false | null | t3_1og9ije | /r/LocalLLaMA/comments/1og9ije/how_good_is_ling1t/ | false | false | 39 | {'enabled': True, 'images': [{'id': 'otgpYtLDXpkJQmBR-9ph4iWWUFS45wo-u3mhR6CbdKw', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/cs7bb6igbdxf1.jpeg?width=108&crop=smart&auto=webp&s=66d6ef5e6a1a38b71b5a57e35e48ee5d939fe583', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/cs7bb6igbdxf1.jp... | ||
Exploring Fine-Tuning Platforms | 1 | I'm curious but if it were up to you, what features would an ideal platform (e.g. Bedrock, Unsloth, Together AI, etc.) NEED to have for you to pay to use it for fine-tuning a model? | 2025-10-26T02:33:37 | https://www.reddit.com/r/LocalLLaMA/comments/1og9h8n/exploring_finetuning_platforms/ | bryanb_roundnet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og9h8n | false | null | t3_1og9h8n | /r/LocalLLaMA/comments/1og9h8n/exploring_finetuning_platforms/ | false | false | self | 1 | null |
As a writer - which model would be better? | 3 | Im actually figuring out which would work better.
I will have a RAG holding my own texts and life informations - so that the moedl knows about these facts.
Then I plan to feed the model with new texts and ideas and have it create scripts from that - in y words and with my added life info.
My machine is a Mac Stud... | 2025-10-26T02:14:31 | https://www.reddit.com/r/LocalLLaMA/comments/1og94c5/as_a_writer_which_model_would_be_better/ | Inevitable_Raccoon_9 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og94c5 | false | null | t3_1og94c5 | /r/LocalLLaMA/comments/1og94c5/as_a_writer_which_model_would_be_better/ | false | false | self | 3 | null |
Community LLM project? | 0 | Hey all. I have made a program that uses multiple accounts on a certain website to generate data from a certain top performing proprietary llm. My plan is to use this data to finetune gpt-oss 120b. I was wondering if anyone else would be interested in assisting with this project. My discord tag is the same as my reddit... | 2025-10-26T01:58:23 | https://www.reddit.com/r/LocalLLaMA/comments/1og8t71/community_llm_project/ | WyattTheSkid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og8t71 | false | null | t3_1og8t71 | /r/LocalLLaMA/comments/1og8t71/community_llm_project/ | false | false | self | 0 | null |
GLM 4.6 reasoning | 4 | I'm using GLM4.6 in Claude Code. Does anyone know how to enable reasoning mode for this model? It seems that CLI Thinking only works with Anthropic models. Can you help me please? | 2025-10-26T01:48:55 | https://www.reddit.com/r/LocalLLaMA/comments/1og8mc7/glm_46_reasoning/ | anthonycdp | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og8mc7 | false | null | t3_1og8mc7 | /r/LocalLLaMA/comments/1og8mc7/glm_46_reasoning/ | false | false | self | 4 | null |
My LLM-powered text adventure needed a dynamic soundtrack, so I'm training a MIDI generation model to compose it on the fly. Here's a video of its progress so far. | 23 | Hey everyone,
I wanted to share a component of a larger project I'm working on called **Synthasia**. It's a text adventure game, but the core idea is to have multiple LLMs working in synergy to create a deeply dynamic and open-ended world. During development, I hit a predictable wall: because the game can go in any di... | 2025-10-26T01:45:03 | https://v.redd.it/fdy23li41dxf1 | orblabs | /r/LocalLLaMA/comments/1og8jil/my_llmpowered_text_adventure_needed_a_dynamic/ | 1970-01-01T00:00:00 | 0 | {} | 1og8jil | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/fdy23li41dxf1/DASHPlaylist.mpd?a=1764164711%2CNzliZmU5MDViNjE5M2ZiMTkwNmQ2NDFkNmIyZmQ4ZGY0Y2MwODExZGZjZDIwNmQ5NDhiMjQwMGEwZTkwNTg5ZA%3D%3D&v=1&f=sd', 'duration': 886, 'fallback_url': 'https://v.redd.it/fdy23li41dxf1/DASH_1080.mp4?source=fallback', '... | t3_1og8jil | /r/LocalLLaMA/comments/1og8jil/my_llmpowered_text_adventure_needed_a_dynamic/ | false | false | 23 | {'enabled': False, 'images': [{'id': 'dXp6ZXRxaTQxZHhmMSaFlwyBbCxWLebwmipVQ7r7-6zFGQDSVaPWFx0zsp7A', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/dXp6ZXRxaTQxZHhmMSaFlwyBbCxWLebwmipVQ7r7-6zFGQDSVaPWFx0zsp7A.png?width=108&crop=smart&format=pjpg&auto=webp&s=3450a239ccb3c496eefe0d2ec6b44d80582ae... | |
If you had $4k, would you invest in a DGX Spark? | 52 | Hey Guys, I am very curious what everyone's opinion is regarding the DGX Spark.
If you had $4k and you needed to use that money to start building out your own personal AI data center, would you buy a DGX Spark... or go a different direction? | 2025-10-26T01:28:00 | https://www.reddit.com/r/LocalLLaMA/comments/1og87pd/if_you_had_4k_would_you_invest_in_a_dgx_spark/ | Excellent_Koala769 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og87pd | false | null | t3_1og87pd | /r/LocalLLaMA/comments/1og87pd/if_you_had_4k_would_you_invest_in_a_dgx_spark/ | false | false | self | 52 | null |
Reinforcement Learning level performance on non-verifiable tasks | 4 | I wanted to put this down somewhere partially so I remember the papers lol.
Reinforcement learning does not teach a model new information or to reason in a way that it could not before. It just makes it more sample efficient to get to answers like the reinforced ones which were already possible with the base model. Th... | 2025-10-26T00:16:03 | https://www.reddit.com/r/LocalLLaMA/comments/1og6sx2/reinforcement_learning_level_performance_on/ | elbiot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og6sx2 | false | null | t3_1og6sx2 | /r/LocalLLaMA/comments/1og6sx2/reinforcement_learning_level_performance_on/ | false | false | self | 4 | null |
Qwen coder local is fabulous. Just a momentary lapse - we get on really well. I told it to take five and get a Monster or something. | 15 | 2025-10-25T23:55:02 | cromagnone | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1og6dis | false | null | t3_1og6dis | /r/LocalLLaMA/comments/1og6dis/qwen_coder_local_is_fabulous_just_a_momentary/ | false | false | 15 | {'enabled': True, 'images': [{'id': 'vHYfVzGj_VwmlJjHkrFw1Kjyxh-ZdV9o0kUiNk-oX8w', 'resolutions': [{'height': 55, 'url': 'https://preview.redd.it/o0yzkkgoicxf1.png?width=108&crop=smart&auto=webp&s=5422f60dbc281259efe3f76588f6642fe08450ef', 'width': 108}, {'height': 110, 'url': 'https://preview.redd.it/o0yzkkgoicxf1.png... | |||
Cursor to Codex CLI: Migrating Rules to AGENTS.md | 1 | I migrated from Cursor to Codex CLI and wrote a Python script to bring my custom Cursor Rules with me. This post has the script and explains how it works. | 2025-10-25T23:22:25 | https://www.adithyan.io/blog/migrating-cursor-rules-to-agents | phoneixAdi | adithyan.io | 1970-01-01T00:00:00 | 0 | {} | 1og5oxr | false | null | t3_1og5oxr | /r/LocalLLaMA/comments/1og5oxr/cursor_to_codex_cli_migrating_rules_to_agentsmd/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'yBBVWvEZ1iNriHxeerfOMOA8JSMVc_I8YUbTVxm-53Y', 'resolutions': [{'height': 61, 'url': 'https://external-preview.redd.it/yBBVWvEZ1iNriHxeerfOMOA8JSMVc_I8YUbTVxm-53Y.jpeg?width=108&crop=smart&auto=webp&s=1a96dba626e31527d9afdda7b69495162327be91', 'width': 108}, {'height': 123, 'url': '... | |
Qwen3-VL-32B at text tasks - some thoughts after using yairpatch's fork and GGUF's | 23 | ## Setup
Using [YairPatch's](https://github.com/yairpatch/llama.cpp) fork and the [Q5 GGUF](https://huggingface.co/yairpatch/Qwen3-VL-32B-Instruct-GGUF/tree/main) from YairPatch's huggingface uploads.
Used a Lambda Labs gh200 instance, but I wasn't really testing for speed so that's less important aside from the fact... | 2025-10-25T22:55:30 | https://www.reddit.com/r/LocalLLaMA/comments/1og54b4/qwen3vl32b_at_text_tasks_some_thoughts_after/ | ForsookComparison | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og54b4 | false | null | t3_1og54b4 | /r/LocalLLaMA/comments/1og54b4/qwen3vl32b_at_text_tasks_some_thoughts_after/ | false | false | self | 23 | {'enabled': False, 'images': [{'id': 'nr7hwPnsJuqWsVyOLsTwbtwdkY9b1KuPXxnKHgldVy0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/nr7hwPnsJuqWsVyOLsTwbtwdkY9b1KuPXxnKHgldVy0.png?width=108&crop=smart&auto=webp&s=9ba729f07211233c259c070b4afb58910f35c633', 'width': 108}, {'height': 108, 'url': 'h... |
How to easily use a chatbot wrapper I made, ollama, gemma 3 abliterated and Coqui TTS to create the ChrisBot uncensored joke telling robot overlord. | 4 | In this post I show off my newest creation, ChrisBot, an AI wrapper for Ollama allowing you to easily edit system prompts and use Coqui text to speech.
This means you can easily make the model uncensored using the following method I document in my blog post.
Basically just load this repo, Ollama, and download and loa... | 2025-10-25T22:55:27 | https://danielkliewer.com/blog/2025-10-25-building-your-own-uncensored-ai-overlord | KonradFreeman | danielkliewer.com | 1970-01-01T00:00:00 | 0 | {} | 1og549p | false | null | t3_1og549p | /r/LocalLLaMA/comments/1og549p/how_to_easily_use_a_chatbot_wrapper_i_made_ollama/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'IIxxQyWdPyEFM8ywRLpf_fPluUqRcqY5a4we-6TrTEM', 'resolutions': [{'height': 90, 'url': 'https://external-preview.redd.it/IIxxQyWdPyEFM8ywRLpf_fPluUqRcqY5a4we-6TrTEM.png?width=108&crop=smart&auto=webp&s=3e692145abe9ada609000a1c9bbf6a0117632424', 'width': 108}, {'height': 181, 'url': 'h... | |
OpenArc 2.0: NPU, Multi-GPU Pipeline Parallell, CPU Tensor Parallell, kokoro, whisper, streaming tool use, openvino llama-bench and more. Apache 2.0 | 25 | Hello!
Today I'm happy to announce [OpenArc 2.0](https://github.com/SearchSavior/OpenArc/tree/2.0) is finally done!! 2.0 brings a full rewrite to support NPU, pipeline parallel for multi GPU, tensor parallel for dual socket CPU, tool use for LLM/VLM, and an **OpenVINO version of llama-bench** and much more.
In the ne... | 2025-10-25T22:28:34 | https://www.reddit.com/r/LocalLLaMA/comments/1og4j8x/openarc_20_npu_multigpu_pipeline_parallell_cpu/ | Echo9Zulu- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og4j8x | false | null | t3_1og4j8x | /r/LocalLLaMA/comments/1og4j8x/openarc_20_npu_multigpu_pipeline_parallell_cpu/ | false | false | self | 25 | null |
Beast AI for translate japanese manga to english? | 0 | I subscribed to ichigo reader and got a choice to what AI use for translate a image
Any advice what select? I can select grok-gemini-kimi and deepseek | 2025-10-25T22:24:53 | https://www.reddit.com/r/LocalLLaMA/comments/1og4gi8/beast_ai_for_translate_japanese_manga_to_english/ | Arkstant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og4gi8 | false | null | t3_1og4gi8 | /r/LocalLLaMA/comments/1og4gi8/beast_ai_for_translate_japanese_manga_to_english/ | false | false | self | 0 | null |
Proper tool calling with gpt-oss | 1 | [removed] | 2025-10-25T21:59:10 | aldegr | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1og3w2u | false | null | t3_1og3w2u | /r/LocalLLaMA/comments/1og3w2u/proper_tool_calling_with_gptoss/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'wM4Q1yLfFhvZ4v1dl6m-jz7X7olwqfiGQtOEKgF9BpI', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/ld28hud6ybxf1.png?width=108&crop=smart&auto=webp&s=654b04b96f1646aab0808c24faaee76081ced15d', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/ld28hud6ybxf1.png... | ||
Proper tool calling with gpt-oss | 1 | [removed] | 2025-10-25T21:47:19 | aldegr | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1og3mej | false | null | t3_1og3mej | /r/LocalLLaMA/comments/1og3mej/proper_tool_calling_with_gptoss/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'kMOAEdCPiGRKFwZTKv307hdUgyazHasAAanmekmHiFM', 'resolutions': [{'height': 54, 'url': 'https://preview.redd.it/bwpka7e1ubxf1.png?width=108&crop=smart&auto=webp&s=084e7148bd9bdb22d4d677c662632c352a885482', 'width': 108}, {'height': 108, 'url': 'https://preview.redd.it/bwpka7e1ubxf1.png... | ||
Llama.cpp model conversion guide | 92 | Since the open source community always benefits by having more people do stuff, I figured I would capitalize on my experiences with a few architectures I've done and add a guide for people who, like me, would like to gain practical experience by porting a model architecture.
Feel free to propose any topics / clarifica... | 2025-10-25T21:35:28 | https://github.com/ggml-org/llama.cpp/discussions/16770 | ilintar | github.com | 1970-01-01T00:00:00 | 0 | {} | 1og3cnt | false | null | t3_1og3cnt | /r/LocalLLaMA/comments/1og3cnt/llamacpp_model_conversion_guide/ | false | false | 92 | {'enabled': False, 'images': [{'id': '9H8ID2ho6Hmpcg_iEkUBl0dzrALfa1J8gFxkkoi6ojc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/9H8ID2ho6Hmpcg_iEkUBl0dzrALfa1J8gFxkkoi6ojc.png?width=108&crop=smart&auto=webp&s=96d15244bd477adc35218a7ed383884e6fb83fb4', 'width': 108}, {'height': 108, 'url': 'h... | |
Is there a leaderboard of current open source models? | 2 | I appologize if this is a question only I don't know the answer to! | 2025-10-25T21:29:33 | https://www.reddit.com/r/LocalLLaMA/comments/1og37oa/is_there_a_leaderboard_of_current_open_source/ | Few-Basil-1185 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og37oa | false | null | t3_1og37oa | /r/LocalLLaMA/comments/1og37oa/is_there_a_leaderboard_of_current_open_source/ | false | false | self | 2 | null |
Who is using Granite 4? What's your use case? | 49 | It's been about 3 weeks since Granite 4 was released with base and instruct versions. If you're using it, what are you using it for? What made you choose it over (or alongside) others? | 2025-10-25T21:01:40 | https://www.reddit.com/r/LocalLLaMA/comments/1og2k8e/who_is_using_granite_4_whats_your_use_case/ | RobotRobotWhatDoUSee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og2k8e | false | null | t3_1og2k8e | /r/LocalLLaMA/comments/1og2k8e/who_is_using_granite_4_whats_your_use_case/ | false | false | self | 49 | {'enabled': False, 'images': [{'id': 'UKX_x2-EVNJEz9GjR6xoQQOlvVV4ZDrjF_HZNgkhbDI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/UKX_x2-EVNJEz9GjR6xoQQOlvVV4ZDrjF_HZNgkhbDI.png?width=108&crop=smart&auto=webp&s=109cc73a8437b544711cd761714adc5f77b8b726', 'width': 108}, {'height': 108, 'url': 'h... |
is MacBook Pro M1 good at working with local llm inference. | 0 | Hi everyone, I’m fairly new to LLMs, so my question may be a little bit silly.
I’m choosing a laptop to run small local models (around 7B–12B parameters) and I’m torn between two options:
MacBook Pro (M1 Pro cpu) — 16 GB RAM, 16 GB VRAM
HP Victus (13th-gen i5, RTX 4050) — 16 GB RAM, 6 GB VRAM
Which one would be better ... | 2025-10-25T20:45:42 | https://www.reddit.com/r/LocalLLaMA/comments/1og26pg/is_macbook_pro_m1_good_at_working_with_local_llm/ | RandRanger | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og26pg | false | null | t3_1og26pg | /r/LocalLLaMA/comments/1og26pg/is_macbook_pro_m1_good_at_working_with_local_llm/ | false | false | self | 0 | null |
FlashPack: High-throughput tensor loading for PyTorch | 9 | FlashPack — a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS).
With FlashPack, loading any model can be 3–6× faster than with the current state-of-the-art methods like `accelerate` or the stand... | 2025-10-25T20:36:37 | https://www.reddit.com/r/LocalLLaMA/comments/1og1z29/flashpack_highthroughput_tensor_loading_for/ | SignificantStop1971 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og1z29 | false | null | t3_1og1z29 | /r/LocalLLaMA/comments/1og1z29/flashpack_highthroughput_tensor_loading_for/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'XqQ_hm7DOmW__mLJOnGBrg2XQr5O6Vlk_-qYGhokUzU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/XqQ_hm7DOmW__mLJOnGBrg2XQr5O6Vlk_-qYGhokUzU.png?width=108&crop=smart&auto=webp&s=f157ba19a2f9e8993d3466d8e82b388aa6984393', 'width': 108}, {'height': 108, 'url': 'h... |
Uncensored AI for scientific research without any filters, and can do very long tasks without bias and overfitting | 0 | Uncensored AI for scientific research without any filters, and can do very long tasks without bias and overfitting
| 2025-10-25T20:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/1og1xkz/uncensored_ai_for_scientific_research_without_any/ | PrintCreepy8982 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og1xkz | false | null | t3_1og1xkz | /r/LocalLLaMA/comments/1og1xkz/uncensored_ai_for_scientific_research_without_any/ | false | false | self | 0 | null |
[P] SpeechAlgo: Open-Source Speech Processing Library for Audio Pipelines | 11 | Released SpeechAlgo - a Python library for speech processing and audio feature extraction.
- Package: pip install speechalgo
- code: https://github.com/tarun7r/SpeechAlgo
Features:
• MFCC, mel-spectrograms, and delta features for ML pipelines
• VAD, pitch detection, and speech enhancement
• 20 + algorithms with cl... | 2025-10-25T20:03:05 | https://www.reddit.com/r/LocalLLaMA/comments/1og16cs/p_speechalgo_opensource_speech_processing_library/ | martian7r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og16cs | false | null | t3_1og16cs | /r/LocalLLaMA/comments/1og16cs/p_speechalgo_opensource_speech_processing_library/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': '-YxD9xE0oZDhxEQtFF19BSJLns4E8jcRSgcz_FLvjhg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-YxD9xE0oZDhxEQtFF19BSJLns4E8jcRSgcz_FLvjhg.png?width=108&crop=smart&auto=webp&s=b5f9df823c165722c0fb0d0c945a264215f357ed', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone know how two daisy chained DGX sparks have been performing yet? | 0 | It'd be nice to see some videos from some YouTube creators using different models and benchmarking. | 2025-10-25T19:47:47 | https://www.reddit.com/r/LocalLLaMA/comments/1og0suf/anyone_know_how_two_daisy_chained_dgx_sparks_have/ | Tired__Dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og0suf | false | null | t3_1og0suf | /r/LocalLLaMA/comments/1og0suf/anyone_know_how_two_daisy_chained_dgx_sparks_have/ | false | false | self | 0 | null |
Recommended models for this use case | 0 | Hey all -- so I've decided that I am gonna host my own LLM for roleplay and chat. I have a 12GB 3060 card -- a Ryzen 9 9950x proc and 64gb of ram. Slowish im ok with SLOW im not --
So what models do you recommend -- i'll likely be using ollama and silly tavern | 2025-10-25T19:46:38 | https://www.reddit.com/r/LocalLLaMA/comments/1og0rs9/recommended_models_for_this_use_case/ | slrg1968 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og0rs9 | false | null | t3_1og0rs9 | /r/LocalLLaMA/comments/1og0rs9/recommended_models_for_this_use_case/ | false | false | self | 0 | null |
Model with no exterior context. | 0 | Is there a model (or a way to make a model) with no existing knowledge other than language, that will only use the info I give it? | 2025-10-25T19:23:25 | https://www.reddit.com/r/LocalLLaMA/comments/1og07f1/model_with_no_exterior_context/ | Kidblunder1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og07f1 | false | null | t3_1og07f1 | /r/LocalLLaMA/comments/1og07f1/model_with_no_exterior_context/ | false | false | self | 0 | null |
GLM 4.5 air for coding | 1 | [removed] | 2025-10-25T19:15:17 | https://www.reddit.com/r/LocalLLaMA/comments/1og009j/glm_45_air_for_coding/ | Magnus114 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1og009j | false | null | t3_1og009j | /r/LocalLLaMA/comments/1og009j/glm_45_air_for_coding/ | false | false | self | 1 | null |
Good open source offline text diff tool? | 0 | The more use AI the more I find myself checking what changes the model made.
In Roo Code there is a diff feature built in which is great, but when use a regular chat model I and defaulting to opening [https://www.diffchecker.com/](https://www.diffchecker.com/) and copy and pasting the previous and new versions of what... | 2025-10-25T19:07:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ofztdl/good_open_source_offline_text_diff_tool/ | RuiRdA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofztdl | false | null | t3_1ofztdl | /r/LocalLLaMA/comments/1ofztdl/good_open_source_offline_text_diff_tool/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'E1x3v60cndigR09Z55eYAb7kpenBrnFpzLAqkUk9H80', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/E1x3v60cndigR09Z55eYAb7kpenBrnFpzLAqkUk9H80.png?width=108&crop=smart&auto=webp&s=0d8536753fc54289c88f4b1f20eab5e642b284f1', 'width': 108}, {'height': 113, 'url': 'h... |
An inherent weakness in open source models | 0 | Closed source models have an advantage in usage data. When you use chatgpt or any other closed source model you're actively training it to be better. With open source models it has no feedback on its work. Is the response good? Bad? Is it just passable? The model has no way of refining itself because of this.
When I ... | 2025-10-25T18:40:27 | https://www.reddit.com/r/LocalLLaMA/comments/1ofz5za/an_inherent_weakness_in_open_source_models/ | Monochrome21 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofz5za | false | null | t3_1ofz5za | /r/LocalLLaMA/comments/1ofz5za/an_inherent_weakness_in_open_source_models/ | false | false | self | 0 | null |
Is there any truly and fully open source LLL? | 0 | Just asking out of curiosity if there is any model with its data and code to train. | 2025-10-25T18:33:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ofyzlh/is_there_any_truly_and_fully_open_source_lll/ | NoFudge4700 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofyzlh | false | null | t3_1ofyzlh | /r/LocalLLaMA/comments/1ofyzlh/is_there_any_truly_and_fully_open_source_lll/ | false | false | self | 0 | null |
Can someone explain this PT-MoE please? | 2 | I don't understand what apple mean why this Parallel Track Mixture of Experts model architecture. I do understand the MoE part but what does the PT part mean? | 2025-10-25T18:11:11 | https://machinelearning.apple.com/research/apple-foundation-models-tech-report-2025 | SrijSriv211 | machinelearning.apple.com | 1970-01-01T00:00:00 | 0 | {} | 1ofyfuh | false | null | t3_1ofyfuh | /r/LocalLLaMA/comments/1ofyfuh/can_someone_explain_this_ptmoe_please/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'D9a4f_PqnwnlUmJ4j6dOW1F7gG_5ht0c45xtUL8kxDY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/D9a4f_PqnwnlUmJ4j6dOW1F7gG_5ht0c45xtUL8kxDY.png?width=108&crop=smart&auto=webp&s=71c7c023a9ec57f87927f898daaedbe1dca2b02a', 'width': 108}, {'height': 113, 'url': 'h... | |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 30 | Hey r/LocalLLaMA,
I've been working on a project that I think this community will really appreciate. It’s called Gemma Web, and it's a completely serverless, private, and offline-first AI workspace that runs Google's Gemma models entirely in your browser.
Live Demo: [https://www.gemmaweb.app/](https://www.gemmaweb.ap... | 2025-10-25T18:11:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ofyfsb/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Abject_Comfort_5220 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofyfsb | false | null | t3_1ofyfsb | /r/LocalLLaMA/comments/1ofyfsb/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 30 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built a 100% private, offline-first AI workspace that runs Gemma in the browser (WASM + RAG). Would love to get feedback from this community! | 1 | [removed] | 2025-10-25T18:05:05 | https://www.reddit.com/r/LocalLLaMA/comments/1ofya99/i_built_a_100_private_offlinefirst_ai_workspace/ | Remarkable_Camp8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofya99 | false | null | t3_1ofya99 | /r/LocalLLaMA/comments/1ofya99/i_built_a_100_private_offlinefirst_ai_workspace/ | false | false | self | 1 | null |
Optimizing gpt-oss-120B on AMD RX 6900 XT 16GB: Achieving 19 tokens/sec | 58 | ## Introduction
OpenAI's gpt-oss-120B is a massive 117B parameter language model, with official recommendations calling for datacenter-grade GPUs like the H100 or MI300X (80GB VRAM). This article documents the optimization journey to run this model at practical speeds (19 tokens/sec) on a consumer AMD RX 6900 X... | 2025-10-25T17:46:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ofxt6s/optimizing_gptoss120b_on_amd_rx_6900_xt_16gb/ | Bright_Resolution_61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofxt6s | false | null | t3_1ofxt6s | /r/LocalLLaMA/comments/1ofxt6s/optimizing_gptoss120b_on_amd_rx_6900_xt_16gb/ | false | false | self | 58 | null |
I built a 100% private, offline-first AI workspace that runs Gemma in the browser (WASM + RAG). Would love to get feedback from this community! | 1 | [removed] | 2025-10-25T17:28:21 | https://gemma-web-ai.vercel.app/ | Dry-Objective-2570 | gemma-web-ai.vercel.app | 1970-01-01T00:00:00 | 0 | {} | 1ofxcyp | false | null | t3_1ofxcyp | /r/LocalLLaMA/comments/1ofxcyp/i_built_a_100_private_offlinefirst_ai_workspace/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... | |
Recommendations - models and GPU | 0 | I'm building a concept device. I'll leave out the major details. But I'm trying to gather ideas and best methods.
I have an ESP32 device gathering data. I want to send this data to an LLM and have it reply / respond accordingly.
Output over TTS is also needed. How do I run, and which LLMs do I run to make this loop... | 2025-10-25T17:26:49 | https://www.reddit.com/r/LocalLLaMA/comments/1ofxbn2/recommendations_models_and_gpu/ | Dino_Walker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofxbn2 | false | null | t3_1ofxbn2 | /r/LocalLLaMA/comments/1ofxbn2/recommendations_models_and_gpu/ | false | false | self | 0 | null |
I built "Gemma Web": A fully private, in-browser AI workspace (Gemma + RAG) that runs 100% offline via WASM. Would love your feedback! | 1 | [removed] | 2025-10-25T17:25:46 | https://www.reddit.com/r/LocalLLaMA/comments/1ofxant/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Dry-Objective-2570 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofxant | false | null | t3_1ofxant | /r/LocalLLaMA/comments/1ofxant/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 1 | [removed] | 2025-10-25T17:21:02 | https://www.reddit.com/r/LocalLLaMA/comments/1ofx6fl/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Weird_Shoulder_2730 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofx6fl | false | null | t3_1ofx6fl | /r/LocalLLaMA/comments/1ofx6fl/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
Hi | 1 | [removed] | 2025-10-25T17:17:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ofx2xs/hi/ | Weird_Shoulder_2730 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofx2xs | false | null | t3_1ofx2xs | /r/LocalLLaMA/comments/1ofx2xs/hi/ | false | false | self | 1 | null |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 1 | [removed] | 2025-10-25T17:10:28 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwwtu/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Remarkable_Camp8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwwtu | false | null | t3_1ofwwtu | /r/LocalLLaMA/comments/1ofwwtu/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
Trying to understand the missing layer in AI infra, where do you see observability & agent debugging going? | 0 | Hey everyone,
I’ve been thinking a lot about how AI systems are evolving, especially with OpenAI’s MCP, LangChain, and all these emerging “agentic” frameworks.
From what I can see, people are building really capable agents… but hardly anyone truly understands what’s happening inside them.
Why an agent made a specific... | 2025-10-25T17:09:34 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwvzl/trying_to_understand_the_missing_layer_in_ai/ | AdVivid5763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwvzl | false | null | t3_1ofwvzl | /r/LocalLLaMA/comments/1ofwvzl/trying_to_understand_the_missing_layer_in_ai/ | false | false | self | 0 | null |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. | 1 | [removed] | 2025-10-25T17:03:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwq7k/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwq7k | false | null | t3_1ofwq7k | /r/LocalLLaMA/comments/1ofwq7k/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. | 1 | [removed] | 2025-10-25T17:00:51 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwnx9/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwnx9 | false | null | t3_1ofwnx9 | /r/LocalLLaMA/comments/1ofwnx9/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 1 | [removed] | 2025-10-25T16:59:10 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwmd2/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwmd2 | false | null | t3_1ofwmd2 | /r/LocalLLaMA/comments/1ofwmd2/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 1 | Hey r/LocalLLaMA,
I've been working on a project that I think this community will really appreciate. It’s called **Gemma Web**, and it's a completely serverless, private, and offline-first AI workspace that runs Google's Gemma models entirely in your browser.
**Live Demo:** [`https://gemma-web-ai.vercel.app/`](https:... | 2025-10-25T16:55:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwixh/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwixh | false | null | t3_1ofwixh | /r/LocalLLaMA/comments/1ofwixh/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. Would love your feedback! | 1 | I've been working on a project that I think this community will really appreciate. It’s called **Gemma Web**, and it's a completely serverless, private, and offline-first AI workspace that runs Google's Gemma models entirely in your browser.
**Live Demo:** [`https://gemma-web-ai.vercel.app/`](https://gemma-web-ai.verc... | 2025-10-25T16:53:55 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwhok/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwhok | false | null | t3_1ofwhok | /r/LocalLLaMA/comments/1ofwhok/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
How to clone a person? | 0 | I don't just mean the text , words and lexicons.
I mean their world view , strategic goals and everything so authentic that it's hard to distinguish each other.
| 2025-10-25T16:53:23 | https://www.reddit.com/r/LocalLLaMA/comments/1ofwh82/how_to_clone_a_person/ | teraflopspeed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofwh82 | false | null | t3_1ofwh82 | /r/LocalLLaMA/comments/1ofwh82/how_to_clone_a_person/ | false | false | self | 0 | null |
I built "Gemma Web": A fully private, in-browser AI workspace that runs 100% offline via WASM. | 3 | Hey r/LocalLLaMA,
I've been working on a project that I think this community will really appreciate. It’s called Gemma Web, and it's a completely serverless, private, and offline-first AI workspace that runs Google's Gemma models entirely in your browser.
Live Demo: [https://gemma-web-ai.vercel.app/](https://gemma-we... | 2025-10-25T16:44:42 | https://www.reddit.com/r/LocalLLaMA/comments/1ofw9ga/i_built_gemma_web_a_fully_private_inbrowser_ai/ | Key-Proposal5664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofw9ga | false | null | t3_1ofw9ga | /r/LocalLLaMA/comments/1ofw9ga/i_built_gemma_web_a_fully_private_inbrowser_ai/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XjlaiEnYGOm9P3vBPd9UEVNFIe2HSoZ5ZF0QnnBeUnU.png?width=108&crop=smart&auto=webp&s=13cb52edf0764b1f659d3ccd5535c10cc4f63b2c', 'width': 108}, {'height': 216, 'url': '... |
Why I Stopped Using Serper and Other SERP APIs for AI Data Projects | 0 | I’ve been experimenting with a few AI projects lately that need **real-time search engine data at scale** — mainly for RAG systems and agents that rely on live web context.
At first, I used some of the well-known SERP APIs (Serper, SerpAPI, etc.), but I quickly hit the same wall:
* Expensive pricing once you go past ... | 2025-10-25T16:32:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ofvy2c/why_i_stopped_using_serper_and_other_serp_apis/ | rxrkrx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofvy2c | false | null | t3_1ofvy2c | /r/LocalLLaMA/comments/1ofvy2c/why_i_stopped_using_serper_and_other_serp_apis/ | false | false | self | 0 | null |
Are local models really good | 1 | I am running gpt oss 20b for home automation using olama as a inferencing server, the server is backed by rtx 5090. I know i can change the name of device to bedroom light, but common the idea of using LLM is to ensure it understands. Any model recommodations which work good for Home Automations , i plan to use same mo... | 2025-10-25T16:03:23 | https://www.reddit.com/r/LocalLLaMA/comments/1ofv8ud/are_local_models_really_good/ | Think_Illustrator188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofv8ud | false | null | t3_1ofv8ud | /r/LocalLLaMA/comments/1ofv8ud/are_local_models_really_good/ | false | false | self | 1 | null |
I rebuilt DeepSeek’s OCR model in Rust so anyone can run it locally (no Python!) | 976 | Hey folks! After wrestling with the original DeepSeek-OCR release (Python + Transformers, tons of dependencies, zero UX), I decided to port the whole inference stack to Rust. The repo is deepseek-ocr.rs (https://github.com/TimmyOVO/deepseek-ocr.rs) and it ships both a
CLI and an OpenAI-compatible server so you can d... | 2025-10-25T15:13:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ofu15a/i_rebuilt_deepseeks_ocr_model_in_rust_so_anyone/ | Outrageous-Voice | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofu15a | false | null | t3_1ofu15a | /r/LocalLLaMA/comments/1ofu15a/i_rebuilt_deepseeks_ocr_model_in_rust_so_anyone/ | false | false | self | 976 | {'enabled': False, 'images': [{'id': 'aINJtHiBev5dmxLITPKF17JnWGrygVOYhvt__C8V8QM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/aINJtHiBev5dmxLITPKF17JnWGrygVOYhvt__C8V8QM.png?width=108&crop=smart&auto=webp&s=2be7cee84444b26fc0e8fe9e7c8b288e514d4fff', 'width': 108}, {'height': 108, 'url': 'h... |
looks like you can use your LM Studio on your iPad via the server API function | 0 | Downloaded this app called Invoke which is free and super easy to use it even provides instructions on how to do it.
Once you install you can just connect to your LM Studio API and load the model of choice.
I even connected to my home Firewall (Cisco) and used Anyconnect VPN to connect to my home network and load up ... | 2025-10-25T15:10:07 | https://www.reddit.com/r/LocalLLaMA/comments/1oftxro/looks_like_you_can_use_your_lm_studio_on_your/ | meshreplacer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oftxro | false | null | t3_1oftxro | /r/LocalLLaMA/comments/1oftxro/looks_like_you_can_use_your_lm_studio_on_your/ | false | false | self | 0 | null |
Single H100: best open-source model + deep thinking setup for reasoning? | 9 | Hi! I have access to a single H100 and want to run an open-source LLM with a multi-agent or “deep thinking” framework for hard math problems and proof generation (hoping to get better results than using just Gemini 2.5 pro).
Looking for advice on the best open-source model for mathematical or logical reasoning that fi... | 2025-10-25T14:49:40 | https://www.reddit.com/r/LocalLLaMA/comments/1oftfoe/single_h100_best_opensource_model_deep_thinking/ | Accomplished_Back718 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oftfoe | false | null | t3_1oftfoe | /r/LocalLLaMA/comments/1oftfoe/single_h100_best_opensource_model_deep_thinking/ | false | false | self | 9 | null |
Conversione .safetensors a.tflite | 2 | Is there a universal .safetensors to .tflite converter? Because I fine-tuned a model and I would like to convert it to .tflite, I've been trying for 2 days but I can't find a solution. I tried with tflite Google AI edge, tf.lite.TFLiteConverter, PyTorch -> ONNX -> TFLite, but none of the methods work. Do you have any a... | 2025-10-25T14:48:26 | https://www.reddit.com/r/LocalLLaMA/comments/1oftelp/conversione_safetensors_atflite/ | fredmore1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oftelp | false | null | t3_1oftelp | /r/LocalLLaMA/comments/1oftelp/conversione_safetensors_atflite/ | false | false | self | 2 | null |
Looking for best Time-Series Data Model for pump or fan prediction on Hugging Face (Any Suggestions?) | 0 | I spent hours on hugging face looking for Time Series Data Model for Pump or Fan prediction but couldn't find a good model that could do predictive analysis, fault prediction and what not... Please suggest the best model on hugging face to analyse time series data with LLM... Thank you for the help... | 2025-10-25T14:16:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ofsn4q/looking_for_best_timeseries_data_model_for_pump/ | Worth-Relation72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofsn4q | false | null | t3_1ofsn4q | /r/LocalLLaMA/comments/1ofsn4q/looking_for_best_timeseries_data_model_for_pump/ | false | false | self | 0 | null |
Looking for best Time-Series Data Model for pump or fan prediction on Hugging Face (Any Suggestions?) | 1 | [removed] | 2025-10-25T14:12:56 | https://www.reddit.com/r/LocalLLaMA/comments/1ofskcu/looking_for_best_timeseries_data_model_for_pump/ | DigTerrible8666 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofskcu | false | null | t3_1ofskcu | /r/LocalLLaMA/comments/1ofskcu/looking_for_best_timeseries_data_model_for_pump/ | false | false | self | 1 | null |
VSORA Launches Europe’s Most Powerful AI Inference Chip | 89 | Seems like a big win for local AI models. | 2025-10-25T13:17:00 | https://finance.yahoo.com/news/vsora-launches-europe-most-powerful-121700744.html | RG54415 | finance.yahoo.com | 1970-01-01T00:00:00 | 0 | {} | 1ofrbcy | false | null | t3_1ofrbcy | /r/LocalLLaMA/comments/1ofrbcy/vsora_launches_europes_most_powerful_ai_inference/ | false | false | 89 | {'enabled': False, 'images': [{'id': 'yZMJwzqfo-1KodiPMX_oqs-WZlqWdJqQO_vA61_E2Yg', 'resolutions': [{'height': 40, 'url': 'https://external-preview.redd.it/yZMJwzqfo-1KodiPMX_oqs-WZlqWdJqQO_vA61_E2Yg.png?width=108&crop=smart&auto=webp&s=77ff4af9442a5b206d01bdcbad217d038f8856f5', 'width': 108}, {'height': 80, 'url': 'ht... | |
Is GLM 4.5 / 4.6 really sensitive to quantisation? Or is vLLM stupifying the models? | 6 | I am trying to run GLM 4.6 or GLM 4.5 Air locally with vLLM.
I've tried:
- zai-org/GLM-4.5-Air-FP8
- vkerkez/GLM-4.6-REAP-266B-A32B-awq-sym
- bullpoint/GLM-4.6-AWQ
but the answers just aren't as smart or deep as the full-fat deepinfra zai-org/GLM-4.6. I'm using OpenWebUI with the same parameters and system prompt.
F... | 2025-10-25T13:00:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ofqyhc/is_glm_45_46_really_sensitive_to_quantisation_or/ | _supert_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofqyhc | false | null | t3_1ofqyhc | /r/LocalLLaMA/comments/1ofqyhc/is_glm_45_46_really_sensitive_to_quantisation_or/ | false | false | self | 6 | null |
What are actual verifiable ways we can detect AI? | 0 | Social media is now filled with AI content that is fooling people left and right. AI generated short form content goes viral frequently, with lots of people assuming it to be real, along with majority of long write ups being chatGPT’d.
Most of us already saw this coming years ago, I’m sure this isn’t a surprise to mo... | 2025-10-25T12:33:57 | https://www.reddit.com/r/LocalLLaMA/comments/1ofqe7x/what_are_actual_verifiable_ways_we_can_detect_ai/ | ra4h | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofqe7x | false | null | t3_1ofqe7x | /r/LocalLLaMA/comments/1ofqe7x/what_are_actual_verifiable_ways_we_can_detect_ai/ | false | false | self | 0 | null |
How to make PocketPal inference faster on android? | 1 | I have an OnePlus 12 24GB running on LineageOS 22.2 with 6.44GB zram. I ran the PocketPal bench at the default pp=512,tg=128,pl=1 and rep=3.
|pp|tg|time|PeakMem|Model|
|:-|:-|:-|:-|:-|
|14.18t/s|6.79t/s|2m50s|81.1%|Qwen3-30B-A3B-Instruct-2507-UD\_Q5\_K\_XL|
|17.42t/s|4.00t/s|3m4s|62.0%|gemma-3-12b-it-qat-Q4\_0|
The Q... | 2025-10-25T12:26:01 | https://www.reddit.com/r/LocalLLaMA/comments/1ofq8jq/how_to_make_pocketpal_inference_faster_on_android/ | Ok_Warning2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofq8jq | false | null | t3_1ofq8jq | /r/LocalLLaMA/comments/1ofq8jq/how_to_make_pocketpal_inference_faster_on_android/ | false | false | self | 1 | null |
which model has the best world knowledge? Open weights and proprietary. | 48 | So I am looking for models with great general world knowledge and application of this. Open weights are preferred (I have access to H200s, so anything below 1.8TB VRAM) but API can be used if necessary. I am finding world knowledge really sucks for open models, even Kimi which can just get things wrong.
For example, k... | 2025-10-25T12:23:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ofq6m7/which_model_has_the_best_world_knowledge_open/ | z_3454_pfk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofq6m7 | false | null | t3_1ofq6m7 | /r/LocalLLaMA/comments/1ofq6m7/which_model_has_the_best_world_knowledge_open/ | false | false | self | 48 | null |
[Open Source] We deployed numerous agents in production and ended up building our own GenAI framework | 0 | Here’s what the journey taught us 🧠
After building and deploying GenAI solutions in production, we got tired of fighting with bloated frameworks, debugging black boxes, and dealing with vendor lock-in.
So we built Flo AI - a Python framework that actually respects your time.
**The Problem We Solved**
Most LLM fram... | 2025-10-25T12:17:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ofq2g3/open_source_we_deployed_numerous_agents_in/ | vizsatiz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofq2g3 | false | null | t3_1ofq2g3 | /r/LocalLLaMA/comments/1ofq2g3/open_source_we_deployed_numerous_agents_in/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'RpGihcxDhJl2ytc4KNpuqMF0cEo8b-nmbPnpsJ3Ucao', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/RpGihcxDhJl2ytc4KNpuqMF0cEo8b-nmbPnpsJ3Ucao.png?width=108&crop=smart&auto=webp&s=d711600f726fdab7395101343a23b589af76d3e3', 'width': 108}, {'height': 108, 'url': 'h... |
re:search | 0 | free beta
*llm agnostic re:search*
[https://github.com/researchnexusgit/research](https://github.com/researchnexusgit/research)
endpoint: *default = local Ollama endpoint*
model: *default = qwen3:4b*
/endpoint → endpoint entry screen
/model → model name entry screen
/release → export current interaction
/se... | 2025-10-25T12:10:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ofpxu2/research/ | Ok_Priority_4635 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofpxu2 | false | null | t3_1ofpxu2 | /r/LocalLLaMA/comments/1ofpxu2/research/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'PNuRpRFh9N2LBMv-7phdHBGCkMLi_MwX57mH8mV5PT8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/PNuRpRFh9N2LBMv-7phdHBGCkMLi_MwX57mH8mV5PT8.png?width=108&crop=smart&auto=webp&s=e6cbf7a85676b81270beb474adb632562b8404c3', 'width': 108}, {'height': 108, 'url': 'h... |
Any local model that can rival gemini 2.5 flash? | 4 | I've been using gemini-cli a lot these days. I'm no programmer nor do i like to program. I only do it because i want to save time by automating some things with scripts. And using gemini-cli with the flash model has been enough for my meager needs.
But i wonder if there's any local models that can compete with it? | 2025-10-25T12:00:58 | https://www.reddit.com/r/LocalLLaMA/comments/1ofprkv/any_local_model_that_can_rival_gemini_25_flash/ | AldebaranReborn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofprkv | false | null | t3_1ofprkv | /r/LocalLLaMA/comments/1ofprkv/any_local_model_that_can_rival_gemini_25_flash/ | false | false | self | 4 | null |
I have ryzen 7 5800x with 32 gb ram and rtx 3090 24gb if anyone wants to rent just dm me | 0 | If anyone need just comment below with price per hour | 2025-10-25T11:52:10 | https://www.reddit.com/r/LocalLLaMA/comments/1ofpltw/i_have_ryzen_7_5800x_with_32_gb_ram_and_rtx_3090/ | Zainnn678 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofpltw | false | null | t3_1ofpltw | /r/LocalLLaMA/comments/1ofpltw/i_have_ryzen_7_5800x_with_32_gb_ram_and_rtx_3090/ | false | false | self | 0 | null |
Unable to setup Cline in VScode with LM studio. Cant set context window. | 1 | Would anyone with some Cline setup experience help me 🙂
I just installed and setting up cline extension in VScode with my local llm on LM studio. But after installing I started the below steps.
1. When I clicked LM studio provider it did not show list of models, So I did manually typed the model ID (seen on left fro... | 2025-10-25T11:37:37 | Pack_Commercial | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofpcje | false | null | t3_1ofpcje | /r/LocalLLaMA/comments/1ofpcje/unable_to_setup_cline_in_vscode_with_lm_studio/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'IyJczp2PPgqn5r95JsmTmNW5_uZjtG8l1GiclTdvUls', 'resolutions': [{'height': 56, 'url': 'https://preview.redd.it/sgtruy7iv8xf1.png?width=108&crop=smart&auto=webp&s=fe50fa530ef767a0d7cbad4807d0ed5c2fe2d50a', 'width': 108}, {'height': 113, 'url': 'https://preview.redd.it/sgtruy7iv8xf1.png... | ||
Tired of tweaking your resume for every job description? I made a project that will do that and much more | 2 | 2025-10-25T11:17:35 | https://v.redd.it/5eamalkvr8xf1 | Sick__sock | /r/LocalLLaMA/comments/1ofp0ck/tired_of_tweaking_your_resume_for_every_job/ | 1970-01-01T00:00:00 | 0 | {} | 1ofp0ck | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/5eamalkvr8xf1/DASHPlaylist.mpd?a=1764112666%2CZjk2MzlmOTk2ZGVlN2Q2MTFjODI0ZGM0YTk1NDI3ZDMzOWI4MzYyMGU0OGVmMzdjZjJlMThmZDU0MTM2Y2U1Mg%3D%3D&v=1&f=sd', 'duration': 121, 'fallback_url': 'https://v.redd.it/5eamalkvr8xf1/DASH_1080.mp4?source=fallback', '... | t3_1ofp0ck | /r/LocalLLaMA/comments/1ofp0ck/tired_of_tweaking_your_resume_for_every_job/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'bTZ4MnZlbHZyOHhmMYjCPdWOhWOC0mMCMfhtU8UInvZvl5_PVa6FYnX-eAIM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bTZ4MnZlbHZyOHhmMYjCPdWOhWOC0mMCMfhtU8UInvZvl5_PVa6FYnX-eAIM.png?width=108&crop=smart&format=pjpg&auto=webp&s=00e9d6ca5bde7a718deb946a3bfd81d003978... | ||
free perplexity pro | 1 | [removed] | 2025-10-25T11:07:09 | https://www.reddit.com/r/LocalLLaMA/comments/1ofou6t/free_perplexity_pro/ | Educational_Past_908 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofou6t | false | null | t3_1ofou6t | /r/LocalLLaMA/comments/1ofou6t/free_perplexity_pro/ | false | false | self | 1 | null |
Enable Gemma 2 2b thinking in LM studio | 0 | Hi All 28cm and E cups,
I was trying to break Gemma 2. I happened to enable Gemma 2 think, the response was blank. I am not sure if it's because I use Qwen3-4b to think first then switch to Gemmma. I think the system prompts play little part.
Any one knows how to recreate such without fail?
I use LM studio 0.3.31... | 2025-10-25T10:54:01 | https://www.reddit.com/gallery/1ofom66 | ywis797 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ofom66 | false | null | t3_1ofom66 | /r/LocalLLaMA/comments/1ofom66/enable_gemma_2_2b_thinking_in_lm_studio/ | false | false | 0 | null | |
Anyone used Reducto for parsing? How good is their embedding-aware chunking? | 2 | Curious if anyone here has used Reducto for document parsing or retrieval pipelines.
They seem to focus on generating LLM-ready chunks using a mix of vision-language models and something they call “embedding-optimized” or intelligent chunking. The idea is that it preserves document layout and meaning (tables, figures,... | 2025-10-25T10:30:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ofo8zs/anyone_used_reducto_for_parsing_how_good_is_their/ | BriefCardiologist656 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofo8zs | false | null | t3_1ofo8zs | /r/LocalLLaMA/comments/1ofo8zs/anyone_used_reducto_for_parsing_how_good_is_their/ | false | false | self | 2 | null |
Anyone used Reducto for parsing? How good is their embedding-aware chunking? | 1 | Curious if anyone here has used Reducto for document parsing or retrieval pipelines.
They seem to focus on generating LLM-ready chunks using a mix of vision-language models and something they call “embedding-optimized” or intelligent chunking. The idea is that it preserves document layout and meaning ... | 2025-10-25T10:27:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ofo7a3/anyone_used_reducto_for_parsing_how_good_is_their/ | BriefCardiologist656 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofo7a3 | false | null | t3_1ofo7a3 | /r/LocalLLaMA/comments/1ofo7a3/anyone_used_reducto_for_parsing_how_good_is_their/ | false | false | self | 1 | null |
Performance difference while using Ollama Model vs HF Model | 0 | **TL;DR:**
Downloaded the exact same model (gpt-oss 20b) from **Ollama Hub** and **Hugging Face**. Both run using **Ollama to do inference**, but the Ollama-Hub copy drives my GPU at \~**100%** and \~**150 t/s**, while the HF copy only uses \~**50%** GPU and \~**80 t/s**. Both are the same quant (I assumed by mode... | 2025-10-25T10:10:09 | https://www.reddit.com/r/LocalLLaMA/comments/1ofnx9i/performance_difference_while_using_ollama_model/ | Warriorsito | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofnx9i | false | null | t3_1ofnx9i | /r/LocalLLaMA/comments/1ofnx9i/performance_difference_while_using_ollama_model/ | false | false | self | 0 | null |
Claude Skills but running locally in Apple container | 0 | 2025-10-25T09:50:39 | https://instavm.io/blog/building-my-offline-workspace-part-2-skills | badhiyahai | instavm.io | 1970-01-01T00:00:00 | 0 | {} | 1ofnm3p | false | null | t3_1ofnm3p | /r/LocalLLaMA/comments/1ofnm3p/claude_skills_but_running_locally_in_apple/ | false | false | default | 0 | null | |
meituan-longcat/LongCat-Video · Hugging Face | 125 | A foundational video generation model with 13.6B parameters, delivering strong performance across Text-to-Video, Image-to-Video, and Video-Continuation generation tasks. | 2025-10-25T09:11:57 | https://huggingface.co/meituan-longcat/LongCat-Video | Dark_Fire_12 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ofn0nb | false | null | t3_1ofn0nb | /r/LocalLLaMA/comments/1ofn0nb/meituanlongcatlongcatvideo_hugging_face/ | false | false | 125 | {'enabled': False, 'images': [{'id': 'Yt-ii7zJ14OIVDQLAiu4mswoqHj6Da2dRjpAXgOm1a4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Yt-ii7zJ14OIVDQLAiu4mswoqHj6Da2dRjpAXgOm1a4.png?width=108&crop=smart&auto=webp&s=bb6bf9eddf2e79d77d651a73e3418c64d10f4339', 'width': 108}, {'height': 116, 'url': 'h... | |
Looking for an arXiv endorser (cs.CV) — "Bullseye": A Modular Multimodal Document Intelligence System. | 1 | [removed] | 2025-10-25T09:11:40 | https://v.redd.it/tqdixzdg58xf1 | BlacksmithEvening650 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofn0hc | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/tqdixzdg58xf1/DASHPlaylist.mpd?a=1763975725%2COGIyOTBhOWRmYzRlYjBjNzA4OTRjOGQ4MDRjMDQwZDc1ZWJhM2Q3ODFhOTYwNDE3MWYxZTIwNjE0YzhiN2VhMw%3D%3D&v=1&f=sd', 'duration': 30, 'fallback_url': 'https://v.redd.it/tqdixzdg58xf1/DASH_1080.mp4?source=fallback', 'h... | t3_1ofn0hc | /r/LocalLLaMA/comments/1ofn0hc/looking_for_an_arxiv_endorser_cscv_bullseye_a/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'eHdod3NoOGc1OHhmMVvaAuAAQiZjK5TP4zgMnPCELVb7YYKxllSqPdFpUi_Z', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eHdod3NoOGc1OHhmMVvaAuAAQiZjK5TP4zgMnPCELVb7YYKxllSqPdFpUi_Z.png?width=108&crop=smart&format=pjpg&auto=webp&s=7ff0cc4c89821f41cb8830614ef0facd6a4e2... | |
Advice on new rig | 0 | Would a 5060 ti 16GB and 96 GB RAM be enough to run smoothly fan favorites such as:
Qwen 30B-A3B,
GLM air 4.5
Example token/s on your rig would be much appreciated! | 2025-10-25T07:52:09 | https://www.reddit.com/r/LocalLLaMA/comments/1oflsb6/advice_on_new_rig/ | AI-On-A-Dime | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oflsb6 | false | null | t3_1oflsb6 | /r/LocalLLaMA/comments/1oflsb6/advice_on_new_rig/ | false | false | self | 0 | null |
Pocket LLM: Chat offline on device all private | AI | 0 | Pocket LLM lets you chat with powerful AI models like Llama, Gemma, deepseek, Apple Intelligence and Qwen directly on your device. No internet, no account, no data sharing. Just fast, private AI powered by Apple MLX.
• Works offline anywhere
• No login, no data collection
• Runs on Apple Silicon for speed
• Support... | 2025-10-25T06:44:16 | https://apps.apple.com/in/app/local-ai-chat-pocket-llm/id6752952699 | Late-Scarcity-5476 | apps.apple.com | 1970-01-01T00:00:00 | 0 | {} | 1ofkqf3 | false | null | t3_1ofkqf3 | /r/LocalLLaMA/comments/1ofkqf3/pocket_llm_chat_offline_on_device_all_private_ai/ | false | false | 0 | {'enabled': False, 'images': [{'id': '8-ESSb9vlceCKX50m0RGxZUO6a-OxmRJ9r6lXdojxC8', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/8-ESSb9vlceCKX50m0RGxZUO6a-OxmRJ9r6lXdojxC8.png?width=108&crop=smart&auto=webp&s=4d832d6ead41b4662648c21ba9ca312162c1515d', 'width': 108}, {'height': 113, 'url': 'h... | |
How do you handle the context window overflow for long-running tasks? | 0 | If you have an AI Agent (or a group of agents) executing a long-running task, how do you manage the context window overflow exceptions?
I want to build a system that will run independently to execute a given task. I consider using the AI SDK and TypeScript for implementation. How can I make my solution resistant to th... | 2025-10-25T06:42:57 | ThingRexCom | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofkpnq | false | null | t3_1ofkpnq | /r/LocalLLaMA/comments/1ofkpnq/how_do_you_handle_the_context_window_overflow_for/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'LIGRKOIhRkWLQZ_DSgfa9YHpooCtcwC2HkiwGeE_tEQ', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/2dgkzr7ue7xf1.png?width=108&crop=smart&auto=webp&s=ef404894db37042d7410a186d6afb229642709b0', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/2dgkzr7ue7xf1.pn... | ||
Why is this happening? | 0 | Ring flash is by Grok 4? | 2025-10-25T03:55:01 | DependentDazzling703 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofhvhw | false | null | t3_1ofhvhw | /r/LocalLLaMA/comments/1ofhvhw/why_is_this_happening/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'qagArYgJWTNIR0PJrePxo5cvqciO7GGs3CYYmPH9WZk', 'resolutions': [{'height': 211, 'url': 'https://preview.redd.it/ilar0nhsk6xf1.jpeg?width=108&crop=smart&auto=webp&s=131efd66cc8e20798b53e82d299a11f77ec0974b', 'width': 108}, {'height': 423, 'url': 'https://preview.redd.it/ilar0nhsk6xf1.j... | ||
Should I keep the 3080ti? | 1 | [removed] | 2025-10-25T03:37:49 | https://www.reddit.com/gallery/1ofhkh3 | one_tall_lamp | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ofhkh3 | false | null | t3_1ofhkh3 | /r/LocalLLaMA/comments/1ofhkh3/should_i_keep_the_3080ti/ | false | false | 1 | null | |
Woke up whole night and still couldn't resolve this one issue | 8 | Google Collab link :- https://colab.research.google.com/drive/1gutbsKAiS46PsSoqPG51fHt8VNRrUNB3?usp=sharing#scrollTo=xIPudkKcQeyD
I was fine tuning gpt oss 20B using unsloth on Google Colab and this error kept coming...
I feel i changed my dataset structure many times and still wasnot about to proceed.....
Als... | 2025-10-25T03:10:46 | thenew_Alex_Bawden | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofh2ia | false | null | t3_1ofh2ia | /r/LocalLLaMA/comments/1ofh2ia/woke_up_whole_night_and_still_couldnt_resolve/ | false | false | 8 | {'enabled': True, 'images': [{'id': 'e9io1A8cHff_3X0MAp2QwYUDozht6vhaFWtKwI1QQms', 'resolutions': [{'height': 84, 'url': 'https://preview.redd.it/1v6zgu92d6xf1.jpeg?width=108&crop=smart&auto=webp&s=f0938a9e3910a16dea6dca13d2ec36f649d700c6', 'width': 108}, {'height': 169, 'url': 'https://preview.redd.it/1v6zgu92d6xf1.jp... | ||
Kimi k2 image generation | 44 | I am so confused because I can’t find any information on Kimi k2 image generation abilities. When I asked Kimi to generate an image it said it couldn’t. But I’m having it code a tarot reading project and it’s generating all these images…when I asked about it Kimi still said it couldn’t generate images. What’s going on ... | 2025-10-25T02:38:13 | Used-Nectarine5541 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ofggny | false | null | t3_1ofggny | /r/LocalLLaMA/comments/1ofggny/kimi_k2_image_generation/ | false | false | 44 | {'enabled': True, 'images': [{'id': 'GqoyRhe7zCeeNbDrevatVjcZEp2hpOexVDMBcFCSraI', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/vimkvz5976xf1.jpeg?width=108&crop=smart&auto=webp&s=87ab8e69569899c9365796ef886f85b15dc77cef', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/vimkvz5976xf1.jp... | ||
What's the current best local model for function calling with low latency? | 1 | Building a local app where a user interacts with a model, where the model asks 3 questions. When the user answers each question, the 3 possible pathways in this experience are: repeat question, exit conversation, go to next question.
That's 3 function/tool calls. Because it's a conversation I need low model response t... | 2025-10-25T02:23:53 | https://www.reddit.com/r/LocalLLaMA/comments/1ofg6w9/whats_the_current_best_local_model_for_function/ | NoConclusion5355 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofg6w9 | false | null | t3_1ofg6w9 | /r/LocalLLaMA/comments/1ofg6w9/whats_the_current_best_local_model_for_function/ | false | false | self | 1 | null |
Highly-customizable Github AI Reviewer Workflow using Open Router | 0 | Hi everyone,
maybe this is useful for you:
* Creates highly-customizable AI Reviews as PR comments
* \~225 lines of code
* Installation: Just 2 files copied to your repo and a open router API Key in your secrets.
* Costs: $0.01 - $0.05 per review (depends highly on model)
Example output: [LearningCircuit/local-dee... | 2025-10-25T01:49:31 | https://www.reddit.com/r/LocalLLaMA/comments/1offir8/highlycustomizable_github_ai_reviewer_workflow/ | ComplexIt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1offir8 | false | null | t3_1offir8 | /r/LocalLLaMA/comments/1offir8/highlycustomizable_github_ai_reviewer_workflow/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'dIv7MxvXQHmt6pMIOKYVqMTr8AO_hTTwGa8OA4QTSOg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dIv7MxvXQHmt6pMIOKYVqMTr8AO_hTTwGa8OA4QTSOg.png?width=108&crop=smart&auto=webp&s=1760f068dc7d57fe18efef6731a77ce279cf8bf5', 'width': 108}, {'height': 108, 'url': 'h... |
If you could have one LLM distilled to a smaller size, which would model would you pick and what size(s) would you pick? | 13 | This is a tough choice for me, as I’ve wanted to have a true distillation of Deepseek for the longest time, but I think Kimi-K2 has changed my mind.
I would love to have Kimi-K2 distilled to a 70b dense model… a more likely size someone might attempt would be 106 billion total parameters and 12 billion active paramet... | 2025-10-25T01:23:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ofezsz/if_you_could_have_one_llm_distilled_to_a_smaller/ | silenceimpaired | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofezsz | false | null | t3_1ofezsz | /r/LocalLLaMA/comments/1ofezsz/if_you_could_have_one_llm_distilled_to_a_smaller/ | false | false | self | 13 | null |
Teaching Gemini AI A New Way to Divide Cake Fairly | 2 | simple stupid solution, solved this a few years ago thought I would see if any ai had a solution, apparently not, a few lesson prompts and Gemini understands, this is geminis article of the simple stupid solution.
Teaching an AI (and Everyone Else) a New Way to Divide Cake Fairly
Introduction: The Age-Old Cake Proble... | 2025-10-25T00:52:34 | https://www.reddit.com/r/LocalLLaMA/comments/1ofedvq/teaching_gemini_ai_a_new_way_to_divide_cake_fairly/ | zero_moo-s | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ofedvq | false | null | t3_1ofedvq | /r/LocalLLaMA/comments/1ofedvq/teaching_gemini_ai_a_new_way_to_divide_cake_fairly/ | false | false | self | 2 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.