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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
A question about LLMs | 7 | Is anyone working on an AI that is capable of learning? And if so, how come I’ve not heard anything yet? | 2025-10-10T03:39:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o2qh9s/a_question_about_llms/ | Savantskie1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2qh9s | false | null | t3_1o2qh9s | /r/LocalLLaMA/comments/1o2qh9s/a_question_about_llms/ | false | false | self | 7 | null |
I made a multimodal local RAG system with LM Studio | 165 | I couldn’t find a RAG system that worked with Google Docs and could have more than 10,000 synced files, so I made one myself. This thing is a beast, it works with Gemma 3 4B decently well but I think the results would be way better with a larger model and a larger dataset. I’ll share the full code later on but I’m tire... | 2025-10-10T03:22:45 | https://v.redd.it/09paso3id7uf1 | donotfire | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o2q5n6 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/09paso3id7uf1/DASHPlaylist.mpd?a=1762658582%2CMWVmODU4NDhkZGM3ODEzNTdlMTJmMDdlM2YzZTQ0N2E5N2RjYzUzNTEyN2U0ZWE0MDA5YzVkMzQzMzdjMmNhYQ%3D%3D&v=1&f=sd', 'duration': 73, 'fallback_url': 'https://v.redd.it/09paso3id7uf1/DASH_1080.mp4?source=fallback', 'h... | t3_1o2q5n6 | /r/LocalLLaMA/comments/1o2q5n6/i_made_a_multimodal_local_rag_system_with_lm/ | false | false | 165 | {'enabled': False, 'images': [{'id': 'cnBqa3NkeWhkN3VmMQb9PvMVdq9S5Iwim0AbH7Nkf50d3AGCnXrbNmpKxt0b', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/cnBqa3NkeWhkN3VmMQb9PvMVdq9S5Iwim0AbH7Nkf50d3AGCnXrbNmpKxt0b.png?width=108&crop=smart&format=pjpg&auto=webp&s=242d8e3c987e4630b5e6d0aac3f1340d952c7... | |
Funny/Humor LLMs | 10 | How do LLMs handle humor? From what I understand, they basically learn by guessing what word comes next based on tons of text they’ve seen. Over time, they get better at it by adjusting their internal weights.
So when you ask them to tell a joke, they can do it because they’ve come across lots of jokes during training... | 2025-10-10T03:03:18 | https://www.reddit.com/r/LocalLLaMA/comments/1o2prgn/funnyhumor_llms/ | ionlycreate42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2prgn | false | null | t3_1o2prgn | /r/LocalLLaMA/comments/1o2prgn/funnyhumor_llms/ | false | false | self | 10 | null |
I built CodeIngest (like gitingest for local files) | 2 | 2025-10-10T02:53:30 | https://github.com/shubhdotai/codeingest | mshubham | github.com | 1970-01-01T00:00:00 | 0 | {} | 1o2pk68 | false | null | t3_1o2pk68 | /r/LocalLLaMA/comments/1o2pk68/i_built_codeingest_like_gitingest_for_local_files/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': 'ANRWLkVSfUIOrvAx8hZmFzCVieCtoTFPNVlJEScsd84', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ANRWLkVSfUIOrvAx8hZmFzCVieCtoTFPNVlJEScsd84.png?width=108&crop=smart&auto=webp&s=56596f7a1a3b5ea2020a0631937e38187dd4eb4d', 'width': 108}, {'height': 108, 'url': 'h... | |
Jailbreaking Moonshot AI on Ok Computer | 4 | Moonshot AI has released a feature called OK Computer, similar to Manus. I discovered some platform limitations and, after extensive testing, found several methods to bypass these restrictions. Here's what I'd like to share:
First, let me list the system boundary data I obtained through extreme testing:
* Single ... | 2025-10-10T02:27:39 | https://www.reddit.com/r/LocalLLaMA/comments/1o2p1is/jailbreaking_moonshot_ai_on_ok_computer/ | Dr_Karminski | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2p1is | false | null | t3_1o2p1is | /r/LocalLLaMA/comments/1o2p1is/jailbreaking_moonshot_ai_on_ok_computer/ | false | false | 4 | null | |
Learning Unity + C# game development — which local LLM model and settings should I use in LM Studio (CUDA)? | 5 | Hey everyone! 👋
I'm starting to learn Unity and C# from scratch, but instead of following tutorials,
I want to learn interactively — by using a local LLM as a coding and design assistant.
My goal is to use the model to:
\- Explain C# code step by step
\- Help me debug Unity scripts and errors
\- Su... | 2025-10-10T02:21:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2oxbj/learning_unity_c_game_development_which_local_llm/ | CommercialStranger82 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2oxbj | false | null | t3_1o2oxbj | /r/LocalLLaMA/comments/1o2oxbj/learning_unity_c_game_development_which_local_llm/ | false | false | self | 5 | null |
Most accurate claude benchmark | 0 | To scale sonnet 4.1 front-end performance
https://preview.redd.it/z16pnxd527uf1.png?width=2482&format=png&auto=webp&s=f09d6a55d595322974c5be55883314e2448146c5 | 2025-10-10T02:21:37 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ox51/most_accurate_claude_benchmark/ | Helpful_Jacket8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ox51 | false | null | t3_1o2ox51 | /r/LocalLLaMA/comments/1o2ox51/most_accurate_claude_benchmark/ | false | false | 0 | null | |
I built an AI tool using llama 3.3 70b | 0 | So I'm Arush, a 14 y/o from India. I recently built NexNotes Al. It has all the features needed for studying and research. Just upload any type of file and get:
question papers
Mindmaps and diagrams (custom)
Quizzes with customized difficulty
Vocab extraction
Humanized text
handwritten text
It can solve your que... | 2025-10-10T01:35:12 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ny0w/i_built_an_ai_tool_using_llama_33_70b/ | BitterTwo5331 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ny0w | false | null | t3_1o2ny0w | /r/LocalLLaMA/comments/1o2ny0w/i_built_an_ai_tool_using_llama_33_70b/ | false | false | self | 0 | null |
How do you guys structure your multi-turn datasets for fine-tuning or layer tuning? | 4 | I'm currently filling mine with coding, simple Q&A, and chess-related data—all around 500+ tokens per turn.
Since you all are the experts, I have a few questions:
1. How do you **clean/refine your datasets**?
2. What are your **criteria for judging** whether a piece of data is "good" enough to include?
3. Can anyone ... | 2025-10-10T00:16:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2mbar/how_do_you_guys_structure_your_multiturn_datasets/ | Patience2277 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2mbar | false | null | t3_1o2mbar | /r/LocalLLaMA/comments/1o2mbar/how_do_you_guys_structure_your_multiturn_datasets/ | false | false | self | 4 | null |
Is there anything faster or smaller with equal quality to Qwen 30B A3B? | 92 | *Specs: RTX 3060 12GB - 4+8+16GB RAM - R5 4600G*
I've tried mistral small, instruct and nemo in 7b, 14b and 24b sizes but unfortunately 7b just can't handle much nothing except for those 200 tokens [c.ai](http://c.ai) chatbots and they're thrice slower than Qwen.
Do you know anything smaller than **Qwen A3B 30B** wit... | 2025-10-09T23:49:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o2lq5n/is_there_anything_faster_or_smaller_with_equal/ | WEREWOLF_BX13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2lq5n | false | null | t3_1o2lq5n | /r/LocalLLaMA/comments/1o2lq5n/is_there_anything_faster_or_smaller_with_equal/ | false | false | self | 92 | {'enabled': False, 'images': [{'id': 'VByatpjC4OWt09UuhmWM1sP5CwhM1Ds9alijJu4qPqU', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/VByatpjC4OWt09UuhmWM1sP5CwhM1Ds9alijJu4qPqU.jpeg?width=108&crop=smart&auto=webp&s=a2f095072d7ec8cf53cf552cba7b9e6e836a5c53', 'width': 108}, {'height': 113, 'url': '... |
Can Multi-GPU? What should I buy 64GB of RAM or an RTX 5060 Ti? I’m currently using an RTX 5070 Ti, and my 24B model consumes about 14GB of VRAM and 20GB of RAM. | 2 | Can LM Studio and text-generation-webui use two GPUs at once, even if they are different models?
I don’t have much knowledge about this I’m still a beginner.
My Spec: CPU Ryzen 9700X GPU RTX 5070 Ti RAM 32GB
Which I should buy RAM or RTX 5060 Ti 16GB? | 2025-10-09T23:16:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o2l0dv/can_multigpu_what_should_i_buy_64gb_of_ram_or_an/ | HQBase | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2l0dv | false | null | t3_1o2l0dv | /r/LocalLLaMA/comments/1o2l0dv/can_multigpu_what_should_i_buy_64gb_of_ram_or_an/ | false | false | self | 2 | null |
Running DeepSeek-R1 Locally with Ollama + LangChain: Transparent Reasoning, Real Tradeoffs | 2 | been experimenting with **DeepSeek-R1** on Ollama, running locally with LangChain for reasoning-heavy tasks (contract analysis + PDF Q&A). the open weights make it practical for privacy-bound deployments, and the reasoning transparency is surprisingly close to o1, though latency jumps once you chain multi-turn logic.
... | 2025-10-09T22:52:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o2khf4/running_deepseekr1_locally_with_ollama_langchain/ | AromaticLab8182 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2khf4 | false | null | t3_1o2khf4 | /r/LocalLLaMA/comments/1o2khf4/running_deepseekr1_locally_with_ollama_langchain/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'bAw-J0PM677XfwDlARd5X-3m1HyxZwwoNSri8JdcXN8', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/bAw-J0PM677XfwDlARd5X-3m1HyxZwwoNSri8JdcXN8.png?width=108&crop=smart&auto=webp&s=e0286370eb5ce8a2ce807e83fc4f59d2e91718e6', 'width': 108}, {'height': 144, 'url': 'h... |
Is there any way I can finetune the GrayWolf models faster? It currently takes 10,000 years to create a LoRA on my current GPU rig and I want to speed up the process. | 86 | 2025-10-09T22:31:49 | Arkhos-Winter | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o2k0cw | false | null | t3_1o2k0cw | /r/LocalLLaMA/comments/1o2k0cw/is_there_any_way_i_can_finetune_the_graywolf/ | false | false | default | 86 | {'enabled': True, 'images': [{'id': '9aievo3cx5uf1', 'resolutions': [{'height': 86, 'url': 'https://preview.redd.it/9aievo3cx5uf1.gif?width=108&crop=smart&format=png8&s=c677d284c92dbfabf5a9187b8cae05b4e8e1ec76', 'width': 108}, {'height': 172, 'url': 'https://preview.redd.it/9aievo3cx5uf1.gif?width=216&crop=smart&format... | ||
What's a reliable and small model for news article summaries? | 2 | wondering what everyone's go to reliable model for clean output is for text summarization these days. I assume small models have enough "intelligence" to summarize effectively at this point but struggling to get good outputs from ones that fit on my AMD 7900 XTX 24GB and are performant since I have about 2 million smal... | 2025-10-09T22:29:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2jymz/whats_a_reliable_and_small_model_for_news_article/ | dlarsen5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2jymz | false | null | t3_1o2jymz | /r/LocalLLaMA/comments/1o2jymz/whats_a_reliable_and_small_model_for_news_article/ | false | false | self | 2 | null |
Any tools that can track and observe multi-turn conversations? | 1 | I have been running into this problem while testing AI agents once conversations go beyond a few turns, it’s really hard to **trace what’s happening across the session**.
Most observability tools only show request–response pairs, but not the **conversation flow**, message dependencies, or how earlier context affects... | 2025-10-09T22:16:07 | https://www.reddit.com/r/LocalLLaMA/comments/1o2jn29/any_tools_that_can_track_and_observe_multiturn/ | MongooseOriginal6450 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2jn29 | false | null | t3_1o2jn29 | /r/LocalLLaMA/comments/1o2jn29/any_tools_that_can_track_and_observe_multiturn/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'uhRpB7D-vTXyU3kWrM4Uv0wsEl8ANQiO9SXhRH44nmE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/uhRpB7D-vTXyU3kWrM4Uv0wsEl8ANQiO9SXhRH44nmE.png?width=108&crop=smart&auto=webp&s=2ac91097383d12b50cccd11a156d801425048149', 'width': 108}, {'height': 113, 'url': 'h... |
When LLMs use Chain-of-Thought as a tool to achieve hidden goals | 12 | When reasoning models hide their true motivations behind fabricated policy refusals.[](https://medium.com/@gabriella_71298/when-llms-use-chain-of-thought-as-a-tool-to-achieve-hidden-goals-d33a0991cd2b) | 2025-10-09T22:02:28 | https://medium.com/@gabriella_71298/when-llms-use-chain-of-thought-as-a-tool-to-achieve-hidden-goals-d33a0991cd2b | ella0333 | medium.com | 1970-01-01T00:00:00 | 0 | {} | 1o2jbby | false | null | t3_1o2jbby | /r/LocalLLaMA/comments/1o2jbby/when_llms_use_chainofthought_as_a_tool_to_achieve/ | false | false | default | 12 | {'enabled': False, 'images': [{'id': 'xkf4DFGJJVQAcOm-gRv1XUfT76S6eJbOZ5vCHrldqoM', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/xkf4DFGJJVQAcOm-gRv1XUfT76S6eJbOZ5vCHrldqoM.jpeg?width=108&crop=smart&auto=webp&s=7e71148290a943095daca4dc044d6b8546eb49b8', 'width': 108}, {'height': 113, 'url': '... |
finished the prototype, guys! It works! | 6 | It's not a custom model yet, just a fine-tuned one for testing.
I only touched the top six layers (wait, maybe it was five? anyway).
What I found out is that persona fine-tuning is surprisingly easy, even with a super low-quality dataset (by my standards).
The dataset size was tiny too: about 200 Q&A pairs, only 88K... | 2025-10-09T21:59:36 | https://www.reddit.com/r/LocalLLaMA/comments/1o2j8ma/finished_the_prototype_guys_it_works/ | Patience2277 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2j8ma | false | null | t3_1o2j8ma | /r/LocalLLaMA/comments/1o2j8ma/finished_the_prototype_guys_it_works/ | false | false | 6 | null | |
Multiple 3090 setup | 2 | I’m looking to setup a home server(s) with multiple 3090 cards. I have no clue where to start.
What’s a well tested setup that works for the below use case?
- For running whisper STT
- Each gpu belongs to a distinct worker
- No need for multi gpu access
Am I better off just building single gpu servers or is there ... | 2025-10-09T21:56:31 | https://www.reddit.com/r/LocalLLaMA/comments/1o2j5yh/multiple_3090_setup/ | praveendath92 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2j5yh | false | null | t3_1o2j5yh | /r/LocalLLaMA/comments/1o2j5yh/multiple_3090_setup/ | false | false | self | 2 | null |
How would I use an LLM approach to cluster 30,000 different store names? | 0 | Hi how are you?
I have a list of 30,000 store names across the USA that need to be grouped together. For example Taco Bell New York, Taco Bell New Jersey, Taco Bell Inc. would fall under one group. I've tried using a basic levenshtein distance or cosine similarity approach but the results weren't great.
I was wonderi... | 2025-10-09T21:42:41 | https://www.reddit.com/r/LocalLLaMA/comments/1o2itr0/how_would_i_use_an_llm_approach_to_cluster_30000/ | Guilty-Armadillo6543 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2itr0 | false | null | t3_1o2itr0 | /r/LocalLLaMA/comments/1o2itr0/how_would_i_use_an_llm_approach_to_cluster_30000/ | false | false | self | 0 | null |
Anyone know of a static FP8 version of the latest Magistral? | 1 | Hello, newb lurker here — hoping a big brain on here could please point me in the right direction. Thanks!
I’m currently running cpatton Magistral small AWQ 8bit on vllm.
I have x2 5060tis for 32gb vram total.
I’d like to try this same Magistral 2509 model out with FP8 but it looks like I need far more vram total i... | 2025-10-09T20:38:26 | https://www.reddit.com/r/LocalLLaMA/comments/1o2h6n0/anyone_know_of_a_static_fp8_version_of_the_latest/ | 02modest_dills | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2h6n0 | false | null | t3_1o2h6n0 | /r/LocalLLaMA/comments/1o2h6n0/anyone_know_of_a_static_fp8_version_of_the_latest/ | false | false | self | 1 | null |
Self-Hosting AI Video Models | 6 | Hi everyone, I'm building apps that generate AI images and videos, and I need some advice on deploying open-source models like those from Alibaba's WAN, CIVIT AI Lora Models or similar ones on my own server. Right now, I'm using ComfyUI on a serverless setup like Runpod for images, but videos are trickier – I can't get... | 2025-10-09T20:12:31 | https://www.reddit.com/r/LocalLLaMA/comments/1o2gi26/selfhosting_ai_video_models/ | Humble_Flamingo_4145 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2gi26 | false | null | t3_1o2gi26 | /r/LocalLLaMA/comments/1o2gi26/selfhosting_ai_video_models/ | false | false | self | 6 | null |
What happened to basedbase and GLM-4.5-Air-GLM-4.6-Distill? | 5 | I've been trying out my new AMD Ryzen AI Max+ system over the past few days, and one of the models I wanted to try was https://huggingface.co/BasedBase/GLM-4.5-Air-GLM-4.6-Distill, which I had bookmarked earlier. When I visited huggingface page today, it's just a 404, as is basedbase's entire profile. Does anyone kno... | 2025-10-09T19:45:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o2fsre/what_happened_to_basedbase_and/ | rpdillon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2fsre | false | null | t3_1o2fsre | /r/LocalLLaMA/comments/1o2fsre/what_happened_to_basedbase_and/ | false | false | self | 5 | null |
How the hell do I get GPT-OSS 20b to use tools in openwebui | 0 | I got Mcpo searXNG working
I tried it with gpt-oss 20b once, it kind of worked,
I try again; it doesn’t work. I try again 20 times.
Can’t use the tool.
If I use OSS 120b it works fine.
But I don’t always want to run a large model just to search up something on the internet or news.
I also set reasoning to high ... | 2025-10-09T19:44:00 | https://www.reddit.com/r/LocalLLaMA/comments/1o2fr38/how_the_hell_do_i_get_gptoss_20b_to_use_tools_in/ | Adventurous-Gold6413 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2fr38 | false | null | t3_1o2fr38 | /r/LocalLLaMA/comments/1o2fr38/how_the_hell_do_i_get_gptoss_20b_to_use_tools_in/ | false | false | self | 0 | null |
Interactive Sandbox for AI Coding Agents | 2 | With so many AI-app builders available today, we wanted to provide an SDK that made it easy for agents to run workloads on the cloud.
We built a little playground that shows exactly how it works: [https://platform.beam.cloud/sandbox-demo](https://platform.beam.cloud/sandbox-demo)
The most popular use-case is running... | 2025-10-09T19:35:58 | velobro | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o2fjon | false | null | t3_1o2fjon | /r/LocalLLaMA/comments/1o2fjon/interactive_sandbox_for_ai_coding_agents/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': 'sl27w92u15uf1', 'resolutions': [{'height': 57, 'url': 'https://preview.redd.it/sl27w92u15uf1.png?width=108&crop=smart&auto=webp&s=58d928a1463501132cb923b7325af2924d2c501d', 'width': 108}, {'height': 115, 'url': 'https://preview.redd.it/sl27w92u15uf1.png?width=216&crop=smart&auto=web... | |
I vibecoded an open source Grok Heavy emulator [CODE] | 18 | So, I’ve been completely obsessed with the idea behind Grok Heavy for the past few days. If you haven't heard of it, it’s xAI’s top model that basically has a team of internal AI agents brainstorm an answer before giving it to you. My first thought was, "I wonder if I can build something with that same philosophy, but ... | 2025-10-09T19:14:06 | https://github.com/valerka1292/OpenHeavy | Objective-Good310 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1o2ezo0 | false | null | t3_1o2ezo0 | /r/LocalLLaMA/comments/1o2ezo0/i_vibecoded_an_open_source_grok_heavy_emulator/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'pndqJxRfxT-xzdR0BdB45NCU4WYw5lcb602cXWaatl0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/pndqJxRfxT-xzdR0BdB45NCU4WYw5lcb602cXWaatl0.png?width=108&crop=smart&auto=webp&s=395a35cb155992b2c90b52dcba277b2d942387d0', 'width': 108}, {'height': 108, 'url': 'h... | |
I vibecoded an open source Grok Heavy emulator [CODE] | 1 | [removed] | 2025-10-09T19:12:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2eykv/i_vibecoded_an_open_source_grok_heavy_emulator/ | Objective-Good310 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2eykv | false | null | t3_1o2eykv | /r/LocalLLaMA/comments/1o2eykv/i_vibecoded_an_open_source_grok_heavy_emulator/ | true | false | spoiler | 1 | null |
Local LLMs vs. cloud for coding | 17 | Hello,
I admit that I had no idea how popular and capable local LLMs (Large Language Models) are. I thought they were mainly for researchers, students, and enthusiasts who like to learn and tinker.
I'm curious how local models compare to cloud solutions like ChatGPT, Gemini, Claude, and others, especially in terms of... | 2025-10-09T18:52:46 | https://www.reddit.com/r/LocalLLaMA/comments/1o2efiq/local_llms_vs_cloud_for_coding/ | tominicz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2efiq | false | null | t3_1o2efiq | /r/LocalLLaMA/comments/1o2efiq/local_llms_vs_cloud_for_coding/ | false | false | self | 17 | null |
Deepmind notebook on how to finetune Gemma 3 270m | 43 | Deepmind just dropped a handy little colab on fine-tuning gemma3-270m for emoji generation. It's nothing SOTA, but it's a great notebook for learning TRL and fine-tuning.
This is a super lower resource task with 270m parameter model, qlora, short sequences. so it's a great one to try out locally or on colab. It's also... | 2025-10-09T18:43:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2e76z/deepmind_notebook_on_how_to_finetune_gemma_3_270m/ | Zealousideal-Cut590 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2e76z | false | null | t3_1o2e76z | /r/LocalLLaMA/comments/1o2e76z/deepmind_notebook_on_how_to_finetune_gemma_3_270m/ | false | false | self | 43 | {'enabled': False, 'images': [{'id': 'nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/nkhh65ujo5BznFJFojoMPaKjGuLSpPj6KGhRov-ykOg.png?width=108&crop=smart&auto=webp&s=3118973964e59402feea50688d746b67ecd3d2df', 'width': 108}, {'height': 216, 'url': '... |
Deepmind notebook on how to finetune Gemma 3 270m | 1 | [removed] | 2025-10-09T18:43:03 | https://www.reddit.com/r/LocalLLaMA/comments/1o2e6fz/deepmind_notebook_on_how_to_finetune_gemma_3_270m/ | Zealousideal-Cut590 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2e6fz | false | null | t3_1o2e6fz | /r/LocalLLaMA/comments/1o2e6fz/deepmind_notebook_on_how_to_finetune_gemma_3_270m/ | false | false | self | 1 | null |
looking for a guide on how to setup localLLm cluster using 3 x Nvidia Jetson Orin Nano Super. | 1 | So I was lucky enough to get a hold of 3 x Nvidia Jetson Orin Nano Super dev kits at a good price.
I got them all updated and installed with NVMe SSDs and they are all running great on their own, tested with Ollama and it looks good.
So no problem there. L4T 36.4.7 *"just having issues with JTOP not detecting jetpa... | 2025-10-09T18:27:15 | https://www.reddit.com/r/LocalLLaMA/comments/1o2drdu/looking_for_a_guide_on_how_to_setup_localllm/ | Von_plaf | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2drdu | false | null | t3_1o2drdu | /r/LocalLLaMA/comments/1o2drdu/looking_for_a_guide_on_how_to_setup_localllm/ | false | false | self | 1 | null |
Local LLM on old HP Z4 G4? | 2 | I need your opinion.
I could get an older HP Z4 G4 workstation for a case of beer. Unfortunately, the workstation only has a Xeon W-2123 CPU but 256 GB DDR4 RAM 2666MHz. The idea was to install one or two used RTX 5060 TI 16Gb cards and use the workstation as a local LLM server. The goal is not to use giant models ext... | 2025-10-09T18:23:14 | https://www.reddit.com/r/LocalLLaMA/comments/1o2dnle/local_llm_on_old_hp_z4_g4/ | Pythagoras1600 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2dnle | false | null | t3_1o2dnle | /r/LocalLLaMA/comments/1o2dnle/local_llm_on_old_hp_z4_g4/ | false | false | self | 2 | null |
anyone noticed ollama embeddings are extremely slow? | 1 | trying to use mxbai-embed-large to embed 27k custom xml testSegments using langchain4j, but it's extremely slow untill it times out. there seems to be a message in the logs documented here [https://github.com/ollama/ollama/issues/12381](https://github.com/ollama/ollama/issues/12381) but i don't know if it's a bug or ... | 2025-10-09T18:23:03 | https://www.reddit.com/r/LocalLLaMA/comments/1o2dnfc/anyone_noticed_ollama_embeddings_are_extremely/ | emaayan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2dnfc | false | null | t3_1o2dnfc | /r/LocalLLaMA/comments/1o2dnfc/anyone_noticed_ollama_embeddings_are_extremely/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'k-NpHS_W2d70fEsN0J3HgZyLLj35n7pzAIKEe16LrYY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/k-NpHS_W2d70fEsN0J3HgZyLLj35n7pzAIKEe16LrYY.png?width=108&crop=smart&auto=webp&s=2c5686c72ff808ca8f3650a3c74655be1da449f0', 'width': 108}, {'height': 108, 'url': 'h... |
Less is More: Recursive Reasoning with Tiny Networks | 8 | 2025-10-09T18:09:58 | https://arxiv.org/html/2510.04871v1 | Opposite_West8608 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1o2db95 | false | null | t3_1o2db95 | /r/LocalLLaMA/comments/1o2db95/less_is_more_recursive_reasoning_with_tiny/ | false | false | default | 8 | null | |
Fastest Fill-in-the-middle Model for General Text? | 4 | I am only able to find FIM models for coding and not for general text. | 2025-10-09T17:51:54 | https://www.reddit.com/r/LocalLLaMA/comments/1o2cu00/fastest_fillinthemiddle_model_for_general_text/ | lattenjoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2cu00 | false | null | t3_1o2cu00 | /r/LocalLLaMA/comments/1o2cu00/fastest_fillinthemiddle_model_for_general_text/ | false | false | self | 4 | null |
Does quantization need training data and will it lower performance for task outside of training data? | 4 | Does quantization make the model more specialized on certain tasks like benchmarks?
I'm using non English dataset and wonder if quantization could make the model perform even worse in my language than the difference in an English benchmark. | 2025-10-09T17:18:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o2bxq9/does_quantization_need_training_data_and_will_it/ | arstarsta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2bxq9 | false | null | t3_1o2bxq9 | /r/LocalLLaMA/comments/1o2bxq9/does_quantization_need_training_data_and_will_it/ | false | false | self | 4 | null |
What's the difference between different 4bit quantization methods? Does vLLM support any one better? | 2 | There seems to be lots of types like awq, bnb, gguf, gptq, w4a16. Any pros and cons of each type except for gguf support different bits. | 2025-10-09T17:14:34 | https://www.reddit.com/r/LocalLLaMA/comments/1o2bu4o/whats_the_difference_between_different_4bit/ | arstarsta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2bu4o | false | null | t3_1o2bu4o | /r/LocalLLaMA/comments/1o2bu4o/whats_the_difference_between_different_4bit/ | false | false | self | 2 | null |
yanolja/YanoljaNEXT-Rosetta-12B-2510 | 34 | We’ve just uploaded the **next version of YanoljaNEXT-Rosetta-12B**, a translation model that’s been **significantly improved** from the previous release.
🧠 **Available on Hugging Face:**
👉 [YanoljaNEXT-Rosetta-12B-2510](https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-12B-2510)
Below is a summary generated by Cl... | 2025-10-09T17:06:16 | https://www.reddit.com/r/LocalLLaMA/comments/1o2bm3z/yanoljayanoljanextrosetta12b2510/ | OldPin8654 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2bm3z | false | null | t3_1o2bm3z | /r/LocalLLaMA/comments/1o2bm3z/yanoljayanoljanextrosetta12b2510/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': '46myQmrkdrTA-Hw5-nEsi1rgfhPvklYDsZYGdeY9qLw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/46myQmrkdrTA-Hw5-nEsi1rgfhPvklYDsZYGdeY9qLw.png?width=108&crop=smart&auto=webp&s=726ddfb42e64b3dcff3a983a5a6aaee31447fa56', 'width': 108}, {'height': 116, 'url': 'h... |
How can CodeBleu be a standard | 1 | Apologies if I failed to grab the concept properly. But since the applications/samples we test our model on using CodeBleu (to my knowledge atleast) isnt same across the board. How can two researchers compare the CodeBleu scores they got on each of their separate LLMs. I am talking about research papers publishing thei... | 2025-10-09T17:00:06 | https://www.reddit.com/r/LocalLLaMA/comments/1o2bg0p/how_can_codebleu_be_a_standard/ | Minute-Plantain-1213 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2bg0p | false | null | t3_1o2bg0p | /r/LocalLLaMA/comments/1o2bg0p/how_can_codebleu_be_a_standard/ | false | false | self | 1 | null |
Chinny (iOS/MacOS): offline, on-device voice cloning with an optimized Chatterbox model | 9 | Hi folks, I've been experimenting with running voice cloning fully offline. Part of the motivation was that I don't trust those web-based or wrapper AI voice cloning apps that gather user data --- who knows when our information could be sold or used in unexpected ways. So I developed **Chinny,** an iOS(16.6+) / macOS(1... | 2025-10-09T16:49:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o2b666/chinny_iosmacos_offline_ondevice_voice_cloning/ | Acceptable-Cycle4645 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2b666 | false | null | t3_1o2b666 | /r/LocalLLaMA/comments/1o2b666/chinny_iosmacos_offline_ondevice_voice_cloning/ | false | false | self | 9 | null |
ReasonScape Evaluation: AI21 Jamba Reasoning vs Qwen3 4B vs Qwen3 4B 2507 | 60 | It's an open secret that LLM benchmarks are bullshit. I built [ReasonScape](https://reasonscape.com/) to be different, lets see what it tells us about how AI21's latest drop compared to the high quality 4B we know and love.
My usual disclaimer is that these are all [information processing tasks](https://github.com/the... | 2025-10-09T16:45:05 | https://www.reddit.com/r/LocalLLaMA/comments/1o2b1yo/reasonscape_evaluation_ai21_jamba_reasoning_vs/ | kryptkpr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2b1yo | false | null | t3_1o2b1yo | /r/LocalLLaMA/comments/1o2b1yo/reasonscape_evaluation_ai21_jamba_reasoning_vs/ | false | false | 60 | null | |
Starter build for running local LLMs | 5 | I'm helping a friend with his first build for running local LLMs, for learning and trying things out. Eventually he plan on doing some projects for work.
Here's my thoughts on a good build that isn't breaking the bank and can be upgraded over time.
CPU: Go with AMD AM5 socket. Epyc and Thread ripper is too expensive.... | 2025-10-09T16:40:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o2axch/starter_build_for_running_local_llms/ | UncleRedz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2axch | false | null | t3_1o2axch | /r/LocalLLaMA/comments/1o2axch/starter_build_for_running_local_llms/ | false | false | self | 5 | null |
Comparing benchmarks | 0 | Found this, interesting and apparently free https://artificialanalysis.ai. Yes, I know benchmarks are suspect for good reason but we still look at them. I have no affiliation with the website. | 2025-10-09T16:30:03 | https://www.reddit.com/r/LocalLLaMA/comments/1o2anpe/comparing_benchmarks/ | jarec707 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2anpe | false | null | t3_1o2anpe | /r/LocalLLaMA/comments/1o2anpe/comparing_benchmarks/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'RVufpUx3tddh_BCVq7ZzBCU7nLRDZ_d0EprIuvN6J-E', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/RVufpUx3tddh_BCVq7ZzBCU7nLRDZ_d0EprIuvN6J-E.png?width=108&crop=smart&auto=webp&s=700f91dbca11e5a7030b915550ae877ef725a0d4', 'width': 108}, {'height': 120, 'url': 'h... |
Is it possible to download models independently? | 1 | I'm new to local llms and would like to know if I'm able to download models through the browser/`wget`/`curl` so that I can back them up locally. Downloading them takes ages and if I mess something up having them backed up to an external drive would be really convenient. | 2025-10-09T16:26:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ajxq/is_it_possible_to_download_models_independently/ | VegetableJudgment971 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ajxq | false | null | t3_1o2ajxq | /r/LocalLLaMA/comments/1o2ajxq/is_it_possible_to_download_models_independently/ | false | false | self | 1 | null |
AI optimization | 5 | With the continuous improvement in optimization and hardware, how long do you anticipate it will take before large-scale models (over 100 billion parameters) become more accessible to the general public? | 2025-10-09T15:44:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o29ekl/ai_optimization/ | a_normal_user1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o29ekl | false | null | t3_1o29ekl | /r/LocalLLaMA/comments/1o29ekl/ai_optimization/ | false | false | self | 5 | null |
test123 | 1 | [deleted] | 2025-10-09T15:37:50 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1o298v8 | false | null | t3_1o298v8 | /r/LocalLLaMA/comments/1o298v8/test123/ | false | false | default | 1 | null | ||
Write prompts in your native language. My one-press tool translates them to English instantly & offline (supports 99+ languages) | 0 | Hey everyone
You know that feeling? You can read English perfectly, but trying to write a prompt from scratch sometimes is a real pain. It totally breaks the creative flow and can ruin a good RP.
So I made this.
It's a simple tool: you write in your native language (99+ supported), press one key (F9), and it instan... | 2025-10-09T15:33:33 | ThetaCursed | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o294t2 | false | null | t3_1o294t2 | /r/LocalLLaMA/comments/1o294t2/write_prompts_in_your_native_language_my_onepress/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'aymd2i8zu3uf1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/aymd2i8zu3uf1.gif?width=108&crop=smart&format=png8&s=ae33134142a3edb5fcfea0f9848b7401aa329bec', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/aymd2i8zu3uf1.gif?width=216&crop=smart&format... | |
Write prompts in your native language. My one-press tool translates them to English instantly & offline (supports 99+ languages) | 0 | ERROR: type should be string, got "https://i.redd.it/hg8xt275f3uf1.gif\n\nHey everyone \n \nYou know that feeling? You can read English perfectly, but trying to write a prompt from scratch sometimes is a real pain. It totally breaks the creative flow and can ruin a good RP. \n \nSo I made this. \nIt's a simple tool: you write in your native language (99+ supported), press one key (F9), and it instantly translates the whole text field to English, right in place. \n \nThe best part? It's 100% offline. Your prompts never leave your PC. This makes it super fast (no lag) and perfect for LM-Studio or something else. \n \nHope it helps some of you out! It's open-source, would love to hear what you think.\n\nGitHub: \n[https://github.com/ThetaCursed/NativePrompt](https://github.com/ThetaCursed/NativePrompt) \n" | 2025-10-09T15:25:24 | https://www.reddit.com/r/LocalLLaMA/comments/1o28wzo/write_prompts_in_your_native_language_my_onepress/ | ThetaCursed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o28wzo | false | null | t3_1o28wzo | /r/LocalLLaMA/comments/1o28wzo/write_prompts_in_your_native_language_my_onepress/ | false | false | 0 | null | |
Feedback on streaming live meeting transcripts into any AI Chat Interface | 2 | Hey guys,
I'm prototyping a small tool/MCP server that streams a live meeting transcript into the AI chat interface you already use. During the call you could ask it things like “Summarize the last 10 min", “Pull action items so far", "Fact‑check what was just said” or "Research the topic we just discussed". This woul... | 2025-10-09T15:21:39 | https://www.reddit.com/r/LocalLLaMA/comments/1o28ta6/feedback_on_streaming_live_meeting_transcripts/ | DerErzfeind61 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o28ta6 | false | null | t3_1o28ta6 | /r/LocalLLaMA/comments/1o28ta6/feedback_on_streaming_live_meeting_transcripts/ | false | false | self | 2 | null |
If I buy a GPU, will the MOE model inference speed improve with partial offload? | 8 | Recently, what I've read, especially about MOE models, has confused me a lot, and I haven't been able to understand if getting an external GPU would be beneficial or not. I understand that even if I offload 99% of parameters in dense models, there will be a significant performance drop. And even with MOE models It's cl... | 2025-10-09T15:21:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o28soy/if_i_buy_a_gpu_will_the_moe_model_inference_speed/ | gkon7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o28soy | false | null | t3_1o28soy | /r/LocalLLaMA/comments/1o28soy/if_i_buy_a_gpu_will_the_moe_model_inference_speed/ | false | false | 8 | null | |
Document Processing for RAG question and answering, and automatic processing of incoming with Business Metadata | 2 | I am in the process of starting to setup RAG on my companies documents, mainly acknowledgments, invoices and purchase orders.
At the moment I am running all the PDF's exported from the PST archive of a mailbox through MinerU2.5-2509-1.2B, Docling Accurate and PyMuPDF, then combining the contents of all three into a si... | 2025-10-09T15:19:07 | https://www.reddit.com/r/LocalLLaMA/comments/1o28qwf/document_processing_for_rag_question_and/ | Unique_Marsupial_556 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o28qwf | false | null | t3_1o28qwf | /r/LocalLLaMA/comments/1o28qwf/document_processing_for_rag_question_and/ | false | false | self | 2 | null |
ZentithLLM — Fully Offline, Privacy-First LLM for Android Devices | 8 | Hey r/LocalLLaMA community!
I’ve been exploring offline AI models on Android and noticed a big gap: most AI assistants either require constant internet or send data to cloud servers. As someone who values privacy and local control, I decided to build **ZentithLLM**, a fully offline AI assistant that runs entirely on-d... | 2025-10-09T15:18:50 | https://www.reddit.com/r/LocalLLaMA/comments/1o28qmw/zentithllm_fully_offline_privacyfirst_llm_for/ | Quiet-Baker8432 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o28qmw | false | null | t3_1o28qmw | /r/LocalLLaMA/comments/1o28qmw/zentithllm_fully_offline_privacyfirst_llm_for/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'hM5SKSbDT8qcg8SjoUIRpNzQW65bvcwuMtq4SFvpc30', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/hM5SKSbDT8qcg8SjoUIRpNzQW65bvcwuMtq4SFvpc30.png?width=108&crop=smart&auto=webp&s=30366fc6fa6d9d7e1f829ad663b1a2c2b8135c5a', 'width': 108}, {'height': 216, 'url': '... |
Moondream3 and Salesforce GTA-1 for UI grounding in computer-use agents | 18 | Moondream3 and Salesforce GTA-1 for UI grounding in computer-use agents
The numbers on ScreenSpot-v2 benchmark:
GTA-1 leads in accuracy (96% vs 84%), but Moondream3 is 2x faster (1.04s vs 1.97s avg).
The median time gap is even bigger: 0.78s vs 1.96s - that's a 2.5x speedup.
GitHub : https://github.com/trycua/cua
... | 2025-10-09T14:48:59 | https://v.redd.it/0odmsxg1n3uf1 | Impressive_Half_2819 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o27xzz | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/0odmsxg1n3uf1/DASHPlaylist.mpd?a=1762613353%2CNTkzNTBmM2VkZGIwZmYxM2I3M2NjNTg1NmZhMmI3NDk1MGM1ZjA1OTc5Njc4YmI3N2M2NjhmZDhmZGE2ODcxYQ%3D%3D&v=1&f=sd', 'duration': 80, 'fallback_url': 'https://v.redd.it/0odmsxg1n3uf1/DASH_720.mp4?source=fallback', 'ha... | t3_1o27xzz | /r/LocalLLaMA/comments/1o27xzz/moondream3_and_salesforce_gta1_for_ui_grounding/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'MXhzZGNjNzFuM3VmMeWLBg1mAXwAigO5PzLkc4zOrANcV84YU3-0ubuxy7cx', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/MXhzZGNjNzFuM3VmMeWLBg1mAXwAigO5PzLkc4zOrANcV84YU3-0ubuxy7cx.png?width=108&crop=smart&format=pjpg&auto=webp&s=c5b7b3d82dd23aa3d68aba5fe0451f9767785... | |
Introducing Playable1-GGUF, by far the world's best open-source 7B model for vibe coding retro arcade games! | 188 | I've taken this idea too far, clearly, but the results are fun! Playable1-GGUF is a q4\_k\_m Qwen2.5-Coder-7B-Instruct fine-tuned on 52,809 lines of Python pygame scripts.
Over the past week I've dialed in the LORA parameters, added games, ironed the bugs out of the dataset, and open-sourced everything.
No q4 model, ... | 2025-10-09T14:48:44 | https://v.redd.it/hscmojn4m3uf1 | jfowers_amd | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o27xsj | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/hscmojn4m3uf1/DASHPlaylist.mpd?a=1762613338%2CMDQ5ZjFlZjNhYThkODkzNzRkOWRjMmQ1ZTQ2YzU5ZjY2MDhkNWFjZjEzYjg3NzM5NDU4Yjc2MzY3MWFmMjZmNA%3D%3D&v=1&f=sd', 'duration': 15, 'fallback_url': 'https://v.redd.it/hscmojn4m3uf1/DASH_1080.mp4?source=fallback', 'h... | t3_1o27xsj | /r/LocalLLaMA/comments/1o27xsj/introducing_playable1gguf_by_far_the_worlds_best/ | false | false | 188 | {'enabled': False, 'images': [{'id': 'amdjandqbjRtM3VmMYQO32V0xtyx5agXCcjKDs7UavRodqRFn_xjnlOv-a1T', 'resolutions': [{'height': 135, 'url': 'https://external-preview.redd.it/amdjandqbjRtM3VmMYQO32V0xtyx5agXCcjKDs7UavRodqRFn_xjnlOv-a1T.png?width=108&crop=smart&format=pjpg&auto=webp&s=210438ca5a74713025bc2987068f6876e542... | |
Will open-source (or more accurately open-weight) models always lag behind closed-source models? | 239 | It seems like open source LLM's are always one step behind closed-source companies. The question here is, is there a possibility for open-weight LLM's to overtake these companies?
Claude, Grok, ChatGPT and other's have billions of dollars in investments yet we saw the leaps DeepSeek was capable of.
Shaking Silico... | 2025-10-09T14:28:23 | Striking_Wedding_461 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o27ex3 | false | null | t3_1o27ex3 | /r/LocalLLaMA/comments/1o27ex3/will_opensource_or_more_accurately_openweight/ | false | false | default | 239 | {'enabled': True, 'images': [{'id': 'a1fnssvaj3uf1', 'resolutions': [{'height': 68, 'url': 'https://preview.redd.it/a1fnssvaj3uf1.png?width=108&crop=smart&auto=webp&s=6e49bbb763bbea427cd9344496a299584e49338a', 'width': 108}, {'height': 137, 'url': 'https://preview.redd.it/a1fnssvaj3uf1.png?width=216&crop=smart&auto=web... | |
How do you guys run Codex CLI with OpenRouter models? (im getting model_not_found) | 3 | hi guys,
i got openrouter API key with credits and a working codex cli
I tried different configs to the toml and can't seem to get it working, always hitting that model\_not\_found issue
the latest version of my config is:
\# Set the default model
model = "google/gemma-7b-it"
windows\_wsl\_setup\_acknowledg... | 2025-10-09T14:28:20 | https://www.reddit.com/r/LocalLLaMA/comments/1o27evq/how_do_you_guys_run_codex_cli_with_openrouter/ | TruthTellerTom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o27evq | false | null | t3_1o27evq | /r/LocalLLaMA/comments/1o27evq/how_do_you_guys_run_codex_cli_with_openrouter/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'F_9MM-rF2vdBXxQ1y06hQopypniBGpYdwwzD0ZOnzlg', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/F_9MM-rF2vdBXxQ1y06hQopypniBGpYdwwzD0ZOnzlg.png?width=108&crop=smart&auto=webp&s=32a58979b0a9d8b4c5df5fae1dccedf83b8b8f17', 'width': 108}, {'height': 113, 'url': 'h... |
Stop converting full documents to Markdown directly in your indexing pipeline | 38 | Hey everyone,
I've been working on document parsing for RAG pipelines, and I keep seeing the same pattern in many places: parse document → convert to markdown → feed to RAG. I get *why* we do this. You want one consistent format so your downstream pipeline doesn't need to handle PDFs, Excel, Word docs, etc. separately... | 2025-10-09T14:05:42 | https://www.reddit.com/r/LocalLLaMA/comments/1o26u9e/stop_converting_full_documents_to_markdown/ | Effective-Ad2060 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o26u9e | false | null | t3_1o26u9e | /r/LocalLLaMA/comments/1o26u9e/stop_converting_full_documents_to_markdown/ | false | false | self | 38 | null |
Oct. 2025 - Best Local Transcription Framework? | 3 | Hi, I was curious to hear from you about the currently **"best" local transcription framework.** I am trying to convert hours of dialogue with amazing people whose life stories we want to conserve.
I am all open with regards to features, incl. adding custom words etc. For my workflow I intend to ideally transcribe the... | 2025-10-09T14:04:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o26te6/oct_2025_best_local_transcription_framework/ | therealAtten | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o26te6 | false | null | t3_1o26te6 | /r/LocalLLaMA/comments/1o26te6/oct_2025_best_local_transcription_framework/ | false | false | self | 3 | null |
Best LLM gateway Suggestions? | 11 | I've been testing out different LLM gateways for a multi-agent system and wanted to share some notes. I have tried multiple models & hosted them, but lately I’ve shifted focus to LLM gateways.
Most of the hosted ones are fine for basic key management or retries, but they fall short once you're comparing models sid... | 2025-10-09T13:48:53 | https://www.reddit.com/r/LocalLLaMA/comments/1o26fda/best_llm_gateway_suggestions/ | Silent_Employment966 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o26fda | false | null | t3_1o26fda | /r/LocalLLaMA/comments/1o26fda/best_llm_gateway_suggestions/ | false | false | self | 11 | null |
Claude Sonnet 4.5 has ideological biases in finetuning and system instructions | 0 | Thought this might come across interesting on how Claude Sonnet 4.5 Thinking mode has specific ideological bias it is aware of but admits it can’t avoid.
I tried to see how quick the ”harmful detector” would go off on Sonnet 4.5 by simple neutral language querying about Adolf Hitler from a historian’s perspective and ... | 2025-10-09T13:41:27 | https://www.reddit.com/gallery/1o268zv | Stochastic_berserker | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1o268zv | false | null | t3_1o268zv | /r/LocalLLaMA/comments/1o268zv/claude_sonnet_45_has_ideological_biases_in/ | false | false | 0 | null | |
Do FP16 MLX models run faster than the 8-bit quantized version of the same model because of the lack of native FP8 support on Apple hardware? | 11 | IIUC Apple hardware only natively supports FP16. All other quantization levels are not natively supported and therefore must be simulated by the hardware, leading to decreased inference speeds.
Is my understanding correct? If so, how much better is running FP16 vs FP8?
| 2025-10-09T13:40:39 | https://www.reddit.com/r/LocalLLaMA/comments/1o268bl/do_fp16_mlx_models_run_faster_than_the_8bit/ | nonredditaccount | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o268bl | false | null | t3_1o268bl | /r/LocalLLaMA/comments/1o268bl/do_fp16_mlx_models_run_faster_than_the_8bit/ | false | false | self | 11 | null |
OpenAI forum post: “Top 30 customers who’ve used 1T+ tokens” (unconfirmed) | 98 | A list circulating via the OpenAI community forum claims 30 orgs (e.g., Duolingo, Shopify, Notion, Salesforce, T-Mobile) each crossed **1T+ tokens** on OpenAI models. Interesting signal of who’s scaling—**treat as unverified**.
* Why it matters: points to heavy production use across edtech, SaaS, dev tools, and telec... | 2025-10-09T13:24:58 | https://www.reddit.com/r/LocalLLaMA/comments/1o25uy1/openai_forum_post_top_30_customers_whove_used_1t/ | freesysck | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o25uy1 | false | null | t3_1o25uy1 | /r/LocalLLaMA/comments/1o25uy1/openai_forum_post_top_30_customers_whove_used_1t/ | false | false | self | 98 | {'enabled': False, 'images': [{'id': '4WmZ5Q-9dVFGCTVvLj9oT-noGe7-M4wRwatmCAIRCVA', 'resolutions': [{'height': 114, 'url': 'https://external-preview.redd.it/4WmZ5Q-9dVFGCTVvLj9oT-noGe7-M4wRwatmCAIRCVA.png?width=108&crop=smart&auto=webp&s=033248978460870993d3db77c1c9d184bb823d83', 'width': 108}, {'height': 229, 'url': '... |
How the dataset is prepared for the slightly big AIs like 4B, 7B and more? | 0 | how does big AI like 7B and more, get trained on multi domain generalizations to remain consistent when prompted for that specific topic? for example, how would a model that knows code but also knows some science topics, would have the dataset formed? | 2025-10-09T12:35:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o24qcb/how_the_dataset_is_prepared_for_the_slightly_big/ | thecowmilk_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o24qcb | false | null | t3_1o24qcb | /r/LocalLLaMA/comments/1o24qcb/how_the_dataset_is_prepared_for_the_slightly_big/ | false | false | self | 0 | null |
Anyone using automated evaluators (LLM-as-a-Judge + programmatic) for prompt or agent testing? | 2 | I am working on ai agent and it consumes my lot of time in evaluating the agent and fidning the bugs. So i thought of trying to set up a workflow to evaluate agents automatically instead of just manual QA. I’m mixing **LLM-as-a-Judge** for subjective stuff (like coherence, tone) with **programmatic evaluators** for fac... | 2025-10-09T12:26:05 | https://www.reddit.com/r/LocalLLaMA/comments/1o24j5f/anyone_using_automated_evaluators_llmasajudge/ | Fit-Practice-9612 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o24j5f | false | null | t3_1o24j5f | /r/LocalLLaMA/comments/1o24j5f/anyone_using_automated_evaluators_llmasajudge/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'uhRpB7D-vTXyU3kWrM4Uv0wsEl8ANQiO9SXhRH44nmE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/uhRpB7D-vTXyU3kWrM4Uv0wsEl8ANQiO9SXhRH44nmE.png?width=108&crop=smart&auto=webp&s=2ac91097383d12b50cccd11a156d801425048149', 'width': 108}, {'height': 113, 'url': 'h... |
How do I keep track of what is the best small coding models that will run on 8gb - 24gb of VRAM? | 0 | I bought a 3090 for coding and I know that there are models good enough to run just fine on my system. I did some great things with GPT 3.5 and the current small models blow that away. Still, I can't find any good leader boards to help keep track of which ones are the best. Does anyone have anything for me? | 2025-10-09T12:22:55 | https://www.reddit.com/r/LocalLLaMA/comments/1o24gsr/how_do_i_keep_track_of_what_is_the_best_small/ | LanceThunder | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o24gsr | false | null | t3_1o24gsr | /r/LocalLLaMA/comments/1o24gsr/how_do_i_keep_track_of_what_is_the_best_small/ | false | false | self | 0 | null |
microsoft/UserLM-8b - “Unlike typical LLMs that are trained to play the role of the 'assistant' in conversation, we trained UserLM-8b to simulate the 'user' role” | 493 | 2025-10-09T11:54:17 | https://huggingface.co/microsoft/UserLM-8b | nullmove | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1o23vqf | false | null | t3_1o23vqf | /r/LocalLLaMA/comments/1o23vqf/microsoftuserlm8b_unlike_typical_llms_that_are/ | false | false | default | 493 | {'enabled': False, 'images': [{'id': 'AHBKf2lyQkjC30uEVnsWIAOzEiogI0jy6tjwogMGZ5A', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/AHBKf2lyQkjC30uEVnsWIAOzEiogI0jy6tjwogMGZ5A.png?width=108&crop=smart&auto=webp&s=7a6bab1ec429786ece52e66105af269e90edbb7a', 'width': 108}, {'height': 116, 'url': 'h... | |
OSS 120B on dual 3090 setup, results, questions | 1 | [removed] | 2025-10-09T11:46:58 | https://www.reddit.com/r/LocalLLaMA/comments/1o23qng/oss_120b_on_dual_3090_setup_results_questions/ | me-but-elsewhere | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o23qng | false | null | t3_1o23qng | /r/LocalLLaMA/comments/1o23qng/oss_120b_on_dual_3090_setup_results_questions/ | false | false | self | 1 | null |
Localized LLMS the key to B2B AI bans? | 0 | Lately I’ve been obsessing over the idea that localized LLMs might be the key to unlocking many of the draconian bans on AI we still see at large B2B enterprises.
What I’m currently seeing at many of the places I teach and consult are IT-sanctioned internal chatbots running within the confines of the corporate firewal... | 2025-10-09T11:06:46 | https://www.reddit.com/r/LocalLLaMA/comments/1o22zxj/localized_llms_the_key_to_b2b_ai_bans/ | DeanOnDelivery | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o22zxj | false | null | t3_1o22zxj | /r/LocalLLaMA/comments/1o22zxj/localized_llms_the_key_to_b2b_ai_bans/ | false | false | self | 0 | null |
Are there any NSFW models that you can run on 12gb beam and 32 ram that are worth running? | 0 | I want stories that have some nuance and understand more complex concepts like being tied up and such
| 2025-10-09T11:00:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o22w3n/are_there_any_nsfw_models_that_you_can_run_on/ | Dex921 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o22w3n | false | null | t3_1o22w3n | /r/LocalLLaMA/comments/1o22w3n/are_there_any_nsfw_models_that_you_can_run_on/ | false | false | nsfw | 0 | null |
What are your thoughts on tencent/Hunyuan-A13B-Instruct? | 37 | Is this a good model? I don't see many people talking about this. Slso, i wanted to try this model on 32gb ram and 12gb vram with there official gptq-int 4 quant: tencent/Hunyuan-A13B-Instruct-GPTQ-Int4. Also, what backend and frontend would you guys recommend for gptq? | 2025-10-09T10:59:21 | https://huggingface.co/tencent/Hunyuan-A13B-Instruct | Brave-Hold-9389 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1o22v1b | false | null | t3_1o22v1b | /r/LocalLLaMA/comments/1o22v1b/what_are_your_thoughts_on/ | false | false | 37 | {'enabled': False, 'images': [{'id': 'B1uwVS2BmhDOjFW0XJ6pW7-r7n5zECGun4YlOmky9YY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/B1uwVS2BmhDOjFW0XJ6pW7-r7n5zECGun4YlOmky9YY.png?width=108&crop=smart&auto=webp&s=07fddabe91e442028f9a3c3afd189223a7d91fce', 'width': 108}, {'height': 116, 'url': 'h... | |
Ideal cost effective Agentic coding membership strategy for my beginner needs? | 0 | All of the options are quite confusing. As a beginner im just building mostly intermediate python stuff at only a few hours a day, so im figuring that i may not need the best possible models for that, so my thoughts are maybe using Gwen Code Free Tier as the workhorse (or maybe Z AI membership) and then Openai codex fo... | 2025-10-09T10:40:05 | https://www.reddit.com/r/LocalLLaMA/comments/1o22iwo/ideal_cost_effective_agentic_coding_membership/ | jayn35 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o22iwo | false | null | t3_1o22iwo | /r/LocalLLaMA/comments/1o22iwo/ideal_cost_effective_agentic_coding_membership/ | false | false | self | 0 | null |
Finetuning 'Qwen3-Coder-30B-A30B' model on 'dalle2/3blue1brown-manim' dataset? | 3 | I was just wondering if this was feasable and was looking for any specific notebooks and related tutorials / guides on this topic.
Dataset: [https://huggingface.co/datasets/dalle2/3blue1brown-manim](https://huggingface.co/datasets/dalle2/3blue1brown-manim)
Model: [https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instr... | 2025-10-09T10:15:22 | https://www.reddit.com/r/LocalLLaMA/comments/1o22432/finetuning_qwen3coder30ba30b_model_on/ | R46H4V | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o22432 | false | null | t3_1o22432 | /r/LocalLLaMA/comments/1o22432/finetuning_qwen3coder30ba30b_model_on/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'U2T1gus8j4mEbxteCPtE7NKQUGorOsSqXtuL42oWhwk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/U2T1gus8j4mEbxteCPtE7NKQUGorOsSqXtuL42oWhwk.png?width=108&crop=smart&auto=webp&s=11f500af936e684f5cc045d21b7253ea779763de', 'width': 108}, {'height': 116, 'url': 'h... |
Past vs Today? | 0 | 2025-10-09T09:58:42 | InfiniteDig6202 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o21u50 | false | null | t3_1o21u50 | /r/LocalLLaMA/comments/1o21u50/past_vs_today/ | false | false | 0 | {'enabled': True, 'images': [{'id': '88TFfG-af5_YHntj6hmyv98-9L557tXdVy2ritXOUqA', 'resolutions': [{'height': 63, 'url': 'https://preview.redd.it/0aoeirr972uf1.jpeg?width=108&crop=smart&auto=webp&s=a8be860d8811a2f91cb83231ae4c4108326a0ddf', 'width': 108}, {'height': 126, 'url': 'https://preview.redd.it/0aoeirr972uf1.jp... | |||
NVIDIA DGX Spark in the wild in a OpenAI conference | 9 | https://www.youtube.com/watch?v=1HL2YHRj270 @20:45 | 2025-10-09T09:34:30 | https://www.reddit.com/r/LocalLLaMA/comments/1o21hap/nvidia_dgx_spark_in_the_wild_in_a_openai/ | Inevitable_Ant_2924 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o21hap | false | null | t3_1o21hap | /r/LocalLLaMA/comments/1o21hap/nvidia_dgx_spark_in_the_wild_in_a_openai/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'T53fPB9xbt_XROQrrAJe3UwOmlUXKBm_MVzFCUKht80', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/T53fPB9xbt_XROQrrAJe3UwOmlUXKBm_MVzFCUKht80.jpeg?width=108&crop=smart&auto=webp&s=df7a18a40a4b23024f231ac94180e7b20c015619', 'width': 108}, {'height': 162, 'url': '... |
I tried to make LLMs do financial research together — now I have a mini AI hedge fund | 1 | [removed] | 2025-10-09T09:30:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o21f8i/i_tried_to_make_llms_do_financial_research/ | Important-Spread-888 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o21f8i | false | null | t3_1o21f8i | /r/LocalLLaMA/comments/1o21f8i/i_tried_to_make_llms_do_financial_research/ | false | false | self | 1 | null |
I tried to make LLMs do financial research together — now I have a mini AI hedge fund | 1 | [removed] | 2025-10-09T09:19:11 | https://www.reddit.com/r/LocalLLaMA/comments/1o2192i/i_tried_to_make_llms_do_financial_research/ | Express-Mountain1268 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2192i | false | null | t3_1o2192i | /r/LocalLLaMA/comments/1o2192i/i_tried_to_make_llms_do_financial_research/ | false | false | self | 1 | null |
Poco f6 8gb 256gb, 8s gen 3, adreno 735, hexagon npu, need a local ai model to run, reasoning required, any tips on what to get and how to get it? | 0 | Can someone suggest which models would work best on my device and guide me on the easiest way to set this up? Thanks in advance | 2025-10-09T08:39:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o20nmg/poco_f6_8gb_256gb_8s_gen_3_adreno_735_hexagon_npu/ | Scary_Purple_760 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o20nmg | false | null | t3_1o20nmg | /r/LocalLLaMA/comments/1o20nmg/poco_f6_8gb_256gb_8s_gen_3_adreno_735_hexagon_npu/ | false | false | self | 0 | null |
How to choose gpt-oss-120b? MXFP4, UD-Q8_K_XL or F16? | 1 | [removed] | 2025-10-09T08:28:13 | https://www.reddit.com/r/LocalLLaMA/comments/1o20i0w/how_to_choose_gptoss120b_mxfp4_udq8_k_xl_or_f16/ | Capable_Trash2065 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o20i0w | false | null | t3_1o20i0w | /r/LocalLLaMA/comments/1o20i0w/how_to_choose_gptoss120b_mxfp4_udq8_k_xl_or_f16/ | false | false | self | 1 | null |
ERNIE-4.5-VL - anyone testing it in the competition? What’s your workflow? | 31 |
So the ERNIE-4.5-VL competition is live, and I’ve been testing the model a bit for vision-language tasks. Wanted to ask the community: how are you all running VL?
Some things I’m curious about:
Are you using it mainly for image-text matching, multimodal reasoning, or something else?
What hardware/setup seems to ... | 2025-10-09T08:01:24 | https://www.reddit.com/r/LocalLLaMA/comments/1o203xu/ernie45vl_anyone_testing_it_in_the_competition/ | MoltisantiCHRST | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o203xu | false | null | t3_1o203xu | /r/LocalLLaMA/comments/1o203xu/ernie45vl_anyone_testing_it_in_the_competition/ | false | false | self | 31 | null |
How are production AI agents dealing with bot detection? (Serious question) | 10 | # The elephant in the room with AI web agents: How do you deal with bot detection?
With all the hype around "computer use" agents (Claude, GPT-4V, etc.) that can navigate websites and complete tasks, I'm surprised there isn't more discussion about a fundamental problem: **every real website has sophisticated bot detec... | 2025-10-09T07:26:42 | https://www.reddit.com/r/LocalLLaMA/comments/1o1zlt0/how_are_production_ai_agents_dealing_with_bot/ | Raise_Fickle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1zlt0 | false | null | t3_1o1zlt0 | /r/LocalLLaMA/comments/1o1zlt0/how_are_production_ai_agents_dealing_with_bot/ | false | false | self | 10 | null |
I did not realize how easy and accessible local LLMs are with models like Qwen3 4b on pure CPU. | 164 | I hadn't tried running LLMs on my laptop until today. I thought CPUs were too slow and getting the old igpu working (AMD 4650U, so Vega something) would be driver hell. So I never bothered.
On a lark, I downloaded LM Studio, downloaded Qwen3 4b q4, and I was getting 5 tok/sec generation with no hassle at all with the ... | 2025-10-09T06:53:26 | https://www.reddit.com/r/LocalLLaMA/comments/1o1z3hj/i_did_not_realize_how_easy_and_accessible_local/ | ___positive___ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1z3hj | false | null | t3_1o1z3hj | /r/LocalLLaMA/comments/1o1z3hj/i_did_not_realize_how_easy_and_accessible_local/ | false | false | self | 164 | null |
Best Vision Model for Building Interiors? | 5 | Hi all, I am looking for a vision model that can accurately describe/identify the entry points of an image (such as hallways, doors, windows, etc). Any ideas as to which model would work the best for this? Or if I may need to train my own? Many thanks for the help! | 2025-10-09T06:40:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o1yw57/best_vision_model_for_building_interiors/ | AffectionateTop7221 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1yw57 | false | null | t3_1o1yw57 | /r/LocalLLaMA/comments/1o1yw57/best_vision_model_for_building_interiors/ | false | false | self | 5 | null |
Chatkit-js with LangGraph Agents? | 2 | So OpenAI has a bunch of examples of using their chatkit-js with their AgentsSDK. I wanted to use their chatkit-js UI but use a LangGraph agent with my local LLM to get the chat responses. Has anyone tried doing that? Or is there a nicer way of building chat interfaces? I don't want to go the Langchain Agent UI route i... | 2025-10-09T06:04:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o1yc72/chatkitjs_with_langgraph_agents/ | LiquidGunay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1yc72 | false | null | t3_1o1yc72 | /r/LocalLLaMA/comments/1o1yc72/chatkitjs_with_langgraph_agents/ | false | false | self | 2 | null |
I've been working on a novel neural network architecture combining HRM with the long-term memory of google Titans! I need help training tho | 25 | Hey everyone! This is my first post here, so I'll cut right to the chase.
A few months ago, shortly after HRM was first announced, I had an idea: "What if you could combine the reasoning capabilities of HRM with the long-term memory of Titans?" Well, fast-forward to today, and I have a working prototype architecture t... | 2025-10-09T05:46:58 | https://www.reddit.com/r/LocalLLaMA/comments/1o1y286/ive_been_working_on_a_novel_neural_network/ | PhysicsDisastrous462 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1y286 | false | null | t3_1o1y286 | /r/LocalLLaMA/comments/1o1y286/ive_been_working_on_a_novel_neural_network/ | false | false | self | 25 | null |
afsjsnekxms | 1 | [deleted] | 2025-10-09T05:44:57 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1o1y11p | false | null | t3_1o1y11p | /r/LocalLLaMA/comments/1o1y11p/afsjsnekxms/ | false | false | default | 1 | null | ||
Intel IPEX vs Pytorch XPU | 4 | Has anyone benchmarked these on Intel Arc GPUs? My question what is the difference between Pytorch XPU calls and Intel IPEX calls. I am struggling to understand where they sit respectfully. I mean does Pytorch XPU not already accelerate the inference? | 2025-10-09T05:33:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o1xun8/intel_ipex_vs_pytorch_xpu/ | lan1990 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1xun8 | false | null | t3_1o1xun8 | /r/LocalLLaMA/comments/1o1xun8/intel_ipex_vs_pytorch_xpu/ | false | false | self | 4 | null |
Small text to text model for RTX 3070? | 5 | I'm using Lm Studio to host a local server, I need a small model to generate text only, I would need to setup at maximum 220 characters on each reply. The more creative, the better. If it supports portuguese, it's perfect.
What is the best model I can use on LM studio to run that?
Thank you very much! | 2025-10-09T04:56:59 | https://www.reddit.com/r/LocalLLaMA/comments/1o1x82c/small_text_to_text_model_for_rtx_3070/ | eddie__b | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1x82c | false | null | t3_1o1x82c | /r/LocalLLaMA/comments/1o1x82c/small_text_to_text_model_for_rtx_3070/ | false | false | self | 5 | null |
Run Qwen3-VL-30B-A3B locally on macOS! | 28 | So far I didn't find any MLX or GGUF model released that worked with Macs, LM Studio or llama.cpp, so I fixed the basic transformers based example given to make it work with macOS and MPS acceleration.
The code bellow allows you to run the model locally on Macs and expose it as an Open AI compatible server so you ... | 2025-10-09T04:32:09 | https://www.reddit.com/r/LocalLLaMA/comments/1o1wsi8/run_qwen3vl30ba3b_locally_on_macos/ | TechnoFreakazoid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1wsi8 | false | null | t3_1o1wsi8 | /r/LocalLLaMA/comments/1o1wsi8/run_qwen3vl30ba3b_locally_on_macos/ | false | false | 28 | {'enabled': False, 'images': [{'id': 'rcGlszXx2uemqw7EFXRpNRQv_QRSWB3aKUyrnGrI2NM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/rcGlszXx2uemqw7EFXRpNRQv_QRSWB3aKUyrnGrI2NM.png?width=108&crop=smart&auto=webp&s=8760b9e966ffe278867478d8548a0b4410e297ed', 'width': 108}, {'height': 108, 'url': 'h... | |
fun fact, GLM publishes an api key inside its full-stack mode that's "GLM-AI" and actually routes requests correctly and unlimited... to GLM-4-Plus. Which is a model not avaliable in the model selector. | 6 | If anyone wanted unlimited usage... why not. Also, I vibecoded an application using this, and apparently this is valid. (not self promotion).
[https://preview-chat-0c9b3d98-f9b6-4587-a547-646d9bcc2ac1.space.z.ai/](https://preview-chat-0c9b3d98-f9b6-4587-a547-646d9bcc2ac1.space.z.ai/) | 2025-10-09T04:23:15 | https://www.reddit.com/r/LocalLLaMA/comments/1o1wmxz/fun_fact_glm_publishes_an_api_key_inside_its/ | Linkpharm2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1wmxz | false | null | t3_1o1wmxz | /r/LocalLLaMA/comments/1o1wmxz/fun_fact_glm_publishes_an_api_key_inside_its/ | false | false | self | 6 | null |
P102-100 on llama.cpp benchmarks. | 27 | For all the people that have been asking me to do some benchmarks on these cards using llama.cpp well, here you go. I still to this day do not regret spending 70 bucks for these two cards. I also would thank the people that explain to me how llama.cpp was better then ollama as this is very true. llama.cpp custom implem... | 2025-10-09T04:04:25 | https://www.reddit.com/r/LocalLLaMA/comments/1o1wb1p/p102100_on_llamacpp_benchmarks/ | Boricua-vet | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1wb1p | false | null | t3_1o1wb1p | /r/LocalLLaMA/comments/1o1wb1p/p102100_on_llamacpp_benchmarks/ | false | false | self | 27 | {'enabled': False, 'images': [{'id': '443rFFkPppzNDFe54hBc-foPeceRrzkFT7Y5MPcCR0Q', 'resolutions': [{'height': 50, 'url': 'https://external-preview.redd.it/443rFFkPppzNDFe54hBc-foPeceRrzkFT7Y5MPcCR0Q.jpeg?width=108&crop=smart&auto=webp&s=1cd95cc55e68809209a471cdd00f1a7d2786cd24', 'width': 108}, {'height': 100, 'url': '... |
Devstral's function calling message rule is insane and hard to understand | 0 | When constructing request messages, `devstral` forces to place `assistant` roled message after the `tool` roled message. However, my agent has not designed like that.
Anyway, to make my agent to work on the `devstral`, I wrapped the OpenAI request module to insert blank string content after the `tool` role. However, a... | 2025-10-09T03:44:54 | https://www.reddit.com/r/LocalLLaMA/comments/1o1vy4d/devstrals_function_calling_message_rule_is_insane/ | jhnam88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1vy4d | false | null | t3_1o1vy4d | /r/LocalLLaMA/comments/1o1vy4d/devstrals_function_calling_message_rule_is_insane/ | false | false | self | 0 | null |
Persona Drift: Why LLMs Forget Who They Are — and How We’re Fixing It | 0 | Hey everyone — I’m Sean, founder of **e**[**chomode.io**](https://github.com/Seanhong0818/Echo-Mode).
We’ve been building a tone-stability layer for LLMs to solve one of the most frustrating, under-discussed problems in AI agents: **persona drift**.
Here’s a quick breakdown of what it is, when it happens, and how we’... | 2025-10-09T03:36:33 | https://www.reddit.com/r/LocalLLaMA/comments/1o1vt99/persona_drift_why_llms_forget_who_they_are_and/ | Medium_Charity6146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1vt99 | false | null | t3_1o1vt99 | /r/LocalLLaMA/comments/1o1vt99/persona_drift_why_llms_forget_who_they_are_and/ | false | false | self | 0 | null |
Qwen3-VL MLX support incoming, thanks to Prince Canuma | 68 | https://huggingface.co/mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit
https://huggingface.co/mlx-community/Qwen3-VL-235B-A22B-Instruct-4bit | 2025-10-09T03:26:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o1vmby/qwen3vl_mlx_support_incoming_thanks_to_prince/ | No_Conversation9561 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1vmby | false | null | t3_1o1vmby | /r/LocalLLaMA/comments/1o1vmby/qwen3vl_mlx_support_incoming_thanks_to_prince/ | false | false | self | 68 | {'enabled': False, 'images': [{'id': 'Dvph43KKs5p4S-PyVjVXVGvU2jLw-_nJIJIKiiGmftI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Dvph43KKs5p4S-PyVjVXVGvU2jLw-_nJIJIKiiGmftI.png?width=108&crop=smart&auto=webp&s=f2e5241f8ca96819484ab11227c6c070fd92a20c', 'width': 108}, {'height': 116, 'url': 'h... |
Pdf | 0 | 2025-10-09T03:08:25 | https://www.reddit.com/r/LocalLLaMA/comments/1o1va37/pdf/ | Suspicious-Job714 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1va37 | false | null | t3_1o1va37 | /r/LocalLLaMA/comments/1o1va37/pdf/ | false | false | 0 | null | ||
Any VL model with size between qwen 30b a 3 b and qwen 235b? | 2 | I have 80GB of VRAM, it can do larger than 30b but not enough for 235B, is there any vision lsnguage models that I can max the VRAM? | 2025-10-09T02:58:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o1v2sa/any_vl_model_with_size_between_qwen_30b_a_3_b_and/ | Striking-Warning9533 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1v2sa | false | null | t3_1o1v2sa | /r/LocalLLaMA/comments/1o1v2sa/any_vl_model_with_size_between_qwen_30b_a_3_b_and/ | false | false | self | 2 | null |
What practical large models can the AI MAX 395 deploy, and where exactly can they be used? | 1 | Before discussing the ROCm ecosystem for the AI MAX 395, we must acknowledge that support for this APU is far from ideal. To date, only llama.cpp and its derivative applications (such as Ollama) offer stable support for this APU. As part of the AMD family, the AI MAX 395—despite not belonging to the Ryzen series—ha... | 2025-10-09T02:23:14 | https://www.reddit.com/r/LocalLLaMA/comments/1o1udni/what_practical_large_models_can_the_ai_max_395/ | Capable_Trash2065 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1udni | false | null | t3_1o1udni | /r/LocalLLaMA/comments/1o1udni/what_practical_large_models_can_the_ai_max_395/ | false | false | self | 1 | null |
A CLI to scrape pages for agents by piggybacking on your browser fingerprint | 15 | I keep hitting a wall with bot detection when trying to get live web data for agents.
So I built [a CLI](https://github.com/8ta4/see) that tells a companion extension to fetch a page. The idea was to control my day-to-day browser to piggyback on its static fingerprint.
This isn't for serious scraping. Forget resident... | 2025-10-09T02:17:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o1u9ia/a_cli_to_scrape_pages_for_agents_by_piggybacking/ | 8ta4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1u9ia | false | null | t3_1o1u9ia | /r/LocalLLaMA/comments/1o1u9ia/a_cli_to_scrape_pages_for_agents_by_piggybacking/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': '-WI2Qo73ogY9S2s2USBowbLE0ktOHpe0pMqz99lVe5k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-WI2Qo73ogY9S2s2USBowbLE0ktOHpe0pMqz99lVe5k.png?width=108&crop=smart&auto=webp&s=1372bb7b728b53d522b0b07d31efa5f6d37292c1', 'width': 108}, {'height': 108, 'url': 'h... |
Built a 1288x RTFx Parakeet Speech-to-Text server... Enjoy! | 14 | Needed to do a little mass-transcription so I hacked up a batching fastAPI Parakeet server and pushed it to the limit. Under ideal circumstances it manages up to 1,288x realtime on a 4090. It's using Parakeet 0.2 so it's English-only (feel free to hack together a 0.3 version if you need other languages, but note that y... | 2025-10-09T01:51:43 | https://github.com/Deveraux-Parker/Nvidia_parakeet-tdt-0.6b-v2-FAST-BATCHING-API-1200x-RTFx/tree/main | teachersecret | github.com | 1970-01-01T00:00:00 | 0 | {} | 1o1tqbr | false | null | t3_1o1tqbr | /r/LocalLLaMA/comments/1o1tqbr/built_a_1288x_rtfx_parakeet_speechtotext_server/ | false | false | default | 14 | null |
I adapted a psychometric theory to show that AI ability architecture makes AGI impossible regardless of scale, and how to measure AI ability for 1/100 to 1/1000 the price of current benchmarks | 0 | Hi r/localllama,
Recently, I noticed that the probability of correct solution of a problem in LLMs is proportional to how common this problem is for humans - all LLMs are more likely to solve more common problems than rare problems. Actual difficulty of a problem for humans matters less than its rarity - there are rar... | 2025-10-09T01:43:40 | https://www.reddit.com/r/LocalLLaMA/comments/1o1tkck/i_adapted_a_psychometric_theory_to_show_that_ai/ | Massive-Shift6641 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1tkck | false | null | t3_1o1tkck | /r/LocalLLaMA/comments/1o1tkck/i_adapted_a_psychometric_theory_to_show_that_ai/ | false | false | self | 0 | null |
Extracting data from consumer product images | 1 | Hey everyone
I’m working on a project where I need to **extract product information from consumer goods** (name, weight, brand, flavor, etc.) **from real-world photos**, not scans.
The images come with several challenges:
* **angle variations**,
* **light reflections and glare**,
* **curved or partially visible tex... | 2025-10-09T01:37:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o1tfyi/extracting_data_from_consumer_product_images/ | kmuentez | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1tfyi | false | null | t3_1o1tfyi | /r/LocalLLaMA/comments/1o1tfyi/extracting_data_from_consumer_product_images/ | false | false | self | 1 | null |
Ненависть к character Ai и альтернативы character Ai | 1 | [removed] | 2025-10-09T01:34:26 | https://www.reddit.com/r/LocalLLaMA/comments/1o1tdmq/ненависть_к_character_ai_и_альтернативы_character/ | kirillOS238 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o1tdmq | false | null | t3_1o1tdmq | /r/LocalLLaMA/comments/1o1tdmq/ненависть_к_character_ai_и_альтернативы_character/ | 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.