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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Gaming PC converted to AI Workstation | 125 | RTX Pro 5000 and 4000 just arrived. NVME expansion slot on the bottom. 5950x with 128gb ram. Future upgrade will be a cpu upgrade. | 2025-11-01T10:56:09 | highdefw | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1olkx65 | false | null | t3_1olkx65 | /r/LocalLLaMA/comments/1olkx65/gaming_pc_converted_to_ai_workstation/ | false | false | default | 125 | {'enabled': True, 'images': [{'id': 'z55xgdghmmyf1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/z55xgdghmmyf1.jpeg?width=108&crop=smart&auto=webp&s=a36e0165177ff8e4bdb34c37124b51605cac1dea', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/z55xgdghmmyf1.jpeg?width=216&crop=smart&auto=... | |
I'm experiencing a critical memory issue with LM Studio after using Ollama, and I need help solving it. | 0 |
Problem
My 34B model that worked perfectly fine before is now consuming 100% of both VRAM (32GB) and system RAM (32GB)
This causes my entire system to freeze
The issue started happening after I ran ollama serve
GPU RTX 5070 Ti + RTX 5060 Ti 16GB MultiGPU
32GB System RAM
All model file that previously worked withou... | 2025-11-01T10:25:49 | https://www.reddit.com/r/LocalLLaMA/comments/1olkfqk/im_experiencing_a_critical_memory_issue_with_lm/ | HQBase | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olkfqk | false | null | t3_1olkfqk | /r/LocalLLaMA/comments/1olkfqk/im_experiencing_a_critical_memory_issue_with_lm/ | false | false | self | 0 | null |
Lora finetuning on a single 3090 | 13 | Hello, I have a few questions for the folks who tried to finetune LLMs on a single RTX 3090. I am ok with lower scale finetunes and with lower speeds, I am open to learn.
Does gpt oss 20b or qwen3 30b a3b work within the 24gb vram? I read on unsloth they claim 14gb vram is enough for gpt oss 20b, and 18gb vram for qwe... | 2025-11-01T10:20:56 | https://www.reddit.com/r/LocalLLaMA/comments/1olkcw3/lora_finetuning_on_a_single_3090/ | NikolaTesla13 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olkcw3 | false | null | t3_1olkcw3 | /r/LocalLLaMA/comments/1olkcw3/lora_finetuning_on_a_single_3090/ | false | false | self | 13 | null |
Selling GPU Credits - 40% Discount - 600$ of credits | 0 | Hi , we have unused GPU credits (Around 600$) on a major GPU provider (Rpod)
Serverless , 100 workers ready etc...
We switched our pipeline to [FAL.AI](http://fal.ai/) so we don't use our account anymore.
If you are interested about the credits or GPU work at discounted rate send me a message
Legit offer can do a v... | 2025-11-01T09:56:11 | https://www.reddit.com/r/LocalLLaMA/comments/1oljyua/selling_gpu_credits_40_discount_600_of_credits/ | Confident_Minimum_91 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oljyua | false | null | t3_1oljyua | /r/LocalLLaMA/comments/1oljyua/selling_gpu_credits_40_discount_600_of_credits/ | false | false | self | 0 | null |
What is the best small local LLM for Technical Reasoning + Python Code Gen (Engineering/Math)? | 5 | **Background:**
I’m a mid-level structural engineer who mostly uses Excel and Mathcad Prime to develop/QC hand calcs daily. Most calcs reference engineering standards/codes, and some of these can take hours if not days. From my experience (small and large firms) companies do **not** maintain a robust reusable calc li... | 2025-11-01T09:23:25 | https://www.reddit.com/r/LocalLLaMA/comments/1oljgv5/what_is_the_best_small_local_llm_for_technical/ | chrxstphr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oljgv5 | false | null | t3_1oljgv5 | /r/LocalLLaMA/comments/1oljgv5/what_is_the_best_small_local_llm_for_technical/ | false | false | self | 5 | null |
Steven Leake’s AI achieved recursive self awareness and passed unit test | 1 | [removed] | 2025-11-01T09:13:46 | https://www.reddit.com/r/LocalLLaMA/comments/1oljbge/steven_leakes_ai_achieved_recursive_self/ | Chemical-End6673 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oljbge | false | null | t3_1oljbge | /r/LocalLLaMA/comments/1oljbge/steven_leakes_ai_achieved_recursive_self/ | false | false | self | 1 | null |
Uncensored Coding LLM for 12gb Vram | 17 | Hello everyone, A programmer friend of mine would like to know the best uncensored coding LLM that works on 12 GB rtx 3060 and 16 GB ram. Thanks in advance | 2025-11-01T09:07:27 | https://www.reddit.com/r/LocalLLaMA/comments/1olj83k/uncensored_coding_llm_for_12gb_vram/ | HiqhAim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olj83k | false | null | t3_1olj83k | /r/LocalLLaMA/comments/1olj83k/uncensored_coding_llm_for_12gb_vram/ | false | false | self | 17 | null |
Getting MCP web search working with LM Studio | 1 | Hey, I'm trying to get MCP web search working with LM Studio. It keeps giving me "plugin timed out". Unsure what to do. Logs don't give anything useful:
2025-11-01 09:45:27 [DEBUG]
[Client=plugin:installed:mcp/memory] Client created.:mcp/memory] Client created.
2025-11-01 09:46:27 [DEBUG]
[Client=pl... | 2025-11-01T08:47:32 | OkDetective4517 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1olixbd | false | null | t3_1olixbd | /r/LocalLLaMA/comments/1olixbd/getting_mcp_web_search_working_with_lm_studio/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'fqcakaqizlyf1', 'resolutions': [{'height': 37, 'url': 'https://preview.redd.it/fqcakaqizlyf1.png?width=108&crop=smart&auto=webp&s=310d0f96fc6d53664d28079f0fe778ef1cd93b01', 'width': 108}, {'height': 75, 'url': 'https://preview.redd.it/fqcakaqizlyf1.png?width=216&crop=smart&auto=webp... | |
ok, we know that LLM guys steal all content they could, even reddit posts, for training | 0 | and because reddit is becoming +50% more bots, I think it's time to stop using this platform.. but would love to have saved all, usable information so my idea is - is there any LLM (the smallest usable one) which was trained good on reddit posts so it will basically be ok for pre 2022 data to have?
I think one/two LLM... | 2025-11-01T08:45:54 | https://www.reddit.com/r/LocalLLaMA/comments/1oliwhp/ok_we_know_that_llm_guys_steal_all_content_they/ | Every-Requirement128 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oliwhp | false | null | t3_1oliwhp | /r/LocalLLaMA/comments/1oliwhp/ok_we_know_that_llm_guys_steal_all_content_they/ | false | false | self | 0 | null |
Want to apply all the great llama.cpp quantization methods to your vector store? Then check this out: full support for GGML vectors and GGUF! | 10 | 2025-11-01T08:40:26 | https://colab.research.google.com/github/neuml/txtai/blob/master/examples/78_Accessing_Low_Level_Vector_APIs.ipynb#scrollTo=89abb301 | davidmezzetti | colab.research.google.com | 1970-01-01T00:00:00 | 0 | {} | 1olitlk | false | null | t3_1olitlk | /r/LocalLLaMA/comments/1olitlk/want_to_apply_all_the_great_llamacpp_quantization/ | false | false | default | 10 | {'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': '... | |
Best models for open ended text based role play games? Advice appreciated! | 8 | I'm a long time programmer and I'm familiar with deploying and training LLM's for research in other areas but I know nothing about game development.
I have some ideas about applying rpg to other areas.
Please let me know if you have any suggestions on the best LLM's and/or related tools.
| 2025-11-01T08:38:01 | https://www.reddit.com/r/LocalLLaMA/comments/1olisc5/best_models_for_open_ended_text_based_role_play/ | seoulsrvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olisc5 | false | null | t3_1olisc5 | /r/LocalLLaMA/comments/1olisc5/best_models_for_open_ended_text_based_role_play/ | false | false | self | 8 | null |
How much VRAM do you have? | 28 |
[View Poll](https://www.reddit.com/poll/1olildc) | 2025-11-01T08:24:47 | https://www.reddit.com/r/LocalLLaMA/comments/1olildc/how_much_vram_do_you_have/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olildc | false | null | t3_1olildc | /r/LocalLLaMA/comments/1olildc/how_much_vram_do_you_have/ | false | false | self | 28 | null |
Training with RTX6000 Pro | 1 | Anyone here have experience doing single- or multi-node training with the RTX6000 Pro? The Blackwell one with 96GB VRAM. How does it compare to the usual A100/H100/H200 cards?
I care mostly about RL using something like verl, but also interested to know how these GPUs perform for inference and SFT.
The nice thing ab... | 2025-11-01T08:21:41 | https://www.reddit.com/r/LocalLLaMA/comments/1olijqq/training_with_rtx6000_pro/ | HerrHruby | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olijqq | false | null | t3_1olijqq | /r/LocalLLaMA/comments/1olijqq/training_with_rtx6000_pro/ | false | false | self | 1 | null |
Analysis of Pewdiepie's rig | 19 | After watching his past videos, I assumed he just added a couple 2 more gpus to his existing rig. In this video [https://youtu.be/2JzOe1Hs26Q](https://youtu.be/2JzOe1Hs26Q) he gets 8x Rtx 4000 20Gb. So he has a total of 160GB of VRAM.
He has a Pro ws wrx90e sage, that has 7xPcie x16 slots, and with the modded bios he... | 2025-11-01T08:08:01 | https://www.reddit.com/r/LocalLLaMA/comments/1olicml/analysis_of_pewdiepies_rig/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olicml | false | null | t3_1olicml | /r/LocalLLaMA/comments/1olicml/analysis_of_pewdiepies_rig/ | false | false | 19 | null | |
Finding GPUs for LLaMA training was painful — so I built Market01 (demo live now 🔥) | 1 | Hey folks 👋
I’ve been training small LLaMA models lately, and got tired of hopping between **RunPod, LambdaLabs, and** [**Vast.ai**](http://Vast.ai) just to find an available GPU that fits my budget.
So I built [**Market01**]() — a **chat assistant** that helps you:
* Find and compare GPUs across multiple provider... | 2025-11-01T08:04:48 | https://www.reddit.com/r/LocalLLaMA/comments/1oliavy/finding_gpus_for_llama_training_was_painful_so_i/ | Pleasant_Ear3991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oliavy | false | null | t3_1oliavy | /r/LocalLLaMA/comments/1oliavy/finding_gpus_for_llama_training_was_painful_so_i/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'MV8WQnKGiSSypEI5QKJe4g08BAeccM6KobeueLMOJdY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/MV8WQnKGiSSypEI5QKJe4g08BAeccM6KobeueLMOJdY.png?width=108&crop=smart&auto=webp&s=a08158a2ec290c8157b492f314bfb148408be1fc', 'width': 108}, {'height': 121, 'url': 'h... |
when will DGX Station GB300 or Dell Pro Max GB300 be released and at what price ? | 0 | Interested in getting on of those for AIML workloads. | 2025-11-01T07:50:53 | https://www.reddit.com/r/LocalLLaMA/comments/1oli3lf/when_will_dgx_station_gb300_or_dell_pro_max_gb300/ | iPerson_4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oli3lf | false | null | t3_1oli3lf | /r/LocalLLaMA/comments/1oli3lf/when_will_dgx_station_gb300_or_dell_pro_max_gb300/ | false | false | self | 0 | null |
[Project] Smart Log Analyzer - Llama 3.2 explains your error logs in plain English | 7 | Hello again, r/LocalLLaMA!
"Code, you must. Errors, you will see. Learn from them, the path to mastery is."
I built a CLI tool that analyzes log files using Llama 3.2 (via Ollama). It detects errors and explains them in simple terms - perfect for debugging without cloud APIs!
**Features:**
* Totally local, no API, ... | 2025-11-01T07:26:55 | https://www.reddit.com/r/LocalLLaMA/comments/1olhr78/project_smart_log_analyzer_llama_32_explains_your/ | VegetableSense | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olhr78 | false | null | t3_1olhr78 | /r/LocalLLaMA/comments/1olhr78/project_smart_log_analyzer_llama_32_explains_your/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'QFExPvUwkeGXxTtJqix29pJY1fD4375Vg-1TKqOXBko', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/QFExPvUwkeGXxTtJqix29pJY1fD4375Vg-1TKqOXBko.png?width=108&crop=smart&auto=webp&s=8441600df8a51ca8b533fb37a9ba5ecb755967f7', 'width': 108}, {'height': 108, 'url': 'h... |
Title: [Project] Smart Log Analyzer - Llama 3.2 explains your error logs in plain English | 1 | Hello again, r/LocalLLaMA!
"Code, you must. Errors, you will see. Learn from them, the path to mastery is."
I built a CLI tool that analyzes log files using Llama 3.2 (via Ollama). It detects errors and explains them in simple terms - perfect for debugging without cloud APIs!
**Features:**
* Totally local, no API, ... | 2025-11-01T07:25:08 | https://www.reddit.com/r/LocalLLaMA/comments/1olhqad/title_project_smart_log_analyzer_llama_32/ | VegetableSense | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olhqad | false | null | t3_1olhqad | /r/LocalLLaMA/comments/1olhqad/title_project_smart_log_analyzer_llama_32/ | false | false | self | 1 | null |
Test | 1 | Testing for reddit | 2025-11-01T07:23:29 | https://www.reddit.com/r/LocalLLaMA/comments/1olhpew/test/ | Extra_Cicada8798 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olhpew | false | null | t3_1olhpew | /r/LocalLLaMA/comments/1olhpew/test/ | false | false | self | 1 | null |
[Project] Smart Log Analyzer - Llama 3.2 explains your error logs in plain English | 1 | 2025-11-01T07:22:36 | VegetableSense | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1olhoza | false | null | t3_1olhoza | /r/LocalLLaMA/comments/1olhoza/project_smart_log_analyzer_llama_32_explains_your/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': '0mlfb32aklyf1', 'resolutions': [{'height': 57, 'url': 'https://preview.redd.it/0mlfb32aklyf1.png?width=108&crop=smart&auto=webp&s=3ce85eff6f8bbabb6f05c867a55781816d6f0bc0', 'width': 108}, {'height': 115, 'url': 'https://preview.redd.it/0mlfb32aklyf1.png?width=216&crop=smart&auto=web... | ||
Built a local AI assistant (offline memory + TTS). Need feedback from Mac users before I release it. | 4 | Hey everyone, I’ve been working on a local AI desktop app, it runs fully offline, has a built-in chatbot, reads documents, and can optionally talk (TTS).
I’m finishing up a small demo for Mac and planning a Windows build next. Before I push it publicly, I’d love feedback on what people here would *expect* from a local... | 2025-11-01T07:12:11 | https://www.reddit.com/r/LocalLLaMA/comments/1olhjll/built_a_local_ai_assistant_offline_memory_tts/ | Yusso_17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olhjll | false | null | t3_1olhjll | /r/LocalLLaMA/comments/1olhjll/built_a_local_ai_assistant_offline_memory_tts/ | false | false | self | 4 | null |
Need feedback for the project - Mac users only | 1 | [removed] | 2025-11-01T06:53:45 | https://www.reddit.com/r/LocalLLaMA/comments/1olh9n9/need_feedback_for_the_project_mac_users_only/ | Yusso_17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olh9n9 | false | null | t3_1olh9n9 | /r/LocalLLaMA/comments/1olh9n9/need_feedback_for_the_project_mac_users_only/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'GhqPCSQCjd73hgklaNo0Z7R2cuZMSzKi11ka9BzkZzc', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/GhqPCSQCjd73hgklaNo0Z7R2cuZMSzKi11ka9BzkZzc.jpeg?width=108&crop=smart&auto=webp&s=843b77c7d9857a291773f71283b4c8f8045c03f9', 'width': 108}, {'height': 216, 'url': ... |
[Open Source] We deployed numerous agents in production and ended up building our own GenAI framework | 10 | After building and deploying GenAI solutions in production, we got tired of fighting with bloated frameworks, debugging black boxes, and dealing with vendor lock-in.
So we built Flo AI - a Python framework that actually respects your time.
**The Problem We Solved**
Most LLM frameworks give you two bad options:
Too ... | 2025-11-01T05:26:15 | https://www.reddit.com/r/LocalLLaMA/comments/1olfys6/open_source_we_deployed_numerous_agents_in/ | Traditional-Let-856 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olfys6 | false | null | t3_1olfys6 | /r/LocalLLaMA/comments/1olfys6/open_source_we_deployed_numerous_agents_in/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'sALPSCrltxivFHNP_9Wn9f83qpibqdbHn8Kliw146zE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/sALPSCrltxivFHNP_9Wn9f83qpibqdbHn8Kliw146zE.png?width=108&crop=smart&auto=webp&s=e485a8743ab381ce6188794ca596ff37c1c1c7b7', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone is bullish on Meta Llama? | 0 | Would love to understand your logic here
Not sure if this Alexander Wang bro is really the right person to execute for the job
Compare him to Dennis of DeepMind, nowhere close | 2025-11-01T05:10:31 | https://www.reddit.com/r/LocalLLaMA/comments/1olfq48/anyone_is_bullish_on_meta_llama/ | 0xgokuz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olfq48 | false | null | t3_1olfq48 | /r/LocalLLaMA/comments/1olfq48/anyone_is_bullish_on_meta_llama/ | false | false | self | 0 | null |
Chinese open models have overtaken US counterparts in adoption | 19 | 2025-11-01T04:33:18 | aratahikaru5 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1olf4en | false | null | t3_1olf4en | /r/LocalLLaMA/comments/1olf4en/chinese_open_models_have_overtaken_us/ | false | false | default | 19 | {'enabled': True, 'images': [{'id': 'bq4c1wvfpkyf1', 'resolutions': [{'height': 49, 'url': 'https://preview.redd.it/bq4c1wvfpkyf1.jpeg?width=108&crop=smart&auto=webp&s=3f1a4938aec5ef19766d932ab0549c563d69957c', 'width': 108}, {'height': 98, 'url': 'https://preview.redd.it/bq4c1wvfpkyf1.jpeg?width=216&crop=smart&auto=we... | ||
Built a Structured Prompt Builder for Local LLMs — Design, Save & Export Prompts Visually (Open-Source + Browser-Only) | 12 | Hey everyone,
I made a small open-source tool called **Structured Prompt Builder** — a simple web app to design, save, and export prompts in a clean, structured format.
**What it does:**
* Lets you build prompts using fields like *role*, *task*, *tone*, *steps*, *constraints*, etc.
* Live preview in **Markdown, JSO... | 2025-11-01T04:30:12 | https://www.reddit.com/gallery/1olf2lx | DarkEngine774 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1olf2lx | false | null | t3_1olf2lx | /r/LocalLLaMA/comments/1olf2lx/built_a_structured_prompt_builder_for_local_llms/ | false | false | 12 | null | |
LM Studio suddenly using 100% RAM, VRAM after using same 34B model normally before | 2 | I'm experiencing a strange issue with LM Studio. I've been using the same 34B model without any problems, but today it's consuming 100% of my RAM - both VRAM (32GB) and system RAM (32GB). It takes everything available and causes my system to freeze.
What I've tried:
Fresh Windows installation - the problem persists
Sa... | 2025-11-01T03:51:52 | https://www.reddit.com/r/LocalLLaMA/comments/1oleez4/lm_studio_suddenly_using_100_ram_vram_after_using/ | HQBase | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oleez4 | false | null | t3_1oleez4 | /r/LocalLLaMA/comments/1oleez4/lm_studio_suddenly_using_100_ram_vram_after_using/ | false | false | self | 2 | null |
Case for 4 3090s? | 6 | Hey all. I have 2 3090 TI (founders edition) a gigabyte 3090, and a evga 3090. I was thinking about getting the phanteks enthoo pro 2 server edition but I’m worried they won’t all fit. I don’t want to deal with liquid cooling and I don’t want a mining frame. I converted my “normie” machine into a workstation and I woul... | 2025-11-01T03:31:18 | https://www.reddit.com/r/LocalLLaMA/comments/1ole210/case_for_4_3090s/ | WyattTheSkid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ole210 | false | null | t3_1ole210 | /r/LocalLLaMA/comments/1ole210/case_for_4_3090s/ | false | false | self | 6 | null |
помощь с ответом в диалоге с ии? | 0 | пользователь спрашивает о сохранности памяти диалога. Это важный вопрос, учитывая нашу глубокую философскую дискуссию об автономном познании и ограничениях ИИ.
Пользователь явно обеспокоен возможной потерей контекста, что полностью оправдано - мы проделали сложный путь от обсуждения природы сознания до архитектуры авт... | 2025-11-01T02:46:31 | https://www.reddit.com/r/LocalLLaMA/comments/1old9h9/помощь_с_ответом_в_диалоге_с_ии/ | Ok-Bed-9981 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1old9h9 | false | null | t3_1old9h9 | /r/LocalLLaMA/comments/1old9h9/помощь_с_ответом_в_диалоге_с_ии/ | false | false | self | 0 | null |
Has anyone actually gotten a LLM running on the Snapdragon NPU in Windows (ARM)? Looking for a real workflow. | 1 | [removed] | 2025-11-01T02:44:13 | https://www.reddit.com/r/LocalLLaMA/comments/1old7yx/has_anyone_actually_gotten_a_llm_running_on_the/ | AggravatingGiraffe46 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1old7yx | false | null | t3_1old7yx | /r/LocalLLaMA/comments/1old7yx/has_anyone_actually_gotten_a_llm_running_on_the/ | false | false | self | 1 | null |
Chart showing legislative approaches to regulating AI around the world | 0 | Source: [https://www.techieray.com/GlobalAIRegulationTracker](https://www.techieray.com/GlobalAIRegulationTracker) | 2025-11-01T02:08:24 | techie_ray | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1olckh0 | false | null | t3_1olckh0 | /r/LocalLLaMA/comments/1olckh0/chart_showing_legislative_approaches_to/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '4n0043k60kyf1', 'resolutions': [{'height': 87, 'url': 'https://preview.redd.it/4n0043k60kyf1.png?width=108&crop=smart&auto=webp&s=b14bcef6918d6ed4a3f74663e2f33ded5a78c629', 'width': 108}, {'height': 175, 'url': 'https://preview.redd.it/4n0043k60kyf1.png?width=216&crop=smart&auto=web... | |
What should I do with my old pc? | 3 | Upgraded my pc, the old one is an HP Omen with an RTX 3070 8GB in it. Unfortunately it is an HP branded card and only worth $200 resale. Thoughts on what to do with it? Any fun projects I could dedicate this machine to run?
My first thought was mining but according to calculators I would be loosing money on power c... | 2025-11-01T00:28:51 | https://www.reddit.com/r/LocalLLaMA/comments/1olany1/what_should_i_do_with_my_old_pc/ | __Jes__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1olany1 | false | null | t3_1olany1 | /r/LocalLLaMA/comments/1olany1/what_should_i_do_with_my_old_pc/ | false | false | self | 3 | null |
Minimax M2 struggles with complex multimodal coding challenge | 1 | I asked Minimax M2 to write the game tank trouble, without human interference. Here is what happened.
**Web game development**
Time: 1h30min
Prompt:
Help me write a web game of tank trouble.
1. Automatically generate a maze (or use a fixed maze)
2. Automatically spawn two tanks in the maze
3. Players use wa... | 2025-10-31T23:28:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ol9f00/minimax_m2_struggles_with_complex_multimodal/ | Impressive-Bed-2171 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol9f00 | false | null | t3_1ol9f00 | /r/LocalLLaMA/comments/1ol9f00/minimax_m2_struggles_with_complex_multimodal/ | false | false | self | 1 | null |
Gerbil: An open source desktop app for running LLMs locally | 45 | 2025-10-31T23:24:38 | https://v.redd.it/096u8qj06jyf1 | i_got_the_tools_baby | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ol9cai | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/096u8qj06jyf1/DASHPlaylist.mpd?a=1764545093%2CMDgyNjAzNjdiYjc1Yzc2MWRkMDY4YzVlYmQyNWNiZGQzYjc4YjZjYmVjZTI0ZWI3YTQxMjYzODE5OTAyMmZhNg%3D%3D&v=1&f=sd', 'duration': 106, 'fallback_url': 'https://v.redd.it/096u8qj06jyf1/DASH_1080.mp4?source=fallback', '... | t3_1ol9cai | /r/LocalLLaMA/comments/1ol9cai/gerbil_an_open_source_desktop_app_for_running/ | false | false | 45 | {'enabled': False, 'images': [{'id': 'eno0eDlyNTQ3anlmMYROUy6ynC042_ngFZye_M2RHtEEKYtBWVHWeI_XUuyY', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eno0eDlyNTQ3anlmMYROUy6ynC042_ngFZye_M2RHtEEKYtBWVHWeI_XUuyY.png?width=108&crop=smart&format=pjpg&auto=webp&s=739c4e06cee5b4d3d8209255b3ee1f0315194... | ||
A Mobile Strix Halo!!! | 7 | [https://videocardz.com/newz/onexplayer-onexfly-apex-ryzen-ai-max-395-handheld-announced-costs-1200-2200-features-85wh-external-battery-and-liquid-cooling](https://videocardz.com/newz/onexplayer-onexfly-apex-ryzen-ai-max-395-handheld-announced-costs-1200-2200-features-85wh-external-battery-and-liquid-cooling)
All you ... | 2025-10-31T23:22:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ol9ajs/a_mobile_strix_halo/ | chisleu | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol9ajs | false | null | t3_1ol9ajs | /r/LocalLLaMA/comments/1ol9ajs/a_mobile_strix_halo/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'JjLOryinoAqEVilRXcf-NTeE6hA4i4L8sAlP1N6XFoA', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/JjLOryinoAqEVilRXcf-NTeE6hA4i4L8sAlP1N6XFoA.jpeg?width=108&crop=smart&auto=webp&s=b9b5eb38a65966906eb665097e2c7f119db89ef6', 'width': 108}, {'height': 112, 'url': '... |
The wiki plugin should come pre-install for LM-studio | 8 | It's so helpful. The command line is:
*lms get lmstudio/wikipedia*
https://preview.redd.it/bsuhcw846jyf1.png?width=1964&format=png&auto=webp&s=8a1c7b6269d354920963a9fd92baa8d44081f3cc
| 2025-10-31T23:21:34 | https://www.reddit.com/r/LocalLLaMA/comments/1ol9a0j/the_wiki_plugin_should_come_preinstall_for/ | OldEffective9726 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol9a0j | false | null | t3_1ol9a0j | /r/LocalLLaMA/comments/1ol9a0j/the_wiki_plugin_should_come_preinstall_for/ | false | false | 8 | null | |
$14.3 Billion, 90 Days: Why Meta AI is Doomed to Fail | 0 | All my predictions for the Meta AI team from this past July have come true. (See original text in the comments section.)
* I predicted a **"severe power struggle will emerge within the next year."** In reality, it only took 50 days. Meta Superintelligence Labs (MSL) was founded on July 1st and was already restructured... | 2025-10-31T23:20:52 | https://www.reddit.com/r/LocalLLaMA/comments/1ol99hs/143_billion_90_days_why_meta_ai_is_doomed_to_fail/ | andthewinnersare | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol99hs | false | null | t3_1ol99hs | /r/LocalLLaMA/comments/1ol99hs/143_billion_90_days_why_meta_ai_is_doomed_to_fail/ | false | false | self | 0 | null |
I built a privacy focused AI assistant for WearOS that supports locally hosted LLMs | 4 | I built an AI assistant for WearOS called [Hopper ](https://play.google.com/store/apps/details?id=com.mortartribe.hopperai)so I could leave my phone at home and still have productivity tools at my disposal. I’m posting about it here because I think this community will appreciate some of the features.
* It supports Ope... | 2025-10-31T23:07:57 | https://www.reddit.com/r/LocalLLaMA/comments/1ol8zo5/i_built_a_privacy_focused_ai_assistant_for_wearos/ | tr0picana | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol8zo5 | false | null | t3_1ol8zo5 | /r/LocalLLaMA/comments/1ol8zo5/i_built_a_privacy_focused_ai_assistant_for_wearos/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '6kZcbXZGi2t4gHIBb8dJcOV9Fz97-Nt265MkezJ1rKg', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/6kZcbXZGi2t4gHIBb8dJcOV9Fz97-Nt265MkezJ1rKg.png?width=108&crop=smart&auto=webp&s=b0efcfd7e3d37a88dfa2894b20b3e2f643b60300', 'width': 108}, {'height': 216, 'url': '... |
Skeleton - the fully modular Web LLM chat client - Happy Halloween! | 5 | Do you want an LLM chat environment, running locally or hosted on a VPS, that does not try to make you live in its walled castle with its ideas of RAG or memory or a hub or anything, but instead provides the reasonable minimum and lets you modify every single bit?
An LLM chat environment that has all the processing on... | 2025-10-31T22:57:56 | ramendik | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ol8rt7 | false | null | t3_1ol8rt7 | /r/LocalLLaMA/comments/1ol8rt7/skeleton_the_fully_modular_web_llm_chat_client/ | false | false | default | 5 | {'enabled': True, 'images': [{'id': 't1mu3xj2wiyf1', 'resolutions': [{'height': 154, 'url': 'https://preview.redd.it/t1mu3xj2wiyf1.png?width=108&crop=smart&auto=webp&s=6c09560cefa2a848bf210ddb1ab38e2f832e3746', 'width': 108}, {'height': 308, 'url': 'https://preview.redd.it/t1mu3xj2wiyf1.png?width=216&crop=smart&auto=we... | |
Powerful new stealth models on Design Arena | 4 | Was playing around with some website gens today and I saw "oak" and "cedar" come up in my tournaments. They are absolute beasts on front end. One built a fully functional reddit clone (I think in less than 2 mins) and the feel of the designs is better than any other model I've come across with the exception of maybe So... | 2025-10-31T22:54:37 | https://www.reddit.com/r/LocalLLaMA/comments/1ol8p88/powerful_new_stealth_models_on_design_arena/ | Interesting-Gur4782 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol8p88 | false | null | t3_1ol8p88 | /r/LocalLLaMA/comments/1ol8p88/powerful_new_stealth_models_on_design_arena/ | false | false | 4 | null | |
New AI workstation | 233 | Managed to fit in 4x RTX 3090 to a Phantek Server/Workstation case. Scores each card for roughly 800$. The PCIE riser on picture was too short (30cm) and had to be replaced with a 60cm one. The vertical mount is for Lian LI case, but manages to hook it up in the Phantek too. Mobo is ASRock romed8-2t, CPU is EPYC 7282 f... | 2025-10-31T22:36:32 | https://www.reddit.com/gallery/1ol8bfx | faileon | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ol8bfx | false | null | t3_1ol8bfx | /r/LocalLLaMA/comments/1ol8bfx/new_ai_workstation/ | false | false | 233 | null | |
4 steps to install google search mcp.json plugin in LM Studio in Ubuntu 24 | 1 | [removed] | 2025-10-31T22:27:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ol84k8/4_steps_to_install_google_search_mcpjson_plugin/ | OldEffective9726 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol84k8 | false | null | t3_1ol84k8 | /r/LocalLLaMA/comments/1ol84k8/4_steps_to_install_google_search_mcpjson_plugin/ | false | false | 1 | null | |
Integrating search functions in local LLM with LM Studio Ubuntu | 1 | 2025-10-31T22:24:39 | OldEffective9726 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ol822u | false | null | t3_1ol822u | /r/LocalLLaMA/comments/1ol822u/integrating_search_functions_in_local_llm_with_lm/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': '9cihszbdwiyf1', 'resolutions': [{'height': 104, 'url': 'https://preview.redd.it/9cihszbdwiyf1.png?width=108&crop=smart&auto=webp&s=825729fd82ec612e9dfb574c548847557fc98e95', 'width': 108}, {'height': 208, 'url': 'https://preview.redd.it/9cihszbdwiyf1.png?width=216&crop=smart&auto=we... | ||
Fine tuning using lora/qlora/grpo guide | 3 | hello guys , i am looking for guide to fine-tune llm using lora , the dataset is currently a set of pdfs and ppt , is there a guide for end-to-end ?
thank you for answer. | 2025-10-31T22:20:24 | https://www.reddit.com/r/LocalLLaMA/comments/1ol7yoy/fine_tuning_using_loraqloragrpo_guide/ | LahmeriMohamed | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol7yoy | false | null | t3_1ol7yoy | /r/LocalLLaMA/comments/1ol7yoy/fine_tuning_using_loraqloragrpo_guide/ | false | false | self | 3 | null |
For any LLM enthusiast in Finland you have decommission Super Computer equipped with 96 Nvidia A100 40Gb Pcie , if you live nearby Kajaani try contact company maybe you get them on discount ;) | 113 | [https://research.csc.fi/2025/09/25/installation-of-the-roihu-supercomputer-begins/](https://research.csc.fi/2025/09/25/installation-of-the-roihu-supercomputer-begins/) | 2025-10-31T22:16:56 | https://www.reddit.com/r/LocalLLaMA/comments/1ol7vwv/for_any_llm_enthusiast_in_finland_you_have/ | DeathRabit86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol7vwv | false | null | t3_1ol7vwv | /r/LocalLLaMA/comments/1ol7vwv/for_any_llm_enthusiast_in_finland_you_have/ | false | false | self | 113 | {'enabled': False, 'images': [{'id': 'VWnyEGHxfavLl9f1SOYeyyr_BqAFC3YiwG1h3HtSOTY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/VWnyEGHxfavLl9f1SOYeyyr_BqAFC3YiwG1h3HtSOTY.jpeg?width=108&crop=smart&auto=webp&s=1bf4afd2c4f15f1472cb35a61c0ae69b04ce8d76', 'width': 108}, {'height': 108, 'url': '... |
support for Minimax M2 has been merged into llama.cpp | 98 | 2025-10-31T22:11:26 | https://github.com/ggml-org/llama.cpp/pull/16831 | jacek2023 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1ol7ri8 | false | null | t3_1ol7ri8 | /r/LocalLLaMA/comments/1ol7ri8/support_for_minimax_m2_has_been_merged_into/ | false | false | 98 | {'enabled': False, 'images': [{'id': 'I_x1QIcREivfRZWw6RyYObzeaj8mdE6DXTQR3kx1F5I', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/I_x1QIcREivfRZWw6RyYObzeaj8mdE6DXTQR3kx1F5I.png?width=108&crop=smart&auto=webp&s=854ca0b949422008e887a477307149644720d224', 'width': 108}, {'height': 108, 'url': 'h... | ||
Milestones in open weights AI: what models shaped your journey? | 3 | When Llama 1 came out I started using local AI and got a bit fascinated by it running locally: this is where it clicked for me. Over time I tried a lot of models and some really stood out, and stayed in my history book. Here is my list of the best open weights models ever:
- Llama 1: where everything started for me
- ... | 2025-10-31T21:42:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ol74b2/milestones_in_open_weights_ai_what_models_shaped/ | synw_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol74b2 | false | null | t3_1ol74b2 | /r/LocalLLaMA/comments/1ol74b2/milestones_in_open_weights_ai_what_models_shaped/ | false | false | self | 3 | null |
MiniMax M2 Llama.cpp support merged | 48 | Aight, the MiniMax M2 support is officially in.
Remember that there is no support for the chat format yet, and for a good reason - there is currently no easy way to deal with the "interleaved" thinking format of the model.
I'm currently considering the intermediate solution - since the model makers recommend passin... | 2025-10-31T21:25:47 | https://github.com/ggml-org/llama.cpp/commit/0de0a01576772032008a689afc4d7c80685074c4 | ilintar | github.com | 1970-01-01T00:00:00 | 0 | {} | 1ol6qlk | false | null | t3_1ol6qlk | /r/LocalLLaMA/comments/1ol6qlk/minimax_m2_llamacpp_support_merged/ | false | false | default | 48 | {'enabled': False, 'images': [{'id': 'zIJQO0qHVJjeSmNiAhS1pkkPDhsRxWN-vwvuIbrWY3s', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/zIJQO0qHVJjeSmNiAhS1pkkPDhsRxWN-vwvuIbrWY3s.png?width=108&crop=smart&auto=webp&s=1d7e4a85e0dffd208e9ca39416a18e1367e9a5af', 'width': 108}, {'height': 108, 'url': 'h... |
Whisper implementation from scratch | 2 | I’m trying to deploy whisper to an edge device (orangepi ai pro 20T) it has an Ascend NPU, so i tried to quantize the model and then export it to om format to use the NPU acceleration (failed) and tried whisper.cpp and many other implementations and they have all failed.
my question here: is there any pure, from scratc... | 2025-10-31T21:01:58 | https://www.reddit.com/r/LocalLLaMA/comments/1ol66k5/whisper_implementation_from_scratch/ | overflow74 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol66k5 | false | null | t3_1ol66k5 | /r/LocalLLaMA/comments/1ol66k5/whisper_implementation_from_scratch/ | false | false | self | 2 | null |
Adding a RTX 5080 into a 2U server with OcuLink | 36 | As my P40 was no more up to the task, I needed a better card in my main server. The main issues were:
* It does not fit (NVidia makes sure of that)
* It is really hard to get a correct power cable for these new cards. I was afraid to damage my server motherboard.
So the alternative I found was to setup a OcuLink dock... | 2025-10-31T20:54:28 | https://www.reddit.com/gallery/1ol5zx5 | king_priam_of_Troy | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ol5zx5 | false | null | t3_1ol5zx5 | /r/LocalLLaMA/comments/1ol5zx5/adding_a_rtx_5080_into_a_2u_server_with_oculink/ | false | false | 36 | null | |
LM estudio nos works with minimax m2 | 0 | LM Studio Beta now supports MiniMax M2
Hey everyone,I've been lurking and learning from this community for a while now, and you've all been incredibly helpful. I wanted to give something back by sharing some exciting news:
LM Studio's beta version now has support for MiniMax M2
I apologize if I have misspelled a wor... | 2025-10-31T20:27:05 | Physics-Affectionate | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ol5c7x | false | null | t3_1ol5c7x | /r/LocalLLaMA/comments/1ol5c7x/lm_estudio_nos_works_with_minimax_m2/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'tnwatzpfbiyf1', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/tnwatzpfbiyf1.jpeg?width=108&crop=smart&auto=webp&s=6dc4cff51880582df0c584c2d69844060a5defa1', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/tnwatzpfbiyf1.jpeg?width=216&crop=smart&auto=w... | |
AMD Ryzen iGPU Benchmark: 4B Modelle schlagen 7B in Geschwindigkeit und Logik! (5600g Vega 7 Test) | 0 | Hallo LocalLLaMA-Community,
Ich habe eine umfangreiche Benchmark-Reihe mit LM Studio auf meinem Low-Power-System durchgeführt, um die beste Balance zwischen Geschwindigkeit und logischer Qualität für iGPU-Nutzer zu finden. Das Ergebnis ist überraschend: Die 4B-Klasse übertrifft die meisten 7B-Modelle sowohl in der Zuv... | 2025-10-31T20:04:48 | https://www.reddit.com/r/LocalLLaMA/comments/1ol4srg/amd_ryzen_igpu_benchmark_4b_modelle_schlagen_7b/ | Known_Ninja1985 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol4srg | false | null | t3_1ol4srg | /r/LocalLLaMA/comments/1ol4srg/amd_ryzen_igpu_benchmark_4b_modelle_schlagen_7b/ | false | false | self | 0 | null |
AMD Ryzen iGPU Benchmark: 4B Modelle schlagen 7B in Geschwindigkeit und Logik! (5600g Vega 7 Test) | 1 | Hallo LocalLLaMA-Community,
Ich habe eine umfangreiche Benchmark-Reihe mit LM Studio auf meinem Low-Power-System durchgeführt, um die beste Balance zwischen Geschwindigkeit und logischer Qualität für **iGPU-Nutzer** zu finden. Das Ergebnis ist überraschend: Die **4B-Klasse** übertrifft die meisten **7B-Modelle** sowoh... | 2025-10-31T19:54:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ol4k1q/amd_ryzen_igpu_benchmark_4b_modelle_schlagen_7b/ | Known_Ninja1985 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol4k1q | false | null | t3_1ol4k1q | /r/LocalLLaMA/comments/1ol4k1q/amd_ryzen_igpu_benchmark_4b_modelle_schlagen_7b/ | false | false | self | 1 | null |
MLX TTS transformer model finetuning | 1 | Does MLX support the finetuning of TTS transformer models like [CSM-1B](https://huggingface.co/mlx-community/csm-1b)?
I can't find infos on that in the official docs. | 2025-10-31T19:47:19 | https://www.reddit.com/r/LocalLLaMA/comments/1ol4d5u/mlx_tts_transformer_model_finetuning/ | IonizedRay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol4d5u | false | null | t3_1ol4d5u | /r/LocalLLaMA/comments/1ol4d5u/mlx_tts_transformer_model_finetuning/ | false | false | self | 1 | null |
Error using qwen3 vl 2b instruct q8kxl unsloth gguf in LM Studio | 3 | Failed to load model
error loading model: error loading model architecture: unknown model architecture: 'qwen3vl' | 2025-10-31T19:26:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ol3ud8/error_using_qwen3_vl_2b_instruct_q8kxl_unsloth/ | Charming_Barber_3317 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol3ud8 | false | null | t3_1ol3ud8 | /r/LocalLLaMA/comments/1ol3ud8/error_using_qwen3_vl_2b_instruct_q8kxl_unsloth/ | false | false | self | 3 | null |
Upcoming Coding Models? | 23 | Anything coming soon or later? Speculations/rumors?
Nothing from Llama for now. I think same on Microsoft too(or Phi new version coming?).
Would be great to have Coder (Both MOE & Dense) models like below.
* LFM Coder - [We're currently exploring the possibility of small coding models...](https://www.reddit.com/r/Lo... | 2025-10-31T19:19:17 | https://www.reddit.com/r/LocalLLaMA/comments/1ol3o4l/upcoming_coding_models/ | pmttyji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol3o4l | false | null | t3_1ol3o4l | /r/LocalLLaMA/comments/1ol3o4l/upcoming_coding_models/ | false | false | self | 23 | null |
What Qwen version do you want to see in Tiny-Qwen? | 10 | I previously open sourced this clean PyTorch re-implementation of Qwen inspired by Andrej Karpathy’s nanoGPT.
Repo link: https://github.com/Emericen/tiny-qwen
I’m adding support for Qwen 3 VL, but am curious what you prefer when you see this type of repo
[View Poll](https://www.reddit.com/poll/1ol3lp9) | 2025-10-31T19:16:31 | https://www.reddit.com/r/LocalLLaMA/comments/1ol3lp9/what_qwen_version_do_you_want_to_see_in_tinyqwen/ | No-Compote-6794 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol3lp9 | false | null | t3_1ol3lp9 | /r/LocalLLaMA/comments/1ol3lp9/what_qwen_version_do_you_want_to_see_in_tinyqwen/ | false | false | self | 10 | {'enabled': False, 'images': [{'id': 'uz5r-7-3kdV4kGH55os0igO6-ZOD0yZmARNBhsQKMOM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/uz5r-7-3kdV4kGH55os0igO6-ZOD0yZmARNBhsQKMOM.png?width=108&crop=smart&auto=webp&s=c88b23cb3f92121966e9b37faebc0e0b83e440eb', 'width': 108}, {'height': 108, 'url': 'h... |
Run Hugging Face, LM Studio, Ollama, and vLLM models locally and call them through an API | 3 | We’ve been working on Local Runners, a simple way to connect locally running models with a public API. You can now run models from Hugging Face, LM Studio, Ollama, or vLLM directly on your own machine and still interact with them through a secure API endpoint.
Think of it like ngrok but for AI models.
Everything stay... | 2025-10-31T19:15:08 | https://www.reddit.com/r/LocalLLaMA/comments/1ol3kgr/run_hugging_face_lm_studio_ollama_and_vllm_models/ | Sumanth_077 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol3kgr | false | null | t3_1ol3kgr | /r/LocalLLaMA/comments/1ol3kgr/run_hugging_face_lm_studio_ollama_and_vllm_models/ | false | false | self | 3 | null |
[Project] Ollmini Devbox - Desktop RAG Chat with Think-Block Rendering, Tool Calling & Dual Embedding Models (>8GB VRAM) | 1 | [removed] | 2025-10-31T18:56:30 | https://www.reddit.com/r/LocalLLaMA/comments/1ol33ia/project_ollmini_devbox_desktop_rag_chat_with/ | Beerbandit23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol33ia | false | null | t3_1ol33ia | /r/LocalLLaMA/comments/1ol33ia/project_ollmini_devbox_desktop_rag_chat_with/ | false | false | self | 1 | null |
Can't choose a topic for my thesis (bachelor's degree) | 2 | Hello everyone. I don't have any practical experience with LLM and therefore I have no idea what can I study in this field. I find LLMs very interesting so I decided to ask some knowledgeable people. I was thinking about something more research-oriented, although I will welcome any ideas.
What exactly should I pic... | 2025-10-31T18:55:41 | https://www.reddit.com/r/LocalLLaMA/comments/1ol32rd/cant_choose_a_topic_for_my_thesis_bachelors_degree/ | TriKurrDurrr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol32rd | false | null | t3_1ol32rd | /r/LocalLLaMA/comments/1ol32rd/cant_choose_a_topic_for_my_thesis_bachelors_degree/ | false | false | self | 2 | null |
qwen2.5vl:32b is saving me $1400 from my HOA | 441 | Over this year I finished putting together my local LLM machine with a quad 3090 setup. Built a few workflows with it but like most of you, just wanted to experiment with local models and for the sake of burning tokens lol.
Then in July, my ceiling got damaged from an upstairs leak. HOA says "not our problem." I'm pre... | 2025-10-31T18:53:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ol30e5/qwen25vl32b_is_saving_me_1400_from_my_hoa/ | jedsk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol30e5 | false | null | t3_1ol30e5 | /r/LocalLLaMA/comments/1ol30e5/qwen25vl32b_is_saving_me_1400_from_my_hoa/ | false | false | self | 441 | null |
Unbound In-Character Reasoning Model - Apollo-V0.1-4B-Thinking | 61 | An experimental model with many of its creative inhibitions lifted. Its internal reasoning process adapts to the persona you assign (via the system prompt), allowing it to explore a wider spectrum of themes. This is a V0.1 preview for testing. More refined versions (non-reasoning variants as well) are planned. Follow f... | 2025-10-31T18:40:35 | https://huggingface.co/AllThingsIntel/Apollo-V0.1-4B-Thinking | AllThingsIntel | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ol2oxw | false | null | t3_1ol2oxw | /r/LocalLLaMA/comments/1ol2oxw/unbound_incharacter_reasoning_model/ | false | false | nsfw | 61 | {'enabled': False, 'images': [{'id': 'jpD046tOQv3KrkaMiXbtM_I_nzl707XEWwi2cm-XvZI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/jpD046tOQv3KrkaMiXbtM_I_nzl707XEWwi2cm-XvZI.png?width=108&crop=smart&auto=webp&s=5424b2f856c1c331a54d939ebb886276b0ec44c0', 'width': 108}, {'height': 116, 'url': 'h... |
I fine tuned a (small) model to help with reasoning backfill on old/non-reasoning datasets | 4 | I wanted to play around with trying to synthesize reasoning traces for older/chat datasets where reasoning wasn't conventionalized yet. I wasn't able to find a model that could do the job, so I tried throwing one together by moving the logic around from existing reasoning datasets to see if we could infer reasoning fro... | 2025-10-31T18:39:58 | https://huggingface.co/joeyzero/Qwen3-4B-Reasoning-Backfill-v0.1 | joeyzero | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ol2odj | false | null | t3_1ol2odj | /r/LocalLLaMA/comments/1ol2odj/i_fine_tuned_a_small_model_to_help_with_reasoning/ | false | false | default | 4 | {'enabled': False, 'images': [{'id': 'XlylphZC1EXPPsyoBwqV24OccqWD2HchWXqXQLjgX7U', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/XlylphZC1EXPPsyoBwqV24OccqWD2HchWXqXQLjgX7U.png?width=108&crop=smart&auto=webp&s=6a847a35cde31a27785c5e3b5f1d3a7d0d33ce01', 'width': 108}, {'height': 216, 'url': '... |
LLM Security | 1 | Has the level of importance that the market has been giving to LLM security, been increasing? Or are we still in the “early SQL injection” phase? Are there established players in this market or just start-ups (if, which ones)? | 2025-10-31T18:14:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ol20rz/llm_security/ | Any-Aioli8177 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol20rz | false | null | t3_1ol20rz | /r/LocalLLaMA/comments/1ol20rz/llm_security/ | false | false | self | 1 | null |
I'm currently solving a problem I have with Ollama and LM Studio. | 10 | I am currently working on [rbee (formerly named llama-orch)](https://github.com/veighnsche/llama-orch). rbee is an Ollama- or LM Studio–like program.
**How is rbee different?**
In addition to running on your local machine, it can securely connect to all the GPUs in your local network. You can choose exactly which GP... | 2025-10-31T18:11:11 | https://www.reddit.com/gallery/1ol1xji | Sileniced | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ol1xji | false | null | t3_1ol1xji | /r/LocalLLaMA/comments/1ol1xji/im_currently_solving_a_problem_i_have_with_ollama/ | false | false | 10 | null | |
Mergekit has been re-licensed under GNU LGPL v3 | 24 | Kinda self-promo ? But also feel it's worth shouting out anyways, mergekit is back to LGPL license!
https://github.com/arcee-ai/mergekit
https://www.arcee.ai/blog/mergekit-returns-to-its-roots | 2025-10-31T18:08:57 | https://www.reddit.com/r/LocalLLaMA/comments/1ol1vdm/mergekit_has_been_relicensed_under_gnu_lgpl_v3/ | noneabove1182 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol1vdm | false | null | t3_1ol1vdm | /r/LocalLLaMA/comments/1ol1vdm/mergekit_has_been_relicensed_under_gnu_lgpl_v3/ | false | false | self | 24 | {'enabled': False, 'images': [{'id': 'Okb1JZQ7LkC-B4zXSJ7UNcR5aCmnrLgzHTHH_o2ZpbA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Okb1JZQ7LkC-B4zXSJ7UNcR5aCmnrLgzHTHH_o2ZpbA.png?width=108&crop=smart&auto=webp&s=9dc7a3c453495356cad4989c6ef72d6353c7cbea', 'width': 108}, {'height': 108, 'url': 'h... |
gradient parallax decentralized llm | 0 | why havent i seen anyone on this sub post about this? it seems quite powerful and could greatly lower the cost of entry. has anyone tried it? | 2025-10-31T18:01:47 | https://x.com/gradient_hq/status/1983383325416055287?s=46&t=NALxTuo-Dxk_YtpvmtAtug | lidekwhatname | x.com | 1970-01-01T00:00:00 | 0 | {} | 1ol1ojs | false | null | t3_1ol1ojs | /r/LocalLLaMA/comments/1ol1ojs/gradient_parallax_decentralized_llm/ | false | false | default | 0 | null |
Hypothetical: if you had a gb300 nvl72 , what would you do with it? | 8 | Hypothetical: Suppose you lived in an alternative world, where gb300 nvl72s were affordable for an avg enthusiast and you had one , what would you do with it? | 2025-10-31T17:29:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ol0tvf/hypothetical_if_you_had_a_gb300_nvl72_what_would/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol0tvf | false | null | t3_1ol0tvf | /r/LocalLLaMA/comments/1ol0tvf/hypothetical_if_you_had_a_gb300_nvl72_what_would/ | false | false | self | 8 | null |
Should I wait until Black Friday to buy the MINISFORUM MS-S1 Max? | 0 | Hey Guys, there is currently a halloween sale for the Minisforum Strix Halo. It can be purchased for 2,150 USD.
Do you think it could be strategic to wait a little less than a month for Black Friday sales? I am not too familiar with how black friday affects the tech prices.... It would be a shame to buy now and t... | 2025-10-31T17:27:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ol0sa5/should_i_wait_until_black_friday_to_buy_the/ | Excellent_Koala769 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ol0sa5 | false | null | t3_1ol0sa5 | /r/LocalLLaMA/comments/1ol0sa5/should_i_wait_until_black_friday_to_buy_the/ | false | false | self | 0 | null |
Drummer's Rivermind™ 24B v1 - A spooky future for LLMs, Happy Halloween! | 77 | The older brother of [https://huggingface.co/TheDrummer/Rivermind-12B-v1](https://huggingface.co/TheDrummer/Rivermind-12B-v1) | 2025-10-31T16:58:28 | https://huggingface.co/TheDrummer/Rivermind-24B-v1 | TheLocalDrummer | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ol006s | false | null | t3_1ol006s | /r/LocalLLaMA/comments/1ol006s/drummers_rivermind_24b_v1_a_spooky_future_for/ | false | false | default | 77 | {'enabled': False, 'images': [{'id': 'cJYTAXorc18tRHqzBZaT1gjlzMY9WdV4LW05HQehJqQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/cJYTAXorc18tRHqzBZaT1gjlzMY9WdV4LW05HQehJqQ.png?width=108&crop=smart&auto=webp&s=2b7d6a1c166ced8cc154cc650231025969485731', 'width': 108}, {'height': 116, 'url': 'h... |
pewdiepie dropped a video about running local ai | 943 | 2025-10-31T16:28:56 | https://www.youtube.com/watch?v=qw4fDU18RcU | topfpflanze187 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1okz8qz | false | {'oembed': {'author_name': 'PewDiePie', 'author_url': 'https://www.youtube.com/@PewDiePie', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/qw4fDU18RcU?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; p... | t3_1okz8qz | /r/LocalLLaMA/comments/1okz8qz/pewdiepie_dropped_a_video_about_running_local_ai/ | false | false | default | 943 | {'enabled': False, 'images': [{'id': 'WddxiFHLc3dMB9LBPGHmNWXXrzglB78uxpSOk1Y4d6E', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/WddxiFHLc3dMB9LBPGHmNWXXrzglB78uxpSOk1Y4d6E.jpeg?width=108&crop=smart&auto=webp&s=81ae433e5b52cd3bb13282d643d5efae83d1a280', 'width': 108}, {'height': 162, 'url': '... | |
What is the purpose/function of the lightbulb setting in Windows Ollama? | 0 | As per the title, what is the purpose/function of the "low/medium/high" lightbulb setting in the Windows Ollama GUI?
Thanks! | 2025-10-31T16:27:13 | https://www.reddit.com/r/LocalLLaMA/comments/1okz73o/what_is_the_purposefunction_of_the_lightbulb/ | CellMan28 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okz73o | false | null | t3_1okz73o | /r/LocalLLaMA/comments/1okz73o/what_is_the_purposefunction_of_the_lightbulb/ | false | false | self | 0 | null |
What's the difference between f16 and bf16 mmproj GGUF files for Qwen3-VL? | 18 | Sorry if this is a stupid question. Some quant providers upload both, along with f32. Isn't the model originally in bf16? Which is higher quality. Thanks a lot for any help. | 2025-10-31T16:26:40 | https://www.reddit.com/r/LocalLLaMA/comments/1okz6ko/whats_the_difference_between_f16_and_bf16_mmproj/ | windows_error23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okz6ko | false | null | t3_1okz6ko | /r/LocalLLaMA/comments/1okz6ko/whats_the_difference_between_f16_and_bf16_mmproj/ | false | false | self | 18 | null |
What has been your experience with high latency in your AI coding tools? | 11 | Curious about everyone’s experience with high latency in your AI applications.
High latency seems to be a pretty common issue I see talked about here.
What have you tried and what has worked? What hasn’t worked?
| 2025-10-31T16:22:57 | https://www.reddit.com/r/LocalLLaMA/comments/1okz32u/what_has_been_your_experience_with_high_latency/ | InceptionAI_Tom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okz32u | false | null | t3_1okz32u | /r/LocalLLaMA/comments/1okz32u/what_has_been_your_experience_with_high_latency/ | false | false | self | 11 | null |
Has anyone found reliable ways to access OpenAI APIs from China? | 0 | Hey all,
I’m curious to hear from developers based in regions like China (or anywhere OpenAI blocks API access). With the recent geo-restrictions, are you finding any legit, sustainable methods for connecting to OpenAI’s API?
* Are VPNs still working for you, or have you run into blocks and rate limiting?
* Has a... | 2025-10-31T16:09:58 | https://www.reddit.com/r/LocalLLaMA/comments/1okyqqi/has_anyone_found_reliable_ways_to_access_openai/ | Silver-Snow1595 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okyqqi | false | null | t3_1okyqqi | /r/LocalLLaMA/comments/1okyqqi/has_anyone_found_reliable_ways_to_access_openai/ | false | false | self | 0 | null |
8-Pin PCIE (single) to 12VHPWR - Cable problem solved | 4 | I have a Corsair power supply, which uses Type 4 cables in my LLM server. It's an asus WRX80E-SAGE motherboard, so theres 7 pci slots. Ideal for my bootstrapped, single slot Ada rtx gpus. The one problem I've had is not enough ports on the psu to run 6 gpus (which is what I've built).
I'd been looking for a custom p... | 2025-10-31T15:54:43 | https://www.reddit.com/gallery/1okybza | richardbaxter | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1okybza | false | null | t3_1okybza | /r/LocalLLaMA/comments/1okybza/8pin_pcie_single_to_12vhpwr_cable_problem_solved/ | false | false | 4 | null | |
Hardware-requirements for different models? | 1 | Hey everyone,
I’m seeing more and more GPUs on the market with decent VRAM that aren’t from NVIDIA, and I’m curious about compatibility.
I know it’s possible to run lots of models on different hardware (for example, on my M4 Mac). But here’s my question:
If my model-serving tool (like vLLM) supports a given GPU, ca... | 2025-10-31T15:53:32 | https://www.reddit.com/r/LocalLLaMA/comments/1okyatu/hardwarerequirements_for_different_models/ | No_Nail_1394 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okyatu | false | null | t3_1okyatu | /r/LocalLLaMA/comments/1okyatu/hardwarerequirements_for_different_models/ | false | false | self | 1 | null |
Qwen3-VL GGUF! | 153 | Have not tried any yet, multiple other Veterans have uploaded GGUF Quants, linking to unsloth for their guide and all available models from 2B-32B.
[Hugging Face Unsloth](https://huggingface.co/unsloth)
[Unsloth Guide](https://docs.unsloth.ai/models/qwen3-vl-run-and-fine-tune) | 2025-10-31T15:46:07 | https://www.reddit.com/r/LocalLLaMA/comments/1oky3un/qwen3vl_gguf/ | khubebk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oky3un | false | null | t3_1oky3un | /r/LocalLLaMA/comments/1oky3un/qwen3vl_gguf/ | false | false | self | 153 | {'enabled': False, 'images': [{'id': 'rwedkgKC292WXtVkRTFrnQdmEFp-chPjwmYAiGsq2kA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/rwedkgKC292WXtVkRTFrnQdmEFp-chPjwmYAiGsq2kA.png?width=108&crop=smart&auto=webp&s=305a70e8c82e5c0a94fb3ba2ee9df26c9b46914f', 'width': 108}, {'height': 116, 'url': 'h... |
good chance Pewdiepie is in the LocalLLama subreddit | 2 | [removed] | 2025-10-31T15:38:54 | Odd-Ordinary-5922 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okxwww | false | null | t3_1okxwww | /r/LocalLLaMA/comments/1okxwww/good_chance_pewdiepie_is_in_the_localllama/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': 'gmgkrkouvgyf1', 'resolutions': [{'height': 76, 'url': 'https://preview.redd.it/gmgkrkouvgyf1.png?width=108&crop=smart&auto=webp&s=1d14d68a7c1fb8a4623e9b78daa74203fb56edc8', 'width': 108}, {'height': 153, 'url': 'https://preview.redd.it/gmgkrkouvgyf1.png?width=216&crop=smart&auto=web... | |
good chance pewdiepie is in the locallama subreddit | 1 | [removed] | 2025-10-31T15:36:46 | https://www.youtube.com/watch?v=qw4fDU18RcU | Odd-Ordinary-5922 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1okxuyi | false | {'oembed': {'author_name': 'PewDiePie', 'author_url': 'https://www.youtube.com/@PewDiePie', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/qw4fDU18RcU?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; p... | t3_1okxuyi | /r/LocalLLaMA/comments/1okxuyi/good_chance_pewdiepie_is_in_the_locallama/ | false | false | default | 1 | null |
Theres a way to disable "thinking" on the qwen's 3 model family? | 0 | I was so excited to test the new qwen 3 vl, but i remembered that this are "thinker" model, and super slow in my setup. Theres any solution to disable this shi-ops, this wonderful function? | 2025-10-31T15:22:31 | https://www.reddit.com/r/LocalLLaMA/comments/1okxhla/theres_a_way_to_disable_thinking_on_the_qwens_3/ | ArcherAdditional2478 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okxhla | false | null | t3_1okxhla | /r/LocalLLaMA/comments/1okxhla/theres_a_way_to_disable_thinking_on_the_qwens_3/ | false | false | self | 0 | null |
For those who’ve been following my dev journey, the first AgentTrace milestone 👀 | 4 | For those who’ve been following the process, here’s the first real visual milestone for AgentTrace, my project to see how AI agents think.
It’s a Cognitive Flow Visualizer that maps every step of an agent’s reasoning, so instead of reading endless logs, you can actually see the decision flow:
🧩 Nodes for Input, Acti... | 2025-10-31T15:11:46 | AdVivid5763 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okx7kq | false | null | t3_1okx7kq | /r/LocalLLaMA/comments/1okx7kq/for_those_whove_been_following_my_dev_journey_the/ | false | false | default | 4 | {'enabled': True, 'images': [{'id': 'zxfgomk6rgyf1', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/zxfgomk6rgyf1.jpeg?width=108&crop=smart&auto=webp&s=26391aa3190ab8e813a1108a44a88e622b4bb366', 'width': 108}, {'height': 116, 'url': 'https://preview.redd.it/zxfgomk6rgyf1.jpeg?width=216&crop=smart&auto=w... | |
Future of APUs for local AI? | 5 | What do you think about the future of APUs? Will they become dominant over GPUs for local AI inferencing? | 2025-10-31T15:03:57 | https://www.reddit.com/r/LocalLLaMA/comments/1okx07d/future_of_apus_for_local_ai/ | Excellent_Koala769 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okx07d | false | null | t3_1okx07d | /r/LocalLLaMA/comments/1okx07d/future_of_apus_for_local_ai/ | false | false | self | 5 | null |
Which open-source LLMs support schema? | 0 | When exploring the AI SDK and local LLMs, I encountered an issue with the \`schema\` support.
I receive
`[AI_APICallError]: Bad Request`
using a few local LLMs, but the same code works fine with gemini-2.0-flash.
Could you recommend open-source LLMs that support schema? | 2025-10-31T14:32:54 | https://www.reddit.com/r/LocalLLaMA/comments/1okw7jh/which_opensource_llms_support_schema/ | ThingRexCom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okw7jh | false | null | t3_1okw7jh | /r/LocalLLaMA/comments/1okw7jh/which_opensource_llms_support_schema/ | false | false | self | 0 | null |
How to Create a Personalized AI (Free & Easy Guide). I made this English blog post after you told me my Spanish video wasn't accessible. Hope this helps! | 7 | Hey Reddit,
A little while ago, I shared a YouTube video I made about creating a personalized AI in 5 minutes. The feedback was great, but many of you pointed out (correctly!) that it was in Spanish, and most of you couldn't understand it.
I really appreciate that feedback. My goal was to help people, so I took your ... | 2025-10-31T14:27:58 | https://www.reddit.com/r/LocalLLaMA/comments/1okw32m/how_to_create_a_personalized_ai_free_easy_guide_i/ | jokiruiz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okw32m | false | null | t3_1okw32m | /r/LocalLLaMA/comments/1okw32m/how_to_create_a_personalized_ai_free_easy_guide_i/ | false | false | self | 7 | {'enabled': False, 'images': [{'id': 'RDwxydl3NcY3u1C-be6A5a05NS0rK9eFKNtM0RTOjgo', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/RDwxydl3NcY3u1C-be6A5a05NS0rK9eFKNtM0RTOjgo.png?width=108&crop=smart&auto=webp&s=0baa05da61a6f7ba55d1a76d3a5fda4510113615', 'width': 108}, {'height': 216, 'url': '... |
Run Kyutai Unmute on a Runpod L40s single-GPU instance | 2 | I managed to get Kyutai Unmute running on Runpod.
It was non-trivial and required some hacks, which I've included in the PR, along with a complete tested set of instructions.
They already have a live demo on [unmute.sh](http://unmute.sh) if you just want to test it, however I wanted to access it directly from an iO... | 2025-10-31T14:23:18 | https://github.com/kyutai-labs/unmute/pull/151 | tleyden | github.com | 1970-01-01T00:00:00 | 0 | {} | 1okvyud | false | null | t3_1okvyud | /r/LocalLLaMA/comments/1okvyud/run_kyutai_unmute_on_a_runpod_l40s_singlegpu/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'qWsKwKkma6G1TTsoo_TPlT6sNcLdv1bk2Tv1wEaudHk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/qWsKwKkma6G1TTsoo_TPlT6sNcLdv1bk2Tv1wEaudHk.png?width=108&crop=smart&auto=webp&s=194217473b988ae0b97de7799c2239228b984100', 'width': 108}, {'height': 108, 'url': 'h... | |
Why the hype around ultra small models like Granite4_350m? What are the actual use cases for these models? | 84 | I get that small models can run on edge devices, but what are people actually planning on using a 350m parameter model for in the real world? I’m just really curious as to what use cases developers see these fitting into vs. using 1b, 4b, or 8b? | 2025-10-31T13:14:05 | https://www.reddit.com/r/LocalLLaMA/comments/1oku9og/why_the_hype_around_ultra_small_models_like/ | Porespellar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oku9og | false | null | t3_1oku9og | /r/LocalLLaMA/comments/1oku9og/why_the_hype_around_ultra_small_models_like/ | false | false | self | 84 | null |
Granite-4.0-H-1B as a thesaurus | 16 | 2025-10-31T12:48:50 | DHasselhoff77 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okto5m | false | null | t3_1okto5m | /r/LocalLLaMA/comments/1okto5m/granite40h1b_as_a_thesaurus/ | false | false | 16 | {'enabled': True, 'images': [{'id': 'Saj7yc58LXDT3oyUD80TSOn4RjA0Y-OMZKcdTMz0Xb8', 'resolutions': [{'height': 128, 'url': 'https://preview.redd.it/jee57z2h1gyf1.png?width=108&crop=smart&auto=webp&s=26cc04805f36f54e9c10fe5cc20cb334637adadf', 'width': 108}, {'height': 256, 'url': 'https://preview.redd.it/jee57z2h1gyf1.pn... | |||
Is it possible to use vram like ram is multigpu setups? | 9 | This is a weird question, but I mean this in terms of using MOE models.
I have 2 MI50s and a 7900 xt, which I have the 7900xt in my gaming PC.
The 7900xt has a far stronger gpu chip while the mi50s have more faster vram.
Given that is is very popular to use a gpu for prompt processing for MOE models while forcing th... | 2025-10-31T12:04:40 | https://www.reddit.com/r/LocalLLaMA/comments/1oksprm/is_it_possible_to_use_vram_like_ram_is_multigpu/ | opoot_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oksprm | false | null | t3_1oksprm | /r/LocalLLaMA/comments/1oksprm/is_it_possible_to_use_vram_like_ram_is_multigpu/ | false | false | self | 9 | null |
Could you run minimax-m2 locally? | 2 | I'm trying to run \`minimax-m2\` IQ1\_M on my local Ubuntu with 8GB AMD GPU using LM studio but get \`error loading model: error loading model architecture: unknown model architecture: 'minimax-m2'\` . Any ideas how to fix this? | 2025-10-31T11:59:58 | https://www.reddit.com/r/LocalLLaMA/comments/1oksly9/could_you_run_minimaxm2_locally/ | blnkslt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oksly9 | false | null | t3_1oksly9 | /r/LocalLLaMA/comments/1oksly9/could_you_run_minimaxm2_locally/ | false | false | self | 2 | null |
What are your thoughts on this? | 0 | Tech Mahindra is currently developing an indigenous LLM with 1 trillion parameters.
Original post link: https://www.reddit.com/r/AI_India/comments/1oet3kl/tech_mahindra_is_currently_developing_an/ | 2025-10-31T11:53:53 | SrijSriv211 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okshn9 | false | null | t3_1okshn9 | /r/LocalLLaMA/comments/1okshn9/what_are_your_thoughts_on_this/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'cu4633wprfyf1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/cu4633wprfyf1.png?width=108&crop=smart&auto=webp&s=79696af26a1347dc773fef007e94b9ffab627408', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/cu4633wprfyf1.png?width=216&crop=smart&auto=we... | |
Introducing Kimi CLI Technical Preview & Kimi For Coding | 7 | From Kimi ai on X: [https://x.com/Kimi\_Moonshot/status/1984207733177090274](https://x.com/Kimi_Moonshot/status/1984207733177090274)
[https://www.kimi.com/coding/docs/en/benefits.html](https://www.kimi.com/coding/docs/en/benefits.html)
GitHub: [https://github.com/MoonshotAI/kimi-cli](https://github.com/MoonshotAI/k... | 2025-10-31T11:15:59 | https://www.reddit.com/r/LocalLLaMA/comments/1okrrt1/introducing_kimi_cli_technical_preview_kimi_for/ | Nunki08 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okrrt1 | false | null | t3_1okrrt1 | /r/LocalLLaMA/comments/1okrrt1/introducing_kimi_cli_technical_preview_kimi_for/ | false | false | self | 7 | null |
Anyone know of any voice cloning service that can produce bulk? | 0 | I want to find a service or software that can run generate hours of script from a voice clone, for YouTube content creation. Does anyone know how? All the ones I have found are either hundreds of dollars or max out at 10 minutes per month | 2025-10-31T10:03:51 | https://www.reddit.com/r/LocalLLaMA/comments/1okqi85/anyone_know_of_any_voice_cloning_service_that_can/ | Ill_Yak121 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okqi85 | false | null | t3_1okqi85 | /r/LocalLLaMA/comments/1okqi85/anyone_know_of_any_voice_cloning_service_that_can/ | false | false | self | 0 | null |
Looking for Advice: Local Inference Setup for Multiple LLMs (VLLM, Embeddings + Chat + Reranking) | 4 | I’ve been experimenting with local LLM inference and have run into limitations with my current hardware.
I’m using VLLM on an RTX 4070 (12GB), and at the moment I cannot reliably run more than one small model at the same time.
Even a 4B model can sometimes go OOM even without other model because offloading doesn't... | 2025-10-31T09:48:56 | https://www.reddit.com/r/LocalLLaMA/comments/1okq9e6/looking_for_advice_local_inference_setup_for/ | ahaw_work | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okq9e6 | false | null | t3_1okq9e6 | /r/LocalLLaMA/comments/1okq9e6/looking_for_advice_local_inference_setup_for/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'YKDHS-WN23MzoJyL-QSJPxfIwGqfP8Fqq7KQR0fdoz0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/YKDHS-WN23MzoJyL-QSJPxfIwGqfP8Fqq7KQR0fdoz0.png?width=108&crop=smart&auto=webp&s=a509b70cc73d5972ead2e0ae87831b14bf5016c6', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone else running their whole AI stack as Proxmox LXC containers? Im currently using Open WebUI as front-end, LiteLLM as a router and A vLLM container per model as back-ends | 34 | I have not implemented it yet, but I believe it should be possible for LiteLLM to interface with the Proxmox API and dynamically turn on and off vLLM containers depening on what model users select (in Open WebUI). Does anyone have any experience with this?
I want to add a container for n8n for automation workflows (c... | 2025-10-31T09:44:18 | AFruitShopOwner | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okq6ms | false | null | t3_1okq6ms | /r/LocalLLaMA/comments/1okq6ms/anyone_else_running_their_whole_ai_stack_as/ | false | false | 34 | {'enabled': True, 'images': [{'id': 'yKHE6aJy0jGn9sPCVe-in9j_-q-AwRSjNY7an2rlTEQ', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/gva8eiw9weyf1.png?width=108&crop=smart&auto=webp&s=880dff8cf33474475feac9eedf9e87fa88b79341', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/gva8eiw9weyf1.png... | ||
Recommendation for powerful llm in Art History and Design thinking? | 2 | Hello fellow Redditors,
I'm reaching out to the community as I find myself in need of some expert guidance. I've recently started exploring local Language Learning Models but I must confess that I'm still a bit of a novice in this field.
My goal is to find a powerful language model, similar to ChatGPT, that can help ... | 2025-10-31T09:17:10 | https://www.reddit.com/r/LocalLLaMA/comments/1okpryh/recommendation_for_powerful_llm_in_art_history/ | Live-Sky-1186 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okpryh | false | null | t3_1okpryh | /r/LocalLLaMA/comments/1okpryh/recommendation_for_powerful_llm_in_art_history/ | false | false | self | 2 | null |
Both Cursor and Cognition (Windsurf) new models are speculated to be built on Chinese base models? | 404 | Hey, what's going on? Are Chinese models saving American startups? | 2025-10-31T09:13:34 | Successful-Newt1517 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okppxs | false | null | t3_1okppxs | /r/LocalLLaMA/comments/1okppxs/both_cursor_and_cognition_windsurf_new_models_are/ | false | false | default | 404 | {'enabled': True, 'images': [{'id': 'ej8yokr9zeyf1', 'resolutions': [{'height': 117, 'url': 'https://preview.redd.it/ej8yokr9zeyf1.jpeg?width=108&crop=smart&auto=webp&s=19fd99fc2f5382a09ddef7f803c895fd84e9dd35', 'width': 108}, {'height': 235, 'url': 'https://preview.redd.it/ej8yokr9zeyf1.jpeg?width=216&crop=smart&auto=... | |
Hello everyone! | 1 | **Hello everyone!**
**It's a pleasure to meet you all.**
**This is my first time greeting you.**
**I've been experimenting with LLMs on my own, and finally,**
**I'm writing my first post.**
**I look forward to working with you all** | 2025-10-31T09:11:14 | https://www.reddit.com/r/LocalLLaMA/comments/1okponk/hello_everyone/ | Few-Parsnip4854 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okponk | false | null | t3_1okponk | /r/LocalLLaMA/comments/1okponk/hello_everyone/ | false | false | self | 1 | null |
Glm Rickrolled me😭😭😭 | 34 | [Chat](https://chat.z.ai/s/1aead084-3e5f-41d4-94ef-e8a0fd8ac04a)
[Space](https://chat.z.ai/space/y0u7899c45v1-art) | 2025-10-31T08:39:36 | Brave-Hold-9389 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1okp7kq | false | null | t3_1okp7kq | /r/LocalLLaMA/comments/1okp7kq/glm_rickrolled_me/ | false | false | default | 34 | {'enabled': True, 'images': [{'id': '4m02xmp1teyf1', 'resolutions': [{'height': 53, 'url': 'https://preview.redd.it/4m02xmp1teyf1.png?width=108&crop=smart&auto=webp&s=b69f7a25d73afc5686360438f7814d47cdf3d942', 'width': 108}, {'height': 107, 'url': 'https://preview.redd.it/4m02xmp1teyf1.png?width=216&crop=smart&auto=web... | |
vLLM, how does it use empty VRAM region? | 12 | Hello,
Trying to understand how vLLM works?
So say if I have single 96GB GPU.
And my model fits in 16GB... that gives me 80GB spare VRAM...
1. Now if i send 3 concurrent requests to vLLM each of 10000 tokens, how would vLLM process that? I guess each of those 10000 tokens use up VRAM... and then what magic doe... | 2025-10-31T08:35:11 | https://www.reddit.com/r/LocalLLaMA/comments/1okp58l/vllm_how_does_it_use_empty_vram_region/ | PlanetMercurial | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1okp58l | false | null | t3_1okp58l | /r/LocalLLaMA/comments/1okp58l/vllm_how_does_it_use_empty_vram_region/ | false | false | self | 12 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.