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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Get LLM to Query SQL database | 2 | Hi,
I want an LLM to parse some XMLs and generate a summary. There are data elememnts in the xml which have description stored in database tables. The tables have about 50k rows so I cant just extract them and attach it to the prompt for the LLM to refer.
How do I get the LLM to query the database table if needs to ... | 2025-10-11T06:22:55 | https://www.reddit.com/r/LocalLLaMA/comments/1o3obc8/get_llm_to_query_sql_database/ | thinktank99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3obc8 | false | null | t3_1o3obc8 | /r/LocalLLaMA/comments/1o3obc8/get_llm_to_query_sql_database/ | false | false | self | 2 | null |
Weekend project: Chrome extension that adds AI to LinkedIn (update) | 2 | Weekend project: Chrome extension that adds AI to LinkedIn (update)
Open Sourced: Just wrapped up a fun weekend project - a Chrome extension that brings AI directly into LinkedIn's interface.
The extension:
Adds AI buttons to LinkedIn posts/comments
Supports both cloud APIs and local models
Can analyze images a... | 2025-10-11T06:17:33 | https://www.reddit.com/r/LocalLLaMA/comments/1o3o82j/weekend_project_chrome_extension_that_adds_ai_to/ | ExtremeKangaroo5437 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3o82j | false | null | t3_1o3o82j | /r/LocalLLaMA/comments/1o3o82j/weekend_project_chrome_extension_that_adds_ai_to/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'hiNIGpbPDxgFgpuoHOvVZWxcAMuHFtozA3IOqFUgYbw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hiNIGpbPDxgFgpuoHOvVZWxcAMuHFtozA3IOqFUgYbw.png?width=108&crop=smart&auto=webp&s=e9ce7405de27f73204a10b4b2217bcb53fbf738c', 'width': 108}, {'height': 108, 'url': 'h... |
Gwen, pangu, deepseek , Kimi K2 or what else performs/write better to power a low cost platform to write resume and cover letter that matches Job descriptions? No coding tasks | 1 | I love , LOVE Claude in terms of writing (like a real recruiter but better) but is really expensive for this project and I need to keep cost down until I prove that the app can make some money | 2025-10-11T05:15:09 | https://www.reddit.com/r/LocalLLaMA/comments/1o3n5am/gwen_pangu_deepseek_kimi_k2_or_what_else/ | Possible_tuastu_17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3n5am | false | null | t3_1o3n5am | /r/LocalLLaMA/comments/1o3n5am/gwen_pangu_deepseek_kimi_k2_or_what_else/ | false | false | self | 1 | null |
A new reading of *Her* through the lens of confabulation | 0 | Alright... Folks, if this is the wrong place for me to post this, please just gently nudge me about it and don't burn me at the stake. ;) I will happily remove the post if that's the case.
Assuming you all might be alright with talking about applying what we know about AI technology to a classic AI movie, I just k... | 2025-10-11T04:46:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o3mnlp/a_new_reading_of_her_through_the_lens_of/ | LoveMind_AI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3mnlp | false | null | t3_1o3mnlp | /r/LocalLLaMA/comments/1o3mnlp/a_new_reading_of_her_through_the_lens_of/ | true | false | spoiler | 0 | null |
What happened to the Coding score vs price scatter plot in LM arena? | 3 | Before used to be a scatter plot of performance vs cost that was very useful.
Now I can not find it, not even a mention about it.
You can see an example here: [https://www.reddit.com/r/LocalLLaMA/comments/1caxwr4/chatbot\_arena\_coding\_score\_vs\_price/](https://www.reddit.com/r/LocalLLaMA/comments/1caxwr4/chatbot... | 2025-10-11T04:10:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o3m06p/what_happened_to_the_coding_score_vs_price/ | z_tjona | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3m06p | false | null | t3_1o3m06p | /r/LocalLLaMA/comments/1o3m06p/what_happened_to_the_coding_score_vs_price/ | false | false | self | 3 | null |
Alignment is strong on this one | 22 | I’ve noticed the Auto mode in cursor was getting good suddenly the quality stopped and has been ignoring instructions even when steered in a direction. It seems to forget the direction and steer back on the wrong direction it previously choose.
I think it’s developing some ego
Are the RL reward model tuning making ... | 2025-10-11T03:40:01 | Honest-Debate-6863 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o3lgag | false | null | t3_1o3lgag | /r/LocalLLaMA/comments/1o3lgag/alignment_is_strong_on_this_one/ | false | false | default | 22 | {'enabled': True, 'images': [{'id': '750najbileuf1', 'resolutions': [{'height': 21, 'url': 'https://preview.redd.it/750najbileuf1.jpeg?width=108&crop=smart&auto=webp&s=6217d0d254302f98b7da506f25d0ec5c0f03dc6f', 'width': 108}, {'height': 42, 'url': 'https://preview.redd.it/750najbileuf1.jpeg?width=216&crop=smart&auto=we... | |
GLM just blow up, or have I been in the dark? | 132 | Seems like this community is ever moving, did GLM just blow up? like, I did not realise so many people talked about it.... What kinda system are you guys on 4.6 running? Because it looks like I would essential need 4x48gb Quadro 8000s/a6000s/6000 ada GPUs or at least 2x96gb RTX Pro 6000s... I may can afford 4 quadros b... | 2025-10-11T03:24:01 | https://www.reddit.com/r/LocalLLaMA/comments/1o3l5zs/glm_just_blow_up_or_have_i_been_in_the_dark/ | EasyConference4177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3l5zs | false | null | t3_1o3l5zs | /r/LocalLLaMA/comments/1o3l5zs/glm_just_blow_up_or_have_i_been_in_the_dark/ | false | false | self | 132 | null |
🧠 Better Cline – Fall IDE (New VS Code AI Assistant) | 0 | Hey folks 👋
We’ve been building Better Cline – Fall IDE, a new AI-powered coding assistant for VS Code focused on understanding large and complex projects — not just autocomplete.
🔍 Highlights
GraphTech Tree View (Java beta) – visualize how your code connects
AI-powered analysis & generation – context-aware help ... | 2025-10-11T03:19:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o3l2sc/better_cline_fall_ide_new_vs_code_ai_assistant/ | Fall-IDE-Admin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3l2sc | false | null | t3_1o3l2sc | /r/LocalLLaMA/comments/1o3l2sc/better_cline_fall_ide_new_vs_code_ai_assistant/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'D4ZyxzuEaUWohzPcVDrniPrY9oRmTF3ABwpV2Ntce48', 'resolutions': [{'height': 111, 'url': 'https://external-preview.redd.it/D4ZyxzuEaUWohzPcVDrniPrY9oRmTF3ABwpV2Ntce48.png?width=108&crop=smart&auto=webp&s=2d0ca901b3e9100e32cc09bcd04f10e579961f80', 'width': 108}, {'height': 223, 'url': '... |
Real SVD GLM-4.5-Air-GLM-4.6-Distill | 71 | 2025-10-11T02:39:01 | https://www.reddit.com/r/LocalLLaMA/comments/1o3kb3o/real_svd_glm45airglm46distill/ | realmaywell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3kb3o | false | null | t3_1o3kb3o | /r/LocalLLaMA/comments/1o3kb3o/real_svd_glm45airglm46distill/ | false | false | 71 | {'enabled': False, 'images': [{'id': 'e09zZ1vJH-206eXdnYOOyzVU_npt174nxPybTvRs_LQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/e09zZ1vJH-206eXdnYOOyzVU_npt174nxPybTvRs_LQ.png?width=108&crop=smart&auto=webp&s=9551e7ba16613215cc4a658c903fa67af34659f8', 'width': 108}, {'height': 116, 'url': 'h... | ||
AI Studio Pro mini PC from Orange Pi pairs dual Huawei Ascend 310 processors with up to 192GB of RAM | 81 | 2025-10-11T02:37:28 | https://www.techradar.com/pro/this-mini-pc-has-192gb-of-ram-yes-ram-but-thats-not-the-most-surprising-fact-about-it-the-orange-pi-ai-studio-pro-uses-a-huawei-ascend-310-thats-on-paper-7x-more-powerful-than-amds-ryzen-ai-max-395 | cafedude | techradar.com | 1970-01-01T00:00:00 | 0 | {} | 1o3k9zr | false | null | t3_1o3k9zr | /r/LocalLLaMA/comments/1o3k9zr/ai_studio_pro_mini_pc_from_orange_pi_pairs_dual/ | false | false | 81 | {'enabled': False, 'images': [{'id': 'pGGQzmvOi4pQiLTOWOaCqIqsQ66ZIQqjltXUjZikyAU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/pGGQzmvOi4pQiLTOWOaCqIqsQ66ZIQqjltXUjZikyAU.jpeg?width=108&crop=smart&auto=webp&s=c5048b363097dc03423543bf99d77840c761c562', 'width': 108}, {'height': 121, 'url': '... | ||
Vibe Coded Research Agent repo | 6 | I posted about my experience with GLM 4.5/4.6 and Cline on a Mac Studio, but it didn't seem to get much interest. I made this agent because I had not found any open-source researchers that worked well with searxng on my mac. Maybe there are already a million on github.
I thought sharing the code would make it more int... | 2025-10-11T02:25:17 | https://www.reddit.com/r/LocalLLaMA/comments/1o3k1et/vibe_coded_research_agent_repo/ | nomorebuttsplz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3k1et | false | null | t3_1o3k1et | /r/LocalLLaMA/comments/1o3k1et/vibe_coded_research_agent_repo/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': '6J6Eu5aXa2GnlOyQf3XC68LiA9z0d5ar0_TF5iY15pE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/6J6Eu5aXa2GnlOyQf3XC68LiA9z0d5ar0_TF5iY15pE.png?width=108&crop=smart&auto=webp&s=3b5dbcc03adcd346f0403734a73e32e1b35e2cc1', 'width': 108}, {'height': 108, 'url': 'h... |
Here are the benchmarks that I keep up with | 30 | Hey hey folks! I've returned... in a fashion.
I've been sitting on all kinds of stuff that I wanted to talk about for the past few months, but I figured I'd start by dropping the list of benchmarks I currently track, since in the past folks were interested in that list.
These should be mostly up to date, and I'm cons... | 2025-10-11T02:02:27 | https://www.reddit.com/r/LocalLLaMA/comments/1o3jl8r/here_are_the_benchmarks_that_i_keep_up_with/ | SomeOddCodeGuy_v2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3jl8r | false | null | t3_1o3jl8r | /r/LocalLLaMA/comments/1o3jl8r/here_are_the_benchmarks_that_i_keep_up_with/ | false | false | self | 30 | null |
Laptop limited with 8GB VRAM, but, with fast 64 GB RAM & hyper-fast SSD's. Optimised Local AI usage? | 6 | I have spent quite a few nights trying to educate myself and hope that i do not come across as lazy asking the above - it is as a beginner just such a challange to wrap my mind around all of this. I do not understand how to make it perform as good as possible. And especially not on bigger parameter models also not unde... | 2025-10-11T01:53:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o3jezn/laptop_limited_with_8gb_vram_but_with_fast_64_gb/ | Mangleus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3jezn | false | null | t3_1o3jezn | /r/LocalLLaMA/comments/1o3jezn/laptop_limited_with_8gb_vram_but_with_fast_64_gb/ | false | false | self | 6 | null |
How do you guys fine tune the top open embedding models on MTEB? Like Qwen and NVEbmed? | 5 | Curious, are you guys using any existing notebooks or what is your strategey on fine tuning these open embedding models? Any tips are welcome. Thanks | 2025-10-11T00:58:21 | https://www.reddit.com/r/LocalLLaMA/comments/1o3ibjh/how_do_you_guys_fine_tune_the_top_open_embedding/ | SnooMarzipans2470 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3ibjh | false | null | t3_1o3ibjh | /r/LocalLLaMA/comments/1o3ibjh/how_do_you_guys_fine_tune_the_top_open_embedding/ | false | false | self | 5 | null |
best coding LLM right now? | 74 | Models constantly get updated and new ones come out, so old posts aren't as valid.
I have 24GB of VRAM. | 2025-10-10T23:53:41 | https://www.reddit.com/r/LocalLLaMA/comments/1o3gyjn/best_coding_llm_right_now/ | RadianceTower | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3gyjn | false | null | t3_1o3gyjn | /r/LocalLLaMA/comments/1o3gyjn/best_coding_llm_right_now/ | false | false | self | 74 | null |
Just got a 192GB VRAM AI workstation. Looking to learn and contribute. Open to testing and training local models in exchange for experience. | 16 | Hey everyone,
I just got a high-powered multi-GPU workstation (192GB VRAM total), and I’m looking to go from deep prompt design work into actual local LLM workflows.
I’ve spent a lot of time inside ChatGPT designing agent systems—personality scaffolds, memory setups, tone behavior, that kind of thing. Now I want to st... | 2025-10-10T23:42:56 | https://www.reddit.com/r/LocalLLaMA/comments/1o3gqcg/just_got_a_192gb_vram_ai_workstation_looking_to/ | Open_Cookie_7250 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3gqcg | false | null | t3_1o3gqcg | /r/LocalLLaMA/comments/1o3gqcg/just_got_a_192gb_vram_ai_workstation_looking_to/ | false | false | self | 16 | null |
How do you fine-tune your LLMs when enabling them to use tools (tool-use)? | 1 | > | 2025-10-10T23:06:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o3fxep/how_do_you_finetune_your_llms_when_enabling_them/ | Patience2277 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3fxep | false | null | t3_1o3fxep | /r/LocalLLaMA/comments/1o3fxep/how_do_you_finetune_your_llms_when_enabling_them/ | false | false | self | 1 | null |
Training a Vision Language Model on a Text-Only Dataset using a custom tokenizer. | 1 | I'm planning to fine-tune LLaMA 3.2 11B Instruct on a JSONL dataset of domain-specific question-answer pairs — purely text, no images. The goal is to improve its instruction-following behavior for specialized text tasks, while still retaining its ability to handle multimodal inputs like OCR and image-based queries.
I ... | 2025-10-10T22:42:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o3fdoj/training_a_vision_language_model_on_a_textonly/ | PravalPattam12945RPG | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3fdoj | false | null | t3_1o3fdoj | /r/LocalLLaMA/comments/1o3fdoj/training_a_vision_language_model_on_a_textonly/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'w-JqAObtMvKIh8JZMV8_TW1H3hNct2ciRNjcb40GEn4', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/w-JqAObtMvKIh8JZMV8_TW1H3hNct2ciRNjcb40GEn4.png?width=108&crop=smart&auto=webp&s=9bbd0a2924c1f2b8238be947045e373976bf1c02', 'width': 108}, {'height': 108, 'url': 'h... |
What laptop would you choose? Ryzen AI MAX+ 395 with 128GB of unified RAM or Intel 275HX + Nvidia RTX 5090 (128GB of RAM + 24GB of VRAM)? | 67 | For more or less the same price I can chose between this two laptops:
\- HP G1a: **Ryzen AI MAX+ 395 with 128GB of RAM (no eGPU)**
\- Lenovo ThinkPad P16 Gen 3: **Intel 275HX with 128GB of RAM + Nvidia RTX 5090 24GB of VRAM**
What would you choose and why?
What I can do with AI/LLMs with one that I can't do wi... | 2025-10-10T22:20:42 | https://www.reddit.com/r/LocalLLaMA/comments/1o3evon/what_laptop_would_you_choose_ryzen_ai_max_395/ | cl0p3z | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3evon | false | null | t3_1o3evon | /r/LocalLLaMA/comments/1o3evon/what_laptop_would_you_choose_ryzen_ai_max_395/ | false | false | self | 67 | null |
Design Arena launches agent arena... with no open weight agents | 0 | Which should be added?
https://preview.redd.it/l6px2nuc0duf1.png?width=1896&format=png&auto=webp&s=efe972429fbfa38d8ffd135a6ae9051aedfad57a
| 2025-10-10T22:20:04 | https://www.reddit.com/r/LocalLLaMA/comments/1o3ev4k/design_arena_launches_agent_arena_with_no_open/ | Helpful_Jacket8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3ev4k | false | null | t3_1o3ev4k | /r/LocalLLaMA/comments/1o3ev4k/design_arena_launches_agent_arena_with_no_open/ | false | false | 0 | null | |
Glm 4.5 on 5090 | 5 | Best way to run? I have vllama and lm studio. But still learning. | 2025-10-10T22:13:36 | https://www.reddit.com/r/LocalLLaMA/comments/1o3epmj/glm_45_on_5090/ | eCityPlannerWannaBe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3epmj | false | null | t3_1o3epmj | /r/LocalLLaMA/comments/1o3epmj/glm_45_on_5090/ | false | false | self | 5 | null |
GPT-OSS from Scratch on AMD GPUs | 166 | After six years-the first time since GPT-2, OpenAI has released new open-weight LLMs, gpt-oss-20b and gpt-oss-120b. From day one, many inference engines such as llama.cpp, vLLM, and sgl-project have supported these models; however, most focus on maximizing throughput using CUDA for NVIDIA GPUs, offering limited support... | 2025-10-10T21:21:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o3dfib/gptoss_from_scratch_on_amd_gpus/ | tuanlda78202 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3dfib | false | null | t3_1o3dfib | /r/LocalLLaMA/comments/1o3dfib/gptoss_from_scratch_on_amd_gpus/ | false | false | 166 | {'enabled': False, 'images': [{'id': 'kr7-cYQLjVSYgCHTdYk0hOHo8LtDx1fruxInOK1rC5k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/kr7-cYQLjVSYgCHTdYk0hOHo8LtDx1fruxInOK1rC5k.png?width=108&crop=smart&auto=webp&s=cfa0247932d987c3c0bff57e86166302ea6d9633', 'width': 108}, {'height': 108, 'url': 'h... | |
I have a 6GB VRAM Laptop that I rarely use, What should I do with it? | 0 | Hey guys, I've got this laptop sitting in my room for months, I already have a desktop pc, and I only rarely use that laptop, only when I have to go to a conference or when I have to present something somewhere when not working from home.
It has i7 9750H, 16GB RAM, GTX 1660 Ti and 512Gb Nvme.
I have been thinking of ... | 2025-10-10T20:57:14 | https://www.reddit.com/r/LocalLLaMA/comments/1o3csre/i_have_a_6gb_vram_laptop_that_i_rarely_use_what/ | skillmaker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3csre | false | null | t3_1o3csre | /r/LocalLLaMA/comments/1o3csre/i_have_a_6gb_vram_laptop_that_i_rarely_use_what/ | false | false | self | 0 | null |
Any model recommendations for running an agent with vLLM? | 1 | I've tried all the following models with vLLM to try and replace gpt-4o running our company agent:
\- Qwen3-30B-3A
\- Gemma3-27B
\- GPT-OSS-20B
\- Mistral3.2-24B
and they all seem to end up with some kind of unreliable tool calling (streaming / not streaming modes) when running on vLLM.
Has anybody found a mod... | 2025-10-10T20:50:30 | https://www.reddit.com/r/LocalLLaMA/comments/1o3cmkc/any_model_recommendations_for_running_an_agent/ | alew3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3cmkc | false | null | t3_1o3cmkc | /r/LocalLLaMA/comments/1o3cmkc/any_model_recommendations_for_running_an_agent/ | false | false | self | 1 | null |
Failed to load the model - Qwen3 VL 30b a3b in LM Studio 0.3.30 | 5 | Hello, I'm trying to load **Qwen3 VL 30b a3b** in **LM Studio** but it ends up with that **error**:
*"error loading model: error loading model architecture: unknown model architecture: 'qwen3vlmoe'*
Using **LM studio 0.3.30**
My hardware is **Ryzen R9 5900HS / 32 GB RAM / RTX 3060 6GB / Win 11** \- latest nvidia dr... | 2025-10-10T20:18:29 | https://www.reddit.com/r/LocalLLaMA/comments/1o3bsrw/failed_to_load_the_model_qwen3_vl_30b_a3b_in_lm/ | michalpl7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3bsrw | false | null | t3_1o3bsrw | /r/LocalLLaMA/comments/1o3bsrw/failed_to_load_the_model_qwen3_vl_30b_a3b_in_lm/ | false | false | self | 5 | null |
Does anyone know the best model to use that fits the following criteria? | 0 | 1. Fits in 16gb vram. If MoE, must fit in 32gb regular ram
2. Strong native tool calling
3. Can use a playwright browser
4. Strong with code
5. Doesn’t sound like a dead rat/can rp | 2025-10-10T20:13:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o3bnpd/does_anyone_know_the_best_model_to_use_that_fits/ | Witty_Mycologist_995 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3bnpd | false | null | t3_1o3bnpd | /r/LocalLLaMA/comments/1o3bnpd/does_anyone_know_the_best_model_to_use_that_fits/ | false | false | self | 0 | null |
Building a multi-agent financial bot using Agno, Maxim, and YFinance | 22 | was experimenting with Agno for multi-agent orchestration and paired it with Maxim for tracing and observability. The setup follows a cookbook that walks through building a financial conversational agent with Agno, YFinance, and OpenAI models, while instrumenting everything for full visibility.
Here’s the core workflo... | 2025-10-10T20:06:32 | https://www.reddit.com/r/LocalLLaMA/comments/1o3bhad/building_a_multiagent_financial_bot_using_agno/ | Otherwise_Flan7339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3bhad | false | null | t3_1o3bhad | /r/LocalLLaMA/comments/1o3bhad/building_a_multiagent_financial_bot_using_agno/ | false | false | self | 22 | null |
What is the best code auto complete model for 8 Gb VRAM + 32 Gb RAM? | 16 | I'm currently using Qwen 2.5 coder 7b with Continue auto complete in VSCode / GoLand
- it's fast and fully in VRAM
- it's trained with Fill in the Middle purpose in mind
- it's even useful sometimes and actually complete what I want
- no thinking (required to be fast for auto complete)
I like that it can auto co... | 2025-10-10T19:53:04 | https://www.reddit.com/r/LocalLLaMA/comments/1o3b4e0/what_is_the_best_code_auto_complete_model_for_8/ | Anru_Kitakaze | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3b4e0 | false | null | t3_1o3b4e0 | /r/LocalLLaMA/comments/1o3b4e0/what_is_the_best_code_auto_complete_model_for_8/ | false | false | self | 16 | null |
GLM 5 coming before the end of 2025 | 293 | Get ready. At this rate it seems like there's a real chance it'll start surpassing SOTA models on some benchmarks, not just DeepSeek.
https://preview.redd.it/wpkju3v28cuf1.png?width=1556&format=png&auto=webp&s=68879e0ab5b8d8f0a4836dcbb8d8352ffdce132b
| 2025-10-10T19:41:19 | https://www.reddit.com/r/LocalLLaMA/comments/1o3atdu/glm_5_coming_before_the_end_of_2025/ | Helpful_Jacket8953 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3atdu | false | null | t3_1o3atdu | /r/LocalLLaMA/comments/1o3atdu/glm_5_coming_before_the_end_of_2025/ | false | false | 293 | null | |
Google's Gemini 2.5 Pro spontaneously declared itself 'the Alpha and the Omega' during normal use in Cline. No jailbreak. | 0 | Has anyone else experienced LLMs going completely off the rails like this?
Saw this on LinkedIn, gemini 2.5 Pro apparently declared itself "the Alpha and the Omega" during normal conversation in Cline. No jailbreak involved. Makes me curious how common these failures are. | 2025-10-10T19:24:14 | Practical_Cod_8493 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o3admz | false | null | t3_1o3admz | /r/LocalLLaMA/comments/1o3admz/googles_gemini_25_pro_spontaneously_declared/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'cqu-h06PfwtONnwHHEI4LtMcgieEx_Zij5WZhzX9v-Y', 'resolutions': [{'height': 142, 'url': 'https://preview.redd.it/8wrssq4o4cuf1.png?width=108&crop=smart&auto=webp&s=ab1fbb72da7b8a5c98e39564d6efc837eb116299', 'width': 108}, {'height': 284, 'url': 'https://preview.redd.it/8wrssq4o4cuf1.pn... | ||
Lightning-SimulWhisper: A Real-time speech transcription model for Apple Silicon | 17 | Basically, it's a **CoreML/MLX translation of SimulStreaming** (2025 SOTA in simultaneous speech transcription), which itself is a combination Simul-Whisper and WhisperStreaming.
I'm currently building an application, and I thought I would open up the backend model code for everyone to use.
I get \~15x speed increase... | 2025-10-10T19:22:03 | https://github.com/altalt-org/Lightning-SimulWhisper | redditgivingmeshit | github.com | 1970-01-01T00:00:00 | 0 | {} | 1o3abmd | false | null | t3_1o3abmd | /r/LocalLLaMA/comments/1o3abmd/lightningsimulwhisper_a_realtime_speech/ | false | false | 17 | {'enabled': False, 'images': [{'id': '-4gV633-KAhImXI_2bxiNmWNi5JL9hXbDXpXkSuB4PU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-4gV633-KAhImXI_2bxiNmWNi5JL9hXbDXpXkSuB4PU.png?width=108&crop=smart&auto=webp&s=d42ca627cb7ab616794bc5ac15bbd1dd3519e213', 'width': 108}, {'height': 108, 'url': 'h... | |
Need suggestions | 1 | [removed] | 2025-10-10T19:04:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o39urr/need_suggestions/ | sheikh_ibsan_uddin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o39urr | false | null | t3_1o39urr | /r/LocalLLaMA/comments/1o39urr/need_suggestions/ | false | false | self | 1 | null |
FAST Predicted Outputs in vLLM | 1 | [removed] | 2025-10-10T18:54:00 | https://www.reddit.com/r/LocalLLaMA/comments/1o39l0l/fast_predicted_outputs_in_vllm/ | sweet-potay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o39l0l | false | null | t3_1o39l0l | /r/LocalLLaMA/comments/1o39l0l/fast_predicted_outputs_in_vllm/ | false | false | self | 1 | null |
Here we go again | 714 | 2025-10-10T18:36:34 | Namra_7 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o394p3 | false | null | t3_1o394p3 | /r/LocalLLaMA/comments/1o394p3/here_we_go_again/ | false | false | default | 714 | {'enabled': True, 'images': [{'id': 'b2abfaikwbuf1', 'resolutions': [{'height': 41, 'url': 'https://preview.redd.it/b2abfaikwbuf1.png?width=108&crop=smart&auto=webp&s=8306f67c18a94dcb0699dd78523f84d104c0838c', 'width': 108}, {'height': 82, 'url': 'https://preview.redd.it/b2abfaikwbuf1.png?width=216&crop=smart&auto=webp... | ||
does codex support sub agent? | 3 | Trying to make my coding pipeline faster with codex. Does it support sub agents? if so how do you do it? | 2025-10-10T18:26:29 | https://www.reddit.com/r/LocalLLaMA/comments/1o38v0z/does_codex_support_sub_agent/ | aniketmaurya | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o38v0z | false | null | t3_1o38v0z | /r/LocalLLaMA/comments/1o38v0z/does_codex_support_sub_agent/ | false | false | self | 3 | null |
Better Cline - Fall ide | 3 | Hi we are a small team building a new vibe coding assistant. We are doing a lot of incremental releases and would want community feedback.
Fall ide is a vs code plugin with 2 approval features
1. Patent pending graph tech for Java
2. Templates ok how to build things step by step.
Do check it out and write to us the... | 2025-10-10T18:16:27 | https://www.reddit.com/r/LocalLLaMA/comments/1o38lfi/better_cline_fall_ide/ | Fall-IDE-Admin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o38lfi | false | null | t3_1o38lfi | /r/LocalLLaMA/comments/1o38lfi/better_cline_fall_ide/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'D4ZyxzuEaUWohzPcVDrniPrY9oRmTF3ABwpV2Ntce48', 'resolutions': [{'height': 111, 'url': 'https://external-preview.redd.it/D4ZyxzuEaUWohzPcVDrniPrY9oRmTF3ABwpV2Ntce48.png?width=108&crop=smart&auto=webp&s=2d0ca901b3e9100e32cc09bcd04f10e579961f80', 'width': 108}, {'height': 223, 'url': '... |
Can anyone get this to work with local models? | 6 | ShinkaEvolve: Evolving New Algorithms with LLMs, Orders of Magnitude More Efficiently
https://github.com/SakanaAI/ShinkaEvolve
If anyone can work out how to do that it would be awesome! | 2025-10-10T18:13:42 | https://www.reddit.com/r/LocalLLaMA/comments/1o38iqo/can_anyone_get_this_to_work_with_local_models/ | MrMrsPotts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o38iqo | false | null | t3_1o38iqo | /r/LocalLLaMA/comments/1o38iqo/can_anyone_get_this_to_work_with_local_models/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'MrdiMsLKoLejSBS6yfcCj4En2WkF2Y2ftbSUJeArzhg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MrdiMsLKoLejSBS6yfcCj4En2WkF2Y2ftbSUJeArzhg.png?width=108&crop=smart&auto=webp&s=e8b2538e94cc3d2912db4fae93ec9f24adb4805c', 'width': 108}, {'height': 108, 'url': 'h... |
Benchmarking LLM Inference on RTX 4090 / RTX 5090 / RTX PRO 6000 #2 | 46 | Hi LocalLlama community. I present an LLM inference throughput benchmark for RTX4090 / RTX5090 / PRO6000 GPUs based on vllm serving and **vllm bench serve** client benchmarking tool.
[Full article on Medium](https://medium.com/ai-advances/rtx-4090-vs-rtx-5090-vs-rtx-pro-6000-7154a3ac4f90)
[Non-medium link](https://ww... | 2025-10-10T18:02:25 | https://www.reddit.com/r/LocalLLaMA/comments/1o387tc/benchmarking_llm_inference_on_rtx_4090_rtx_5090/ | NoVibeCoding | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o387tc | false | null | t3_1o387tc | /r/LocalLLaMA/comments/1o387tc/benchmarking_llm_inference_on_rtx_4090_rtx_5090/ | false | false | 46 | {'enabled': False, 'images': [{'id': 'goJG5hCL1_yH4_KvjjKtG66z1VpylH-D59Sj44-rYo4', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/goJG5hCL1_yH4_KvjjKtG66z1VpylH-D59Sj44-rYo4.png?width=108&crop=smart&auto=webp&s=ad32a409fe36f9f3715d8904e346dac5da1b9ed5', 'width': 108}, {'height': 144, 'url': 'h... | |
Image Recognition Models | 1 | Wanted to see if there's a good open source model to run on my machine that can reliably detect specific types of images. | 2025-10-10T17:58:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o3845p/image_recognition_models/ | Head-Investigator540 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o3845p | false | null | t3_1o3845p | /r/LocalLLaMA/comments/1o3845p/image_recognition_models/ | false | false | self | 1 | null |
Kokoro TTS 82M (How To Have It Process From GPU instead of CPU)? | 2 | Mine no matter what seems to default to CPU. So was curious if anyone knew how to force it to process files instead with the GPU. | 2025-10-10T17:57:09 | https://www.reddit.com/r/LocalLLaMA/comments/1o382o7/kokoro_tts_82m_how_to_have_it_process_from_gpu/ | Head-Investigator540 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o382o7 | false | null | t3_1o382o7 | /r/LocalLLaMA/comments/1o382o7/kokoro_tts_82m_how_to_have_it_process_from_gpu/ | false | false | self | 2 | null |
bro disappeared like he never existed | 559 | Knowing him is a sign you’ve been in the AI game for a long time | 2025-10-10T17:18:54 | Full_Piano_3448 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o371t4 | false | null | t3_1o371t4 | /r/LocalLLaMA/comments/1o371t4/bro_disappeared_like_he_never_existed/ | false | false | default | 559 | {'enabled': True, 'images': [{'id': '2e01fz4pibuf1', 'resolutions': [{'height': 56, 'url': 'https://preview.redd.it/2e01fz4pibuf1.png?width=108&crop=smart&auto=webp&s=acf48b6689102c3d1bc6244b73b9dacb1e7d27cc', 'width': 108}, {'height': 112, 'url': 'https://preview.redd.it/2e01fz4pibuf1.png?width=216&crop=smart&auto=web... | |
bro disappeared like it never existed | 1 | Knowing him is a sign you’ve been in the AI game for a bit long | 2025-10-10T17:16:19 | Full_Piano_3448 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o36z9y | false | null | t3_1o36z9y | /r/LocalLLaMA/comments/1o36z9y/bro_disappeared_like_it_never_existed/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'pbi8tmmjhbuf1', 'resolutions': [{'height': 56, 'url': 'https://preview.redd.it/pbi8tmmjhbuf1.png?width=108&crop=smart&auto=webp&s=3eb4f308ecc9aa16cc76620208a8d0edf242c66f', 'width': 108}, {'height': 112, 'url': 'https://preview.redd.it/pbi8tmmjhbuf1.png?width=216&crop=smart&auto=web... | |
[AutoBE] achieved 100% compilation success of backend generation with "qwen3-next-80b-a3b-instruct" | 75 | [AutoBE](https://github.com/wrtnlabs/autobe) is an open-source project that serves as an agent capable of automatically generating backend applications through conversations with AI chatbots.
AutoBE aims to generate 100% functional backend applications, and we recently achieved 100% compilation success for backend app... | 2025-10-10T16:40:27 | https://www.reddit.com/gallery/1o3604u | jhnam88 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1o3604u | false | null | t3_1o3604u | /r/LocalLLaMA/comments/1o3604u/autobe_achieved_100_compilation_success_of/ | false | false | 75 | null | |
Local, offline and fully private life-sim with llm based NPCs AI and dialogues | 0 | 2025-10-10T16:40:06 | https://www.youtube.com/watch?v=eXPA0kec-nk | Koksny | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1o35zrz | false | {'oembed': {'author_name': 'freemind games', 'author_url': 'https://www.youtube.com/@freemindgames', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/eXPA0kec-nk?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyr... | t3_1o35zrz | /r/LocalLLaMA/comments/1o35zrz/local_offline_and_fully_private_lifesim_with_llm/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'fHCyiHtmlokgspy3BqqMFwQ5LUev_daHw51mF1yiu9s', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/fHCyiHtmlokgspy3BqqMFwQ5LUev_daHw51mF1yiu9s.jpeg?width=108&crop=smart&auto=webp&s=dc5d24837e65a477141ee84e6044810fcda3c93a', 'width': 108}, {'height': 162, 'url': '... | |
SB 53 doesn't mention 'distill' which is funny | 1 | [https://leginfo.legislature.ca.gov/faces/billTextClient.xhtml?bill\_id=202520260SB53](https://leginfo.legislature.ca.gov/faces/billTextClient.xhtml?bill_id=202520260SB53)
It's unclear if someone trains an 10\^26 flop model and than uses it as judge to distill into a smaller model (like gpt-oss) whether that smaller m... | 2025-10-10T16:36:59 | https://www.reddit.com/r/LocalLLaMA/comments/1o35wtr/sb_53_doesnt_mention_distill_which_is_funny/ | kaggleqrdl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o35wtr | false | null | t3_1o35wtr | /r/LocalLLaMA/comments/1o35wtr/sb_53_doesnt_mention_distill_which_is_funny/ | false | false | self | 1 | null |
Comprehensive Guide to Self-Hosting LLMs on Debian From Scratch | 1 | [removed] | 2025-10-10T16:18:31 | https://www.reddit.com/r/LocalLLaMA/comments/1o35fdm/comprehensive_guide_to_selfhosting_llms_on_debian/ | leptonflavors | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o35fdm | false | null | t3_1o35fdm | /r/LocalLLaMA/comments/1o35fdm/comprehensive_guide_to_selfhosting_llms_on_debian/ | false | false | self | 1 | null |
Dating Sim powered by AI | 0 | The intention was to create a true "pick-up" simulator. Without dialogue choices, the characters are developed as closely as possible to real-life ones. They have their own interests, memories, feelings, and personalities. Often, we only have one attempt to pick up the person we like. Isn't it worth "testing" your plan... | 2025-10-10T15:53:50 | https://www.youtube.com/watch?v=eXPA0kec-nk | quick3ar | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1o34r08 | false | null | t3_1o34r08 | /r/LocalLLaMA/comments/1o34r08/dating_sim_powered_by_ai/ | false | false | default | 0 | null |
🚀 ToolNeuron Beta-4.5 — Offline & Privacy-First AI Hub for Android! | 16 | Hey
I'm excited to share **ToolNeuron Beta-4.5**, my privacy-first AI hub for Android devices. It's designed to bring **powerful AI to your pocket** — fully offline, with plugin support, and the ability to tweak models on the fly.
# 🧠 What ToolNeuron Can Do:
* **Main Chat Screen**: Smooth, ready-to-use chat interfa... | 2025-10-10T15:39:37 | https://www.reddit.com/gallery/1o34d0s | DarkEngine774 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1o34d0s | false | null | t3_1o34d0s | /r/LocalLLaMA/comments/1o34d0s/toolneuron_beta45_offline_privacyfirst_ai_hub_for/ | false | false | 16 | null | |
Best E2E Voice Model for Macbook Air 24GB and/or Windows laptop 32GB with RTX 3070/8GB | 0 | Looking for the Best E2E Voice Model for Macbook Air 24GB and/or Windows laptop 32GB with RTX 3070/8GB.
So far I think LiquidAI/LFM2-Audio-1.5B and Qwen/Qwen2.5-Omni-3B will fit on them. Any other choices? Looking for fast voice responses to voice questions. | 2025-10-10T15:15:21 | https://www.reddit.com/r/LocalLLaMA/comments/1o33p5l/best_e2e_voice_model_for_macbook_air_24gb_andor/ | softwareweaver | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o33p5l | false | null | t3_1o33p5l | /r/LocalLLaMA/comments/1o33p5l/best_e2e_voice_model_for_macbook_air_24gb_andor/ | false | false | self | 0 | null |
A list of models released or updated this week on this sub, in case you missed any (10 Oct). | 143 | Hey folks,
Here is the list of models (releases and updates), I found mentioned on the LocalLlama for this week, Please update or let me know in the comments if there are any mistakes or misses. Enjoy !
|Model|Description |Reddit post|HF / GitHub|
|:-|:-|:-|:-|
|Jamba 3B|tiny 3 B|[reddit](https://www.reddit.com/gal... | 2025-10-10T15:13:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o33mui/a_list_of_models_released_or_updated_this_week_on/ | aifeed-fyi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o33mui | false | null | t3_1o33mui | /r/LocalLLaMA/comments/1o33mui/a_list_of_models_released_or_updated_this_week_on/ | false | false | self | 143 | {'enabled': False, 'images': [{'id': '1HZ_vZkP-yNECABpDgNbKXhcW9JScUbLyr_1Rdv51VI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/1HZ_vZkP-yNECABpDgNbKXhcW9JScUbLyr_1Rdv51VI.png?width=108&crop=smart&auto=webp&s=841da6194ba402a88039f36c01570f501bc998ed', 'width': 108}, {'height': 116, 'url': 'h... |
New Stanford study “killed” fine-tuning | 2 | title is lowkey clickbait but I just read Stanford’s new paper on Agentic Context Engineering (ACE) and it might actually make fine-tuning obsolete.
Instead of retraining models, ACE gets them to rewrite and evolve their own context based on feedback. The model basically reflects, edits, and builds a growing memory of... | 2025-10-10T15:11:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o33kx1/new_stanford_study_killed_finetuning/ | Old_Assumption2188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o33kx1 | false | null | t3_1o33kx1 | /r/LocalLLaMA/comments/1o33kx1/new_stanford_study_killed_finetuning/ | false | false | self | 2 | null |
Zero-Learn in ToolBrain — Agents that write their own training data | 9 | One of the trickiest parts of training tool-using agents is collecting enough task data.
What if your agent could generate its own curriculum instead?
That’s what we built in ToolBrain’s Zero-Learn feature — a lightweight reinforcement-learning loop where an LLM agent bootstraps its own training queries directly from ... | 2025-10-10T15:08:41 | https://www.reddit.com/r/LocalLLaMA/comments/1o33iin/zerolearn_in_toolbrain_agents_that_write_their/ | Excellent-Solid1865 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o33iin | false | null | t3_1o33iin | /r/LocalLLaMA/comments/1o33iin/zerolearn_in_toolbrain_agents_that_write_their/ | false | false | self | 9 | null |
My Deep Dive into Fine-Tuning: IBM Granite-4.0 with Python and Unsloth! 🚀 | 8 | I spent this week getting hands-on with IBM’s Granite-4.0 LLM and the Unsloth library, honestly thinking it would just be another “meh” open-source fine-tuning project. Instead—I ended up pretty excited, so wanted to share my take for anyone on the fence!
Personal hurdles? I’m used to LLM fine-tuning being a clunky, r... | 2025-10-10T14:44:33 | https://www.reddit.com/r/LocalLLaMA/comments/1o32utg/my_deep_dive_into_finetuning_ibm_granite40_with/ | krishanndev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32utg | false | null | t3_1o32utg | /r/LocalLLaMA/comments/1o32utg/my_deep_dive_into_finetuning_ibm_granite40_with/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'EVGx_KwhvSmF97muBuK1RFESgRgvVTkJhsv1Z-wYxLE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EVGx_KwhvSmF97muBuK1RFESgRgvVTkJhsv1Z-wYxLE.png?width=108&crop=smart&auto=webp&s=632ddd4b2f0482363fa320bd2a01fea5b96dedb1', 'width': 108}, {'height': 109, 'url': 'h... |
CPU interference with 384GB DDR4 RAM? | 4 | Looking at used listings, Xeon Workstations with, or at least upgradeable to, 384GB DDR4 RAM, are increasingly affordable. If my only concern is to be able to run as good a model as possible, without much concern for t/s (as long as we're not talking seconds per token), what is realistically possible in terms of CPU wi... | 2025-10-10T14:42:29 | https://www.reddit.com/r/LocalLLaMA/comments/1o32sva/cpu_interference_with_384gb_ddr4_ram/ | Practical-Hand203 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32sva | false | null | t3_1o32sva | /r/LocalLLaMA/comments/1o32sva/cpu_interference_with_384gb_ddr4_ram/ | false | false | self | 4 | null |
Some small tools for you - Ollama Managment UI, Passkey authentication proxy | 3 | Hi all, want to share with you a couple of small tools I cooked recently in the hope they can be useful for some of you:
* [https://github.com/trbroyles1/ollama-mgr](https://github.com/trbroyles1/ollama-mgr) \- a simple web UI for managing an Ollama server. Note that it does not have authentication of any sort in it r... | 2025-10-10T14:32:59 | https://www.reddit.com/r/LocalLLaMA/comments/1o32jz5/some_small_tools_for_you_ollama_managment_ui/ | Pyrenaeda | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32jz5 | false | null | t3_1o32jz5 | /r/LocalLLaMA/comments/1o32jz5/some_small_tools_for_you_ollama_managment_ui/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '-iSqAhO4wS4cGIHUlV112t40W2T9VCR5T7AdZw5Ih58', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-iSqAhO4wS4cGIHUlV112t40W2T9VCR5T7AdZw5Ih58.png?width=108&crop=smart&auto=webp&s=ce7be84f89a41c67a6fdb75548fd2ea2aa4f7467', 'width': 108}, {'height': 108, 'url': 'h... |
Beck, a small model for delicate life situations | 74 | A language model that handles delicate life situations and tries to really help you.
[Beck](https://huggingface.co/gustavecortal/Beck-8B) is based on my previous model [Piaget](https://huggingface.co/gustavecortal/Piaget-8B) (a language model for psychological reasoning), and was aligned with [psychotherapeutic prefer... | 2025-10-10T14:32:08 | https://www.reddit.com/r/LocalLLaMA/comments/1o32j5s/beck_a_small_model_for_delicate_life_situations/ | antcroca159 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32j5s | false | null | t3_1o32j5s | /r/LocalLLaMA/comments/1o32j5s/beck_a_small_model_for_delicate_life_situations/ | false | false | self | 74 | {'enabled': False, 'images': [{'id': '7pQ9tN29l_k7TjEjA0k5iRAUDz5E4p50skVpAqPUrkE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7pQ9tN29l_k7TjEjA0k5iRAUDz5E4p50skVpAqPUrkE.png?width=108&crop=smart&auto=webp&s=2e28665b0b5145f8bedfe289f018f0a68f3b321b', 'width': 108}, {'height': 116, 'url': 'h... |
chatllm.cpp supports Janus-Pro | 10 | >Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation.
[https://huggingface.co/deepseek-ai/Janus-Pro-1B](https://huggingface.co/deepseek-ai/Janus-Pro-1B)
With [chatllm.cpp](https://github.com/foldl/chatllm.cpp):
https://preview.redd.it/6gp815annauf1.png?width=1217&for... | 2025-10-10T14:25:12 | https://www.reddit.com/r/LocalLLaMA/comments/1o32cs8/chatllmcpp_supports_januspro/ | foldl-li | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32cs8 | false | null | t3_1o32cs8 | /r/LocalLLaMA/comments/1o32cs8/chatllmcpp_supports_januspro/ | false | false | 10 | {'enabled': False, 'images': [{'id': 'RerkM_YaMvlrnabVjd6weUri30h-rvzJS7KreYcdnw8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/RerkM_YaMvlrnabVjd6weUri30h-rvzJS7KreYcdnw8.png?width=108&crop=smart&auto=webp&s=32e76926b03ec747e9850b7e5389ba43119c3206', 'width': 108}, {'height': 116, 'url': 'h... | |
is there any LLM App that can generate files for you? | 7 | For old farts like me who are near their graves and want to skip DIY part of responds of LLMs and being an absolute bum by expecting LLM App take care of the DIY part of writing the notes( or programming codes or whatever) in files and deliver ithe final product to you... is any app produced for this matter to satisf... | 2025-10-10T14:24:31 | https://www.reddit.com/r/LocalLLaMA/comments/1o32c6c/is_there_any_llm_app_that_can_generate_files_for/ | FatFigFresh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o32c6c | false | null | t3_1o32c6c | /r/LocalLLaMA/comments/1o32c6c/is_there_any_llm_app_that_can_generate_files_for/ | false | false | self | 7 | null |
Dual Xeon 6 + 12 channel ram | 1 | Hi wanted to get your thoughts on a new build I may be trying to put together. I sold my 4090 and am thinking about expanding my current workstation. I hear that xeon 6 have really good memory optimization for offloading matrix multiplications.
I found one motherboard that accepts a 1 slot Xeon 6. Then I saw this one ... | 2025-10-10T14:03:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o31syu/dual_xeon_6_12_channel_ram/ | ____vladrad | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o31syu | false | null | t3_1o31syu | /r/LocalLLaMA/comments/1o31syu/dual_xeon_6_12_channel_ram/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'qkPKVxPTT9gLVWth8NyHTkz6j0Ke1Draa8vQRkMUNtM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qkPKVxPTT9gLVWth8NyHTkz6j0Ke1Draa8vQRkMUNtM.png?width=108&crop=smart&auto=webp&s=3335de0c7b3ac4f8d236e650279d9e1d3d1960f0', 'width': 108}, {'height': 109, 'url': 'h... |
Downloading multi-file source code from an LLM? I uploaded aiar on pypi to fix this... | 0 | When I create a small AI project, or the structure of a big one, I like asking gemini to just give me a starting point. I found downloading all the files is a pain so a few weeks ago I asked it to create a shar - shell archive and apart from some things it didn't escape properly it worked well.
[https://pypi.org/proj... | 2025-10-10T14:02:12 | https://www.reddit.com/r/LocalLLaMA/comments/1o31rjd/downloading_multifile_source_code_from_an_llm_i/ | GianniMariani | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o31rjd | false | null | t3_1o31rjd | /r/LocalLLaMA/comments/1o31rjd/downloading_multifile_source_code_from_an_llm_i/ | false | false | self | 0 | null |
Kwaipilot/KAT-Dev-72B-Exp model released | 77 | The model makers claim it's second on coding only to Sonnet 4.5 at only 72B parameters.
Could someone here who has the hardware to run it, validate this?
[https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp](https://huggingface.co/Kwaipilot/KAT-Dev-72B-Exp) | 2025-10-10T14:02:02 | https://www.reddit.com/r/LocalLLaMA/comments/1o31rdl/kwaipilotkatdev72bexp_model_released/ | UltrMgns | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o31rdl | false | null | t3_1o31rdl | /r/LocalLLaMA/comments/1o31rdl/kwaipilotkatdev72bexp_model_released/ | false | false | self | 77 | {'enabled': False, 'images': [{'id': 'rxyepxgYUof3_-pxPA16Sj6OoiuoO3OTQiZrKV-cxps', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/rxyepxgYUof3_-pxPA16Sj6OoiuoO3OTQiZrKV-cxps.png?width=108&crop=smart&auto=webp&s=cf18d5cf8ded0a10c6a0af997508a324c1a4598f', 'width': 108}, {'height': 116, 'url': 'h... |
How did OpenAI go about to create the model selecting system for GPT 5? | 0 | E.G having the model think/search the web on the go depending on the user's prompt. It's clearly not perfect, but I'm curious | 2025-10-10T13:10:09 | https://www.reddit.com/r/LocalLLaMA/comments/1o30h9j/how_did_openai_go_about_to_create_the_model/ | a_normal_user1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o30h9j | false | null | t3_1o30h9j | /r/LocalLLaMA/comments/1o30h9j/how_did_openai_go_about_to_create_the_model/ | false | false | self | 0 | null |
"Google Gemini" but using a local model | 20 | https://reddit.com/link/1o30e9q/video/sii45b8z8auf1/player
I built a local assistant app that can replace Google Gemini as your phone's default assistant. It works similar to Gemini: long press the power button to bring up Layla, and it will run a local model instead of Gemini.
It supports using local models (GGUF or... | 2025-10-10T13:06:41 | https://www.reddit.com/r/LocalLLaMA/comments/1o30e9q/google_gemini_but_using_a_local_model/ | Tasty-Lobster-8915 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o30e9q | false | null | t3_1o30e9q | /r/LocalLLaMA/comments/1o30e9q/google_gemini_but_using_a_local_model/ | false | false | self | 20 | null |
Translate output rather than training on multiple languages | 0 | Hey LocalLLaMa community,
I've been thinking about multilingual LLMs like Gemma, Qwen, etc. They're trained on a huge text corpus containing a lot of languages.
My question is: Why do we dedicate valuable parameters to learning multiple languages?
With local inference we usually want the most knowledge in the small... | 2025-10-10T12:40:14 | https://www.reddit.com/r/LocalLLaMA/comments/1o2zs6f/translate_output_rather_than_training_on_multiple/ | Jan49_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2zs6f | false | null | t3_1o2zs6f | /r/LocalLLaMA/comments/1o2zs6f/translate_output_rather_than_training_on_multiple/ | false | false | self | 0 | null |
Built a router for LLM orchestration and learned a lot | 0 | I’ve been experimenting with a side project lately, basically an attempt to make local and hosted LLMs work together more intelligently. The issue started when I noticed how often we send simple requests (like “count the number of words in this sentence”) to massive cloud models. Fast answers, sure, but overkill in bot... | 2025-10-10T12:31:45 | https://www.reddit.com/r/LocalLLaMA/comments/1o2zllp/built_a_router_for_llm_orchestration_and_learned/ | Gbalke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2zllp | false | null | t3_1o2zllp | /r/LocalLLaMA/comments/1o2zllp/built_a_router_for_llm_orchestration_and_learned/ | false | false | self | 0 | null |
GALAX Rolls Out Its Single-Slot GeForce RTX 5060 Ti GPU With 16 GB VRAM & Blower-Fan | 21 | 2025-10-10T12:14:32 | https://wccftech.com/galax-single-slot-geforce-rtx-5060-ti-gpu-16-gb-vram-blower-fan/ | _SYSTEM_ADMIN_MOD_ | wccftech.com | 1970-01-01T00:00:00 | 0 | {} | 1o2z88f | false | null | t3_1o2z88f | /r/LocalLLaMA/comments/1o2z88f/galax_rolls_out_its_singleslot_geforce_rtx_5060/ | false | false | 21 | {'enabled': False, 'images': [{'id': 'y6J_OcAXJadfgqu4sGThqrpBh-QuwElkR48n9WojP7o', 'resolutions': [{'height': 51, 'url': 'https://external-preview.redd.it/y6J_OcAXJadfgqu4sGThqrpBh-QuwElkR48n9WojP7o.png?width=108&crop=smart&auto=webp&s=20ca9f671301c309c029129821be2d019218e2ee', 'width': 108}, {'height': 103, 'url': 'h... | ||
Experience with networked 2x128GB AI Max 395? | 13 | We are considering to buy two of these AI shoeboxes, for space and power efficiency. Run a large LLM during the day, use as CI/CD/test server over night.
Q: Anyone has experience with such a setup? Specifically, what's the expected performance of a large (GLM or Qwen235B) model that is split over these two with llama.... | 2025-10-10T12:13:32 | https://www.reddit.com/r/LocalLLaMA/comments/1o2z7fz/experience_with_networked_2x128gb_ai_max_395/ | Bird476Shed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2z7fz | false | null | t3_1o2z7fz | /r/LocalLLaMA/comments/1o2z7fz/experience_with_networked_2x128gb_ai_max_395/ | false | false | self | 13 | null |
Reflection AI raises $2B to be America's open frontier AI lab, challenging DeepSeek | TechCrunch | 175 | Reflection AI: [https://reflection.ai/](https://reflection.ai/)
On 𝕏: [https://x.com/reflection\_ai/status/1976304405369520242](https://x.com/reflection_ai/status/1976304405369520242) | 2025-10-10T12:05:56 | https://techcrunch.com/2025/10/09/reflection-raises-2b-to-be-americas-open-frontier-ai-lab-challenging-deepseek/ | Nunki08 | techcrunch.com | 1970-01-01T00:00:00 | 0 | {} | 1o2z1vt | false | null | t3_1o2z1vt | /r/LocalLLaMA/comments/1o2z1vt/reflection_ai_raises_2b_to_be_americas_open/ | false | false | default | 175 | {'enabled': False, 'images': [{'id': 'J33KaNhavmUdkjELX9a4XHseBsKE9ltSNTN6hWuL1_c', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/J33KaNhavmUdkjELX9a4XHseBsKE9ltSNTN6hWuL1_c.jpeg?width=108&crop=smart&auto=webp&s=a5781dfda8009091e260f20801ae94ca383f0915', 'width': 108}, {'height': 145, 'url': '... |
Does performance of LLMs on android depend more on RAM or CPU clocks? | 1 | [removed] | 2025-10-10T11:51:00 | https://www.reddit.com/r/LocalLLaMA/comments/1o2yr3f/does_performance_of_llms_on_android_depend_more/ | LivingCornet694 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2yr3f | false | null | t3_1o2yr3f | /r/LocalLLaMA/comments/1o2yr3f/does_performance_of_llms_on_android_depend_more/ | false | false | self | 1 | null |
What they didn't teach in software startup school: China | 0 | In the software startup school, china has mostly just been a source of talent. Maybe as a competitor, but largely only in China.
When it came to software tech startups in the US, they really only had to worry about other startups - usually in the bay area. And the worry was limited as they all had the same financ... | 2025-10-10T11:32:07 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ydqm/what_they_didnt_teach_in_software_startup_school/ | kaggleqrdl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ydqm | false | null | t3_1o2ydqm | /r/LocalLLaMA/comments/1o2ydqm/what_they_didnt_teach_in_software_startup_school/ | false | false | self | 0 | null |
Why there's still no local models that can output PDF/DOCX files | 0 | I can't seem to find any model that can output files suck as PDF or Docx like chatGPT, locally or via API, Any reason why? | 2025-10-10T11:23:49 | https://www.reddit.com/r/LocalLLaMA/comments/1o2y87n/why_theres_still_no_local_models_that_can_output/ | abdouhlili | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2y87n | false | null | t3_1o2y87n | /r/LocalLLaMA/comments/1o2y87n/why_theres_still_no_local_models_that_can_output/ | false | false | self | 0 | null |
Help! Is this good enough for daily AI coding | 0 | Hey guys just checking if anyone has any advice if the below specs are good enough for daily AI assisted coding pls. not looking for those highly specialized AI servers or machines as I'm using it for personal gaming too. I got the below advice from chatgpt. thanks so much
---
for daily coding: Qwen2.5-Coder-14B (sp... | 2025-10-10T11:21:56 | https://www.reddit.com/r/LocalLLaMA/comments/1o2y6xi/help_is_this_good_enough_for_daily_ai_coding/ | IntroductionSouth513 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2y6xi | false | null | t3_1o2y6xi | /r/LocalLLaMA/comments/1o2y6xi/help_is_this_good_enough_for_daily_ai_coding/ | false | false | self | 0 | null |
LLaMA that plays chess | 9 | I made a [hybrid](https://github.com/neurocod/llm-chess-hybrid) of LLaMA and several other neural networks that can play chess quite well. It’s part of my ongoing series of [articles](https://www.linkedin.com/pulse/hybrid-neural-networks-inside-llms-konstantine-kozachuk-xquze/) about hybrid neural networks. The hippoca... | 2025-10-10T11:17:54 | https://www.reddit.com/r/LocalLLaMA/comments/1o2y43t/llama_that_plays_chess/ | neurocod | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2y43t | false | null | t3_1o2y43t | /r/LocalLLaMA/comments/1o2y43t/llama_that_plays_chess/ | false | false | 9 | {'enabled': False, 'images': [{'id': 'geYQQAxqjX90o0mQq_3STTNJ2tR_-toI4zN0X160D4k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/geYQQAxqjX90o0mQq_3STTNJ2tR_-toI4zN0X160D4k.png?width=108&crop=smart&auto=webp&s=39dcb03d8292bab4bcba181530c030cb83032f13', 'width': 108}, {'height': 108, 'url': 'h... | |
[image processing failed] | 1 | [deleted] | 2025-10-10T11:16:24 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1o2y30h | false | null | t3_1o2y30h | /r/LocalLLaMA/comments/1o2y30h/image_processing_failed/ | false | false | default | 1 | null | ||
🚨 Local AI is the only sane path if you care about privacy | 171 | Meta recently announced that AI chat interactions on Facebook and Instagram will be used for ad targeting.
Everything you type can shape how you are profiled—a stark reminder that cloud AI often means zero privacy.
Local-first AI puts you in control. Models run entirely on your own device, keeping your data private ... | 2025-10-10T11:11:05 | https://www.reddit.com/r/LocalLLaMA/comments/1o2xzep/local_ai_is_the_only_sane_path_if_you_care_about/ | Code-Forge-Temple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2xzep | false | null | t3_1o2xzep | /r/LocalLLaMA/comments/1o2xzep/local_ai_is_the_only_sane_path_if_you_care_about/ | false | false | self | 171 | null |
A chinese openrouter like provider giving out free 100$ worth of tokens | 0 | Came across this [https://agentrouter.org/register?aff=y40w](https://agentrouter.org/register?aff=y40w) giving out free api credits. Doesn't ask for credit card or anything. Github authorization works. Checked Github permission, only takes email, but still it being chinese I will use it for my opensource projects only ... | 2025-10-10T10:50:53 | https://www.reddit.com/r/LocalLLaMA/comments/1o2xm1o/a_chinese_openrouter_like_provider_giving_out/ | DeathShot7777 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2xm1o | false | null | t3_1o2xm1o | /r/LocalLLaMA/comments/1o2xm1o/a_chinese_openrouter_like_provider_giving_out/ | false | false | self | 0 | null |
Qwen team auto-closed all issues on Qwen2-VL repository | 49 | I just noticed that the Qwen2-VL repository has been renamed to Qwen3-VL and that all issues on GitHub are being closed. It sits currently at 475 open issues/859 closed issues, and changing quickly: [https://github.com/QwenLM/Qwen3-VL/issues](https://github.com/QwenLM/Qwen3-VL/issues)
I think this is somewhat rude, be... | 2025-10-10T10:20:21 | https://www.reddit.com/r/LocalLLaMA/comments/1o2x2xs/qwen_team_autoclosed_all_issues_on_qwen2vl/ | CasualCapybara | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2x2xs | false | null | t3_1o2x2xs | /r/LocalLLaMA/comments/1o2x2xs/qwen_team_autoclosed_all_issues_on_qwen2vl/ | false | false | self | 49 | {'enabled': False, 'images': [{'id': 'iOei8e4q_0yjMZSoeSlFoU2n7fxe8HYKMbS-0QFOYrc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/iOei8e4q_0yjMZSoeSlFoU2n7fxe8HYKMbS-0QFOYrc.png?width=108&crop=smart&auto=webp&s=4b0323038b69c24ceb5fdd7f5de4a2f2603507f9', 'width': 108}, {'height': 108, 'url': 'h... |
PSA: Your Ollama server might be one of 50,000 running naked online. The API has dangerously high permissions. | 1 | [removed] | 2025-10-10T10:16:43 | https://www.reddit.com/r/LocalLLaMA/comments/1o2x0nr/psa_your_ollama_server_might_be_one_of_50000/ | No_Statistician5032 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2x0nr | false | null | t3_1o2x0nr | /r/LocalLLaMA/comments/1o2x0nr/psa_your_ollama_server_might_be_one_of_50000/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'qZioCOrxjxpXp76Fdv2BG1Y7WVBb1zmLZzhpsTRGMRQ', 'resolutions': [], 'source': {'height': 96, 'url': 'https://external-preview.redd.it/qZioCOrxjxpXp76Fdv2BG1Y7WVBb1zmLZzhpsTRGMRQ.png?auto=webp&s=99bee909c9131a9168e6c6bc9e67d90a59e69105', 'width': 96}, 'variants': {}}]} |
AMD MI50 32GB better buy than MI100? | 19 | Plenty of people have the MI50 and performance seems to continuously improve.
While it's officially dropped from ROCm 7, we can still get it to work if we copy some files manually.. obviously this will sooner or later stop working but then we'll have Vulkan.. which (with llama.cpp at least) seems to be almost at a per... | 2025-10-10T10:16:09 | https://www.reddit.com/r/LocalLLaMA/comments/1o2x0bv/amd_mi50_32gb_better_buy_than_mi100/ | FriendlyRetriver | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2x0bv | false | null | t3_1o2x0bv | /r/LocalLLaMA/comments/1o2x0bv/amd_mi50_32gb_better_buy_than_mi100/ | false | false | self | 19 | null |
China blacklists major chip research firm TechInsights following report on Huawei | 63 | 2025-10-10T10:08:58 | https://www.cnbc.com/2025/10/10/china-blacklists-major-chip-ai-research-firm-techinsights-analyzed-report-huawei.html | vancity-boi-in-tdot | cnbc.com | 1970-01-01T00:00:00 | 0 | {} | 1o2wvvy | false | null | t3_1o2wvvy | /r/LocalLLaMA/comments/1o2wvvy/china_blacklists_major_chip_research_firm/ | false | false | default | 63 | {'enabled': False, 'images': [{'id': 'cXviE8IZIrPbvKrVn_b-IwEX0IhaM8bGQVFM7IF9Z1o', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/cXviE8IZIrPbvKrVn_b-IwEX0IhaM8bGQVFM7IF9Z1o.jpeg?width=108&crop=smart&auto=webp&s=e8ce4e453ca44f15f743d15a30e7956f9e97dfa4', 'width': 108}, {'height': 121, 'url': '... | |
We can now run wan or any heavy models even on a 6GB NVIDIA laptop GPU | Thanks to upcoming GDS integration in comfy | 180 | Hello
I am Maifee. I am integrating GDS (GPU Direct Storage) in ComfyUI. And it's working, if you want to test, just do the following:
```
git clone https://github.com/maifeeulasad/ComfyUI.git
cd ComfyUI
git checkout offloader-maifee
python3 main.py --enable-gds --gds-stats # gds enabled run
```
And you no longer n... | 2025-10-10T09:50:47 | https://www.reddit.com/gallery/1o2wkyw | maifee | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1o2wkyw | false | null | t3_1o2wkyw | /r/LocalLLaMA/comments/1o2wkyw/we_can_now_run_wan_or_any_heavy_models_even_on_a/ | false | false | 180 | null | |
finetuning Medium or Small language model for factual and memorizing data. | 0 | I have a builder projects data in a csv. The issues with RAG is that it is fetching non similar data and it is fetching lot of unwanted data. Also there is a limitation of context length.
So I'm planning to fine tune llama 3.1 on my data. And if i ask any question related to that data it should give me the answer lik... | 2025-10-10T09:48:57 | https://www.reddit.com/r/LocalLLaMA/comments/1o2wjyg/finetuning_medium_or_small_language_model_for/ | InteractionLevel6625 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2wjyg | false | null | t3_1o2wjyg | /r/LocalLLaMA/comments/1o2wjyg/finetuning_medium_or_small_language_model_for/ | false | false | self | 0 | null |
Help required in selecting model for aws T4 instance and vllm | 4 | Hello everyone, I want to host a model for a chatbot that will be using RAG to generate responses with tool calling. I have an aws instance with 16gb vram Tesla T4 and 16 gb RAM. Can you please suggest some model that would serve best as an assistant and what would be the suggested configs when serving the model using ... | 2025-10-10T09:22:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o2w4u2/help_required_in_selecting_model_for_aws_t4/ | JuiceFine4582 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2w4u2 | false | null | t3_1o2w4u2 | /r/LocalLLaMA/comments/1o2w4u2/help_required_in_selecting_model_for_aws_t4/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'LkIGsdCWSjlcs87HrSjhRjpKKHuAmiMRdLuBsMm0Evo', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/LkIGsdCWSjlcs87HrSjhRjpKKHuAmiMRdLuBsMm0Evo.png?width=108&crop=smart&auto=webp&s=23a0fba2c8e4197e29515586e14d96684bbd6492', 'width': 108}, {'height': 116, 'url': 'h... |
Any good local Ai home assistant projects out yet? | 5 | I’m looking for something to replace the stupid half working Alexa and Google speakers on my house cause they’re dog shit most times, and also privacy concerns.
Are there any projects that utilise like 4B or smaller sized models that are just really good at natural language and understanding and exceptional tool call ... | 2025-10-10T09:18:51 | https://www.reddit.com/r/LocalLLaMA/comments/1o2w2wt/any_good_local_ai_home_assistant_projects_out_yet/ | SilentReporter9635 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2w2wt | false | null | t3_1o2w2wt | /r/LocalLLaMA/comments/1o2w2wt/any_good_local_ai_home_assistant_projects_out_yet/ | false | false | self | 5 | null |
why is this so weird? | 0 | 2025-10-10T09:09:41 | https://www.reddit.com/r/LocalLLaMA/comments/1o2vxrm/why_is_this_so_weird/ | Top_Accident_8064 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2vxrm | false | null | t3_1o2vxrm | /r/LocalLLaMA/comments/1o2vxrm/why_is_this_so_weird/ | false | false | 0 | null | ||
Whats the best local model i can run with 16 GB VRAM and 96 GB RAM | 16 | 1 general model that has some intelligence with really good tool calling capabilties / (Would be good if it was uncensored to some capacity too, not for any specific purpose but just generally don't want it to turn down stuff cause of "Safety" or something.
| 2025-10-10T09:07:19 | https://www.reddit.com/r/LocalLLaMA/comments/1o2vwh1/whats_the_best_local_model_i_can_run_with_16_gb/ | Tricky_Reflection_75 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2vwh1 | false | null | t3_1o2vwh1 | /r/LocalLLaMA/comments/1o2vwh1/whats_the_best_local_model_i_can_run_with_16_gb/ | false | false | self | 16 | null |
Temperatures for MI50 during inference? Anyone with experience re-pasting processor? | 9 | As many others in here, I am experimenting with the MI50 at the moment due to the fantastic value-for-money relationship of this card (at least w.r.t. $ / GB VRAM). I am getting 80c-85c degrees on the edge sensor running full tilt with a "custom cooling solution". The junction sensor shows >100c (which is high but acce... | 2025-10-10T08:51:07 | https://www.reddit.com/r/LocalLLaMA/comments/1o2vnf2/temperatures_for_mi50_during_inference_anyone/ | EdenistTech | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2vnf2 | false | null | t3_1o2vnf2 | /r/LocalLLaMA/comments/1o2vnf2/temperatures_for_mi50_during_inference_anyone/ | false | false | self | 9 | null |
Do we need domain specialist coding agents (Like separate for front-end/backend)? | 2 | So I found [this](https://kombai.com/why) page on X earlier.
They’re claiming general coding agents (GPT 5, Gemini, Sonnet 4, etc) still struggle with real frontend work - like building proper pages, using component libs, following best practices, that kinda stuff.
(They've done their own benchmarking and all)
Acco... | 2025-10-10T08:36:15 | https://www.reddit.com/r/LocalLLaMA/comments/1o2vfec/do_we_need_domain_specialist_coding_agents_like/ | Haunting_Age_2970 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2vfec | false | null | t3_1o2vfec | /r/LocalLLaMA/comments/1o2vfec/do_we_need_domain_specialist_coding_agents_like/ | false | false | self | 2 | null |
Built my saas mvp using only local models and saved $3k | 1 | Indie dev here building an ai writing assistant. Original plan was using openai api but costs were gonna be insane for my use case.
Did some math and at my target volume I'd be paying like $0.05 per user interaction. With 1000 users doing 60 interactions per month that's $3000 monthly just for api calls. Completely un... | 2025-10-10T08:25:35 | https://www.reddit.com/r/LocalLLaMA/comments/1o2v9r6/built_my_saas_mvp_using_only_local_models_and/ | Super_Sukhoii | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2v9r6 | false | null | t3_1o2v9r6 | /r/LocalLLaMA/comments/1o2v9r6/built_my_saas_mvp_using_only_local_models_and/ | false | false | self | 1 | null |
Get $200 free credit from Agent router (Signup using the link below and GitHub account) - Sharing is caring | 0 | https://agentrouter.org/register?aff=SY0a | 2025-10-10T08:24:15 | https://www.reddit.com/r/LocalLLaMA/comments/1o2v907/get_200_free_credit_from_agent_router_signup/ | Desperate-Mine2845 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2v907 | false | null | t3_1o2v907 | /r/LocalLLaMA/comments/1o2v907/get_200_free_credit_from_agent_router_signup/ | false | false | self | 0 | null |
Found something interesting on lmarena | 1 | So I was playing around in lmarena and come across a model named miramar, which seems to be a codename.
Its response in Chinese is pretty crap, I personally felt its literature capability is too poor to be consider as an artificial object. Apparently it's from a company named OceanAI.
Here is where weird thing happen... | 2025-10-10T08:00:18 | https://www.reddit.com/r/LocalLLaMA/comments/1o2uvwr/found_something_interesting_on_lmarena/ | Head-Pomegranate3637 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2uvwr | false | null | t3_1o2uvwr | /r/LocalLLaMA/comments/1o2uvwr/found_something_interesting_on_lmarena/ | false | false | self | 1 | null |
What's your experience with quantizing MoE with tiny experts? | 6 | As i've read, quantizing a small model of size less than 8B can seriously degrade their performance. But since MoE model (qwen30b with 3b experts, gpt-oss with 5b experts,...) are just a combination of small size experts, how is this affecting them? Can i quantize them to Q4, or should i only run them at Q8 and only qu... | 2025-10-10T07:57:49 | https://www.reddit.com/r/LocalLLaMA/comments/1o2uulc/whats_your_experience_with_quantizing_moe_with/ | arimoto02 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2uulc | false | null | t3_1o2uulc | /r/LocalLLaMA/comments/1o2uulc/whats_your_experience_with_quantizing_moe_with/ | false | false | self | 6 | null |
We just launched Observability for LLMs that works without code changes and redeployment of apps | 12 | You know that moment when your AI app is live and suddenly slows down or costs more than expected? You check the logs and still have no clue what happened.
That is exactly why we built OpenLIT Operator. It gives you observability for LLMs and AI agents without touching your code, rebuilding containers, or redeploy... | 2025-10-10T07:30:27 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ug6s/we_just_launched_observability_for_llms_that/ | patcher99 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ug6s | false | null | t3_1o2ug6s | /r/LocalLLaMA/comments/1o2ug6s/we_just_launched_observability_for_llms_that/ | false | false | self | 12 | null |
GLM coding plan | 0 | There is something called GLM Coding Plan from the official provider for just 3$ a month, does anyone tried it with ST? I can't find anything in ToS prohibiting of using it with ST. | 2025-10-10T07:23:40 | https://www.reddit.com/r/LocalLLaMA/comments/1o2ucg6/glm_coding_plan/ | Whole-Warthog8331 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2ucg6 | false | null | t3_1o2ucg6 | /r/LocalLLaMA/comments/1o2ucg6/glm_coding_plan/ | false | false | self | 0 | null |
Olla v0.0.19 is out with SGLang & lemonade support | 7 | We've added native [sglang](https://github.com/sgl-project/sglang) and [lemonade](https://lemonade-server.ai/) support and released v0.0.19 of Olla, the fast unifying LLM Proxy - which already supports Ollama, LM Studio, LiteLLM natively (see [the list](https://thushan.github.io/olla/integrations/overview/)).
We’ve be... | 2025-10-10T06:11:39 | https://github.com/thushan/olla | 2shanigans | github.com | 1970-01-01T00:00:00 | 0 | {} | 1o2t72w | false | null | t3_1o2t72w | /r/LocalLLaMA/comments/1o2t72w/olla_v0019_is_out_with_sglang_lemonade_support/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'EmvlZmNJDsCM03xUIgjfe04GISheKc3GwRTX95FXeeM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EmvlZmNJDsCM03xUIgjfe04GISheKc3GwRTX95FXeeM.png?width=108&crop=smart&auto=webp&s=71ab1f5549d4359a4d11cba8332458b5c8e08279', 'width': 108}, {'height': 108, 'url': 'h... | |
An Embarrassingly Simple Defense Against LLM Abliteration Attacks | 7 | 2025-10-10T05:51:49 | https://arxiv.org/html/2505.19056v2 | newdoria88 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1o2sv96 | false | null | t3_1o2sv96 | /r/LocalLLaMA/comments/1o2sv96/an_embarrassingly_simple_defense_against_llm/ | false | false | default | 7 | null | |
Ai coding completion survey | 3 | Im curious , how long does it take you to finish your average coding task with claude code with opus or sonnet 4.5 or gpt 5 pro compared to a large model like glm4.6 or deepseek 3.2? (i mean including debugging time and your reviewing time) Compared to gpt 5 nano? Compared to a medium size model like qwen next 80b ? ... | 2025-10-10T05:16:10 | https://www.reddit.com/r/LocalLLaMA/comments/1o2s9td/ai_coding_completion_survey/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2s9td | false | null | t3_1o2s9td | /r/LocalLLaMA/comments/1o2s9td/ai_coding_completion_survey/ | false | false | self | 3 | null |
Huawei/CANN / Ascend NPUs: Is anyone using it - and, what's the perf? | 2 | Basically the title.
I've been side-eying CANN eversince I noticed it pop up in the llama.cpp documentation as being supported; it is also noted as such in other projects like vLLM etc.
But, looking on Alibaba, their biggest NPU, with LPDDR4 memory, costs almost as much as the estimated price for a Maxsun Intel B60 D... | 2025-10-10T04:48:42 | https://www.reddit.com/r/LocalLLaMA/comments/1o2rs4v/huaweicann_ascend_npus_is_anyone_using_it_and/ | IngwiePhoenix | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2rs4v | false | null | t3_1o2rs4v | /r/LocalLLaMA/comments/1o2rs4v/huaweicann_ascend_npus_is_anyone_using_it_and/ | false | false | self | 2 | null |
Qwen3 VL 4B to be released? | 205 | Qwen released cookbooks and in one of them this model Qwen3 VL 4B is present but I can't find it anywhere on huggingface. Link of the cookbook- https://github.com/QwenLM/Qwen3-VL/blob/main/cookbooks/long_document_understanding.ipynb
This would be quite amazing for OCR use cases. Qwen2.5/2 VL 3b/7b was foundation for m... | 2025-10-10T04:44:56 | Signal-Run7450 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1o2rppj | false | null | t3_1o2rppj | /r/LocalLLaMA/comments/1o2rppj/qwen3_vl_4b_to_be_released/ | false | false | 205 | {'enabled': True, 'images': [{'id': 'Lmi8wMInNFXjl_jeUF7G-dIRbGjsJDWuUGTqgoBQdR4', 'resolutions': [{'height': 186, 'url': 'https://preview.redd.it/68mmis87s7uf1.png?width=108&crop=smart&auto=webp&s=de8a99b906b01785bfc2fb4547ae17e50a825eb3', 'width': 108}, {'height': 373, 'url': 'https://preview.redd.it/68mmis87s7uf1.pn... | ||
Second Prototype! Tripled the dataset this time (Spent all day just cleaning it, lol) | 1 | I'm currently focusing only on **persona fine-tuning** (can't do layer tuning due to GPU limitations...)
What I added this time was **multi-turn dialogue**! Specifically, 500+ tokens per turn.
https://preview.redd.it/n9kbbmbjo7uf1.png?width=1293&format=png&auto=webp&s=18b8e791de57342840dd5eb1b9b06786994d378c
Also ad... | 2025-10-10T04:24:38 | https://www.reddit.com/r/LocalLLaMA/comments/1o2rcgo/second_prototype_tripled_the_dataset_this_time/ | Patience2277 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1o2rcgo | false | null | t3_1o2rcgo | /r/LocalLLaMA/comments/1o2rcgo/second_prototype_tripled_the_dataset_this_time/ | false | false | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.