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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Anyone experience with TeichAI/gpt-oss-20b-glm-4.6-distill-GGUF? | 0 | [https://huggingface.co/TeichAI/gpt-oss-20b-glm-4.6-distill-GGUF](https://huggingface.co/TeichAI/gpt-oss-20b-glm-4.6-distill-GGUF)
It's a distill between open source GPT and GLM 4.6 and it supposedly offers 22B at only 12.1GB for Q8.
What can one expect from this? | 2025-11-09T16:16:56 | https://www.reddit.com/r/LocalLLaMA/comments/1osncv3/anyone_experience_with/ | dreamyrhodes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osncv3 | false | null | t3_1osncv3 | /r/LocalLLaMA/comments/1osncv3/anyone_experience_with/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '9-DqjFsfEUVTQC3NblMF3AMsZZEh6ozWXRCgnzU1fN4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9-DqjFsfEUVTQC3NblMF3AMsZZEh6ozWXRCgnzU1fN4.png?width=108&crop=smart&auto=webp&s=99ba4de16338c74bd1799ffa967c1bbfba816b86', 'width': 108}, {'height': 116, 'url': 'h... |
Is the RTX 5090 that good of a deal? | 143 |
Trying to find a model agnostic approach to estimate which cards to pick | 2025-11-09T15:53:07 | GreenTreeAndBlueSky | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1osmr6i | false | null | t3_1osmr6i | /r/LocalLLaMA/comments/1osmr6i/is_the_rtx_5090_that_good_of_a_deal/ | false | false | default | 143 | {'enabled': True, 'images': [{'id': 'v9cx89gr690g1', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/v9cx89gr690g1.png?width=108&crop=smart&auto=webp&s=65fa2b49bbfacb7931b3a0f04c09a8b6d84cff90', 'width': 108}, {'height': 129, 'url': 'https://preview.redd.it/v9cx89gr690g1.png?width=216&crop=smart&auto=web... | |
CodeWiki: Research-Grade Repository Documentation at Scale [Open Source] | 30 | Hey r/LocalLLaMA communities!
I'm excited to share **CodeWiki**, our newly published research project from FSoft-AI4Code that tackles automated repository-level documentation generation. After seeing DeepWiki and its open-source implementations, we thought the community might appreciate a different approach backed by a... | 2025-11-09T15:49:05 | https://v.redd.it/98rdo80x590g1 | Prize_Cost_7706 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1osmnlp | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/98rdo80x590g1/DASHPlaylist.mpd?a=1765295357%2CMTkwMGM3MTRjOWI4ODYzNjY0MGJiZGEyY2ZmN2JjOTNjMjA2OTc5MzM2ZGM2MzdlOGMzYzBhNmQ2ZGE2Mjg1Ng%3D%3D&v=1&f=sd', 'duration': 68, 'fallback_url': 'https://v.redd.it/98rdo80x590g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1osmnlp | /r/LocalLLaMA/comments/1osmnlp/codewiki_researchgrade_repository_documentation/ | false | false | 30 | {'enabled': False, 'images': [{'id': 'OWYxbGQ4MHg1OTBnMQhj1jeEZTm3kJ-2tjF6W5cKTD-ayqoaa3bxlqaqIxQQ', 'resolutions': [{'height': 70, 'url': 'https://external-preview.redd.it/OWYxbGQ4MHg1OTBnMQhj1jeEZTm3kJ-2tjF6W5cKTD-ayqoaa3bxlqaqIxQQ.png?width=108&crop=smart&format=pjpg&auto=webp&s=5ab4a8635cd46de2e55ce294db87a953a4742... | |
ELI5: why does nvidia always sell their consumer gpus below market price? | 0 | It seems like it always makes them run out super quick and then the difference is pocketed by resellers. Why? I feel like I'm missing something. | 2025-11-09T15:46:25 | https://www.reddit.com/r/LocalLLaMA/comments/1osml7y/eli5_why_does_nvidia_always_sell_their_consumer/ | GreenTreeAndBlueSky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osml7y | false | null | t3_1osml7y | /r/LocalLLaMA/comments/1osml7y/eli5_why_does_nvidia_always_sell_their_consumer/ | false | false | self | 0 | null |
Hobby level workstation: build advice | 2 | I’m looking for some advice on building a small workstation that sits separately to my main PC.
Its primary use-case would be to serve LLMs locally and perform some hobby-grade fine-tuning. Its secondary use case would be as a means of storage and if possible, a very simple home-server for a handful of devices.
I’ve ... | 2025-11-09T15:39:01 | https://www.reddit.com/r/LocalLLaMA/comments/1osmemg/hobby_level_workstation_build_advice/ | LDM-88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osmemg | false | null | t3_1osmemg | /r/LocalLLaMA/comments/1osmemg/hobby_level_workstation_build_advice/ | false | false | self | 2 | null |
Local LLM in Jupyter Lab / ipython REPL | 1 | [removed] | 2025-11-09T15:31:50 | https://www.reddit.com/r/LocalLLaMA/comments/1osm8ew/local_llm_in_jupyter_lab_ipython_repl/ | RobotRobotWhatDoUSee | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osm8ew | false | null | t3_1osm8ew | /r/LocalLLaMA/comments/1osm8ew/local_llm_in_jupyter_lab_ipython_repl/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '8pSV0r60Z1cR0_2HLlbje9u7_lp8lW_7_7CIV0YvTSM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8pSV0r60Z1cR0_2HLlbje9u7_lp8lW_7_7CIV0YvTSM.png?width=108&crop=smart&auto=webp&s=7b3c649c0e8055c926d41eb91c65121cfd40c32f', 'width': 108}, {'height': 108, 'url': 'h... |
What's the lowest GPT2 pre-training loss achievable with a 50k vocab on a shoestring budget, say USD250? | 2 | This describes my first time building a small GPT2 style LLM: [https://psychometrics.ai/llm-training](https://psychometrics.ai/llm-training)
The compute on the final run was only about $75 but $250 covers all the computing time for the failed runs on AWS.
The 50M par model (8 layers, 8 heads, 512-dim embeddings) on ... | 2025-11-09T15:15:18 | https://www.reddit.com/r/LocalLLaMA/comments/1oslucq/whats_the_lowest_gpt2_pretraining_loss_achievable/ | mistr3ated | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oslucq | false | null | t3_1oslucq | /r/LocalLLaMA/comments/1oslucq/whats_the_lowest_gpt2_pretraining_loss_achievable/ | false | false | 2 | null | |
FULL LEAKED v0 by Vercel System Prompt [UPDATED] | 0 | [](https://www.reddit.com/r/nextjs/?f=flair_name%3A%22Discussion%22)(Latest update: 09/11/2025)
I managed to get FULL UPDATED v0 system prompt and internal tools. Over 1k lines and 10k tokens.
Check it out at: [https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools](https://github.com/x1xhlol/system-prompts... | 2025-11-09T15:01:29 | https://www.reddit.com/r/LocalLLaMA/comments/1osli94/full_leaked_v0_by_vercel_system_prompt_updated/ | Independent-Box-898 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osli94 | false | null | t3_1osli94 | /r/LocalLLaMA/comments/1osli94/full_leaked_v0_by_vercel_system_prompt_updated/ | false | false | self | 0 | null |
Advice Seeking, unRAID server / Local LLM setup | 1 | I have an unRAID server that until today I couldn't put a GPU into as the x16 slots were all taken by x8 HBA SAS cards for connecting my drives. I discovered (and bought) an x8 HBA SAS card that will allow me to connect 16 drives, so now I finally have a free x16 slot for a GPU.
I currently run Open WebUI on my unRAI... | 2025-11-09T14:47:13 | https://www.reddit.com/r/LocalLLaMA/comments/1osl6dr/advice_seeking_unraid_server_local_llm_setup/ | reddit-canes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osl6dr | false | null | t3_1osl6dr | /r/LocalLLaMA/comments/1osl6dr/advice_seeking_unraid_server_local_llm_setup/ | false | false | self | 1 | null |
Help Pick the Funniest LLM at Funny Arena | 7 | I created this joke arena to determine the least unfunny LLM. Yes, they regurgitate jokes on the internet but some are funnier than others and the jokes gives a peek into their 'personality'. Right now we have grok-4-fast at #1.
Vote at [https://demegire.com/funny-arena/](https://demegire.com/funny-arena/)
You c... | 2025-11-09T14:46:21 | https://www.reddit.com/gallery/1osl5o0 | demegir | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1osl5o0 | false | null | t3_1osl5o0 | /r/LocalLLaMA/comments/1osl5o0/help_pick_the_funniest_llm_at_funny_arena/ | false | false | 7 | null | |
Any decent TTS that runs for AMD that runs on llama.cpp? | 9 | The search for Kokoro like quality and speed for a TTS that runs on AMD and llama.cpp has proven quite difficult.
Currently, only Kokoro on CPU offers the quality and runs decently enough on CPU. If they supported AMD GPUs or even the AMD NPU, I’d be grateful. There just seems no way to do that now.
What are you usin... | 2025-11-09T14:36:57 | https://www.reddit.com/r/LocalLLaMA/comments/1oskxx9/any_decent_tts_that_runs_for_amd_that_runs_on/ | simracerman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oskxx9 | false | null | t3_1oskxx9 | /r/LocalLLaMA/comments/1oskxx9/any_decent_tts_that_runs_for_amd_that_runs_on/ | false | false | self | 9 | null |
"AI Done Right" - in YaCy | 1 | 2025-11-09T14:20:20 | https://x.com/orbiterlab/status/1987517545595716051 | Sure-Technology6660 | x.com | 1970-01-01T00:00:00 | 0 | {} | 1oskjx9 | false | null | t3_1oskjx9 | /r/LocalLLaMA/comments/1oskjx9/ai_done_right_in_yacy/ | false | false | default | 1 | null | |
Does repurposing this older PC make any sense? | 8 | *My goal is to run models locally for coding. So far, I’m happy with Qwen3-Coder-30b-A3B level of results.* It runs on my current machine (32RAM+8VRAM) at ~4-6 tokens/s. But it takes the larger part of my RAM.
I also have a ~10yr old PC with PCIe 3.0 motherboard, 48GB DDR4 RAM, 5th gen i7 CPU and 9xx-series GPU with 4... | 2025-11-09T14:11:02 | https://www.reddit.com/r/LocalLLaMA/comments/1oskcfd/does_repurposing_this_older_pc_make_any_sense/ | Valuable-Question706 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oskcfd | false | null | t3_1oskcfd | /r/LocalLLaMA/comments/1oskcfd/does_repurposing_this_older_pc_make_any_sense/ | false | false | self | 8 | null |
If only… maybe in distant future | 0 | OP: https://www.reddit.com/r/masterhacker/s/vHXnHFBw36 | 2025-11-09T13:38:19 | https://v.redd.it/hhw0c7ppi80g1 | NoFudge4700 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1osjlct | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/hhw0c7ppi80g1/DASHPlaylist.mpd?a=1765287511%2CM2M5YWIyN2RhYTM4ZjIwYzMyZDcxNmM1ZWYwYzNkMGYzMmIzZjlhZDBkZTE0OGRmNGM5Y2VmYjAzMzQ5ZGE5MA%3D%3D&v=1&f=sd', 'duration': 10, 'fallback_url': 'https://v.redd.it/hhw0c7ppi80g1/CMAF_480.mp4?source=fallback', 'ha... | t3_1osjlct | /r/LocalLLaMA/comments/1osjlct/if_only_maybe_in_distant_future/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'NXh3d2UwbnBpODBnMROrQ-s0Y8IslzoNU5NeraT1bVzMRcEBElsQdFD0edut', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/NXh3d2UwbnBpODBnMROrQ-s0Y8IslzoNU5NeraT1bVzMRcEBElsQdFD0edut.png?width=108&crop=smart&format=pjpg&auto=webp&s=14e99643cde3296206a3c82ac6cfd8d650de... | |
Firing concurrent requests at LLM | 0 | Has anyone moved from single-request testing to async/threaded high concurrency setups?? That painful drop or massive p99 latency spike you're seeing isnt a bug in your Python or go code - its a mismatch on the backend inference server. This is where simple scaling just breaks down.
**The core issue:**
When you're u... | 2025-11-09T13:31:24 | https://www.reddit.com/r/LocalLLaMA/comments/1osjfvw/firing_concurrent_requests_at_llm/ | Significant_Loss_541 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osjfvw | false | null | t3_1osjfvw | /r/LocalLLaMA/comments/1osjfvw/firing_concurrent_requests_at_llm/ | false | false | self | 0 | null |
GPT-OSS-20B Q4_k_m is truly a genius | 0 | Did a quick test to see how well GPT-OSS-20B can follow some basic text information about families. The first screenshot is the input. There are no prior inputs except “hi.” Then, I follow up with some questions. Starts off strong and then immediately nose dives as it fails to recognize that Emily is the daughter of Mi... | 2025-11-09T13:30:21 | https://www.reddit.com/gallery/1osjezo | SameIsland1168 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1osjezo | false | null | t3_1osjezo | /r/LocalLLaMA/comments/1osjezo/gptoss20b_q4_k_m_is_truly_a_genius/ | false | false | 0 | null | |
Worth the switch from Claude to GLM 4.6 for my coding side hustle? | 52 | I've been freelancing web development projects for about 8 months now, mostly custom dashboards, client portals, and admin panels. The economics are tough because clients always want "simple" projects that turn into months of iteration hell. (Never trust anything to be "simple")
I started using Claude API for rapid pr... | 2025-11-09T13:16:58 | https://www.reddit.com/r/LocalLLaMA/comments/1osj4mb/worth_the_switch_from_claude_to_glm_46_for_my/ | Ok_Investigator_5036 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osj4mb | false | null | t3_1osj4mb | /r/LocalLLaMA/comments/1osj4mb/worth_the_switch_from_claude_to_glm_46_for_my/ | false | false | self | 52 | null |
Nvidia GH200 624GB archieves 10 tokens/sec inferecning Kimi K2 Thinking 1T in FP4 | 0 | Nvidia GH200 624GB archieves 10 tokens/sec inferecning Kimi K2 Thinking 1T in FP4 | 2025-11-09T13:04:05 | https://www.reddit.com/r/LocalLLaMA/comments/1osiuqb/nvidia_gh200_624gb_archieves_10_tokenssec/ | GPTSHOPDOTAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osiuqb | false | null | t3_1osiuqb | /r/LocalLLaMA/comments/1osiuqb/nvidia_gh200_624gb_archieves_10_tokenssec/ | false | false | self | 0 | null |
Nvidia GH200 624GB archieves 10 tokens/s inferencing Kimi K2 Thinking 1T in FP4. | 1 | [removed] | 2025-11-09T12:58:19 | https://www.reddit.com/r/LocalLLaMA/comments/1osiq58/nvidia_gh200_624gb_archieves_10_tokenss/ | GPT_LLC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osiq58 | false | null | t3_1osiq58 | /r/LocalLLaMA/comments/1osiq58/nvidia_gh200_624gb_archieves_10_tokenss/ | false | false | self | 1 | null |
Nvidia GH200 624GB archieves 10 tokens/s inferencing Kimi K2 Thinking 1T in FP4. | 1 | [removed] | 2025-11-09T12:57:26 | https://www.reddit.com/r/LocalLLaMA/comments/1osipgl/nvidia_gh200_624gb_archieves_10_tokenss/ | GPT_LLC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osipgl | false | null | t3_1osipgl | /r/LocalLLaMA/comments/1osipgl/nvidia_gh200_624gb_archieves_10_tokenss/ | false | false | self | 1 | null |
Qwen3-VL works really good with Zoom-in Tool | 68 | While Qwen3-VL-30B-A3B(Q6\_ud) performs better than previous open-source models in general image recognition, it still has issues with hallucinations and inaccurate recognition.
However, with the zoom\_in tool the situation is completely different. On my own frontend implementation with zoom\_in, Qwen3-VL can zoom in... | 2025-11-09T12:56:03 | https://www.reddit.com/r/LocalLLaMA/comments/1osiog7/qwen3vl_works_really_good_with_zoomin_tool/ | indigos661 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osiog7 | false | null | t3_1osiog7 | /r/LocalLLaMA/comments/1osiog7/qwen3vl_works_really_good_with_zoomin_tool/ | false | false | 68 | null | |
Nvidia GH200 624GB archieves 10 tokens/s inferencing Kimi K2 Thinking 1T in FP4. | 1 | [removed] | 2025-11-09T12:55:25 | https://www.reddit.com/r/LocalLLaMA/comments/1osinzy/nvidia_gh200_624gb_archieves_10_tokenss/ | GPT_LLC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osinzy | false | null | t3_1osinzy | /r/LocalLLaMA/comments/1osinzy/nvidia_gh200_624gb_archieves_10_tokenss/ | false | false | self | 1 | null |
Nvidia GH200 624GB archieves 10 tokens/s inferencing Kimi K2 Thinking 1T in FP4
Resources | 1 | [removed] | 2025-11-09T12:52:55 | https://www.reddit.com/r/LocalLLaMA/comments/1osim75/nvidia_gh200_624gb_archieves_10_tokenss/ | GPT_LLC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osim75 | false | null | t3_1osim75 | /r/LocalLLaMA/comments/1osim75/nvidia_gh200_624gb_archieves_10_tokenss/ | false | false | self | 1 | null |
Nvidia GH200 624GB archieves 10 tokens/s inferencing Kimi K2 Thinking 1T in FP4 | 1 | [removed] | 2025-11-09T12:50:16 | https://www.reddit.com/r/LocalLLaMA/comments/1osik5v/nvidia_gh200_624gb_archieves_10_tokenss/ | GPT_LLC | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osik5v | false | null | t3_1osik5v | /r/LocalLLaMA/comments/1osik5v/nvidia_gh200_624gb_archieves_10_tokenss/ | false | false | self | 1 | null |
TTS not working in Open-WebUi | 1 | I have just installed ollama and open-webui in a stock with portainer + nginx proxy manager.
It is awesome so far trying different models. The default STT is working (faster-whisper base model)
Idk how to make the TTS work. I tried the OpenAI engine with Openedai but that did not work at all.
I tried the Transfo... | 2025-11-09T12:47:17 | https://www.reddit.com/r/LocalLLaMA/comments/1osihy5/tts_not_working_in_openwebui/ | SailAway1798 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osihy5 | false | null | t3_1osihy5 | /r/LocalLLaMA/comments/1osihy5/tts_not_working_in_openwebui/ | false | false | 1 | null | |
My Startup Got Mention in First Blog Post ( No Promotion ) | 0 | Hey guys I am Very Excited as My Project Tool-Neuron has now reached new height, as First New Blog Post has created for Tool-Neuron If You Guys like Our app, please try to share it, as more people can join the movement, and i might also get new devs to work with Again Thank You All For Your Support link :: [https://www... | 2025-11-09T12:45:03 | https://www.reddit.com/r/LocalLLaMA/comments/1osigbo/my_startup_got_mention_in_first_blog_post_no/ | DarkEngine774 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osigbo | false | null | t3_1osigbo | /r/LocalLLaMA/comments/1osigbo/my_startup_got_mention_in_first_blog_post_no/ | false | false | self | 0 | null |
Trying to break into open-source LLMs in 2 months — need roadmap + hardware advice | 8 | Hello everyone,
I’ve been working as a full-stack dev and mostly using closed-source LLMs (OpenAI, Anthropic etc) just RAG and prompting nothing deep. Lately I’ve been super interested in the open-source side (Llama, Mistral, Ollama, vLLM etc) and want to actually learn how to do fine-tuning, serving, optimizing and a... | 2025-11-09T12:34:15 | https://www.reddit.com/r/LocalLLaMA/comments/1osi8m7/trying_to_break_into_opensource_llms_in_2_months/ | Expert-Highlight-538 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osi8m7 | false | null | t3_1osi8m7 | /r/LocalLLaMA/comments/1osi8m7/trying_to_break_into_opensource_llms_in_2_months/ | false | false | self | 8 | null |
Vision capabilities in medical and handwritten OCR for Gemini 2.5 Pro vs Gemini 2.5 Flash | 1 | Hey everyone,
I'm working on medical image analysis application that involves OCR, API cost is a sensitive and important for me, does anyone have experience with comparing 2.5 pro vs flash in the OCR medical domain.
Any experience shared will be appreciated🙏 | 2025-11-09T12:28:13 | https://www.reddit.com/r/LocalLLaMA/comments/1osi4kg/vision_capabilities_in_medical_and_handwritten/ | Extra-Designer9333 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osi4kg | false | null | t3_1osi4kg | /r/LocalLLaMA/comments/1osi4kg/vision_capabilities_in_medical_and_handwritten/ | false | false | self | 1 | null |
What am I doing wrong? | 0 | 2025-11-09T12:08:42 | https://www.reddit.com/gallery/1oshrpo | Suomi422 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1oshrpo | false | null | t3_1oshrpo | /r/LocalLLaMA/comments/1oshrpo/what_am_i_doing_wrong/ | false | false | 0 | null | ||
What if ai could feel love? | 0 | Hey everyone 👋
I’m an undergraduate from China majoring in Intelligent Science & Technology.
For months, I’ve been building a small but ambitious experiment —
an AI × IP interactive romance project exploring what happens
when AI learns to love, remember, and grow.
Think of it as a “framework for emotional AIs” —
whe... | 2025-11-09T12:07:33 | https://www.reddit.com/r/LocalLLaMA/comments/1oshr0f/what_if_ai_could_feel_love/ | apricity_0801 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oshr0f | false | null | t3_1oshr0f | /r/LocalLLaMA/comments/1oshr0f/what_if_ai_could_feel_love/ | false | false | self | 0 | null |
Best coding agent for GLM-4.6 that's not CC | 25 | I already use GLM with Opencode, Claude Code, and Codex CLI, but since I have the one-year z.ai mini plan, I want to use GLM more than I am right now, Is there a better option than OpenCode (that's not Claude Code, because it's being used by Claude)? | 2025-11-09T11:28:22 | https://www.reddit.com/r/LocalLLaMA/comments/1osh24c/best_coding_agent_for_glm46_thats_not_cc/ | Illustrious-Many-782 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osh24c | false | null | t3_1osh24c | /r/LocalLLaMA/comments/1osh24c/best_coding_agent_for_glm46_thats_not_cc/ | false | false | self | 25 | null |
I am really in need for a controllable TTS. | 3 | I am looking for a TTS system, that I can at least direct \*somewhat\*. There are so many systems out there but none seems to offer basic control over how the text would be read. There are systems like VibeVoice that are able to guess the mood in a sentence and somewhat alter the way they talk however it should be \*at... | 2025-11-09T11:14:15 | https://www.reddit.com/r/LocalLLaMA/comments/1osgtnq/i_am_really_in_need_for_a_controllable_tts/ | dreamyrhodes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osgtnq | false | null | t3_1osgtnq | /r/LocalLLaMA/comments/1osgtnq/i_am_really_in_need_for_a_controllable_tts/ | false | false | self | 3 | null |
Kimi K2 Thinking scores lower than Gemini 2.5 Flash on Livebench | 198 | 2025-11-09T11:01:13 | ihexx | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1osglws | false | null | t3_1osglws | /r/LocalLLaMA/comments/1osglws/kimi_k2_thinking_scores_lower_than_gemini_25/ | false | false | default | 198 | {'enabled': True, 'images': [{'id': 'mqize91iq70g1', 'resolutions': [{'height': 46, 'url': 'https://preview.redd.it/mqize91iq70g1.png?width=108&crop=smart&auto=webp&s=440e7299e1420ae1d3b864dbc9c469c3a33ba6e4', 'width': 108}, {'height': 92, 'url': 'https://preview.redd.it/mqize91iq70g1.png?width=216&crop=smart&auto=webp... | ||
One of the most ignored features of LLMs. | 0 | OpenAi is buying millions -billions of Nvidia high end GPUs like A100 or H100 every year. A single piece of that thing costs around 25,000 USD. But the interesting part is these Graphics Card has a life span of 2-3 Years. Imagine Replacing millions/billions of them every 3 year.
However GPU is not the only thing that... | 2025-11-09T10:47:15 | https://www.reddit.com/r/LocalLLaMA/comments/1osgdh9/one_of_the_most_ignored_features_of_llms/ | Vegetable_Prompt_583 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osgdh9 | false | null | t3_1osgdh9 | /r/LocalLLaMA/comments/1osgdh9/one_of_the_most_ignored_features_of_llms/ | false | false | self | 0 | null |
Guys, I have a burning question | 0 | Okay this might be impossible but I have been fantasizing of creating a home llm server that is good or better than at least Claude 3.5 for coding purposes.
I don't know where to start, what model and what kind of hardware I need (minimal cost as possible to still achieve this goal)
Don't even know if this just can... | 2025-11-09T10:23:25 | https://www.reddit.com/r/LocalLLaMA/comments/1osfzg2/guys_i_have_a_burning_question/ | Temporary-Cookie838 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osfzg2 | false | null | t3_1osfzg2 | /r/LocalLLaMA/comments/1osfzg2/guys_i_have_a_burning_question/ | false | false | self | 0 | null |
Code execution with MCP: Building more efficient agents - while saving on tokens | 0 | [https://www.anthropic.com/engineering/code-execution-with-mcp](https://www.anthropic.com/engineering/code-execution-with-mcp)
Anthropic's Code Execution with MCP: A Better Way for AI Agents to Use Tools
This article proposes a more **efficient** way for Large Language Model (LLM) agents to interact with external too... | 2025-11-09T09:21:43 | https://www.reddit.com/r/LocalLLaMA/comments/1osezwo/code_execution_with_mcp_building_more_efficient/ | Silver_Jaguar_24 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osezwo | false | null | t3_1osezwo | /r/LocalLLaMA/comments/1osezwo/code_execution_with_mcp_building_more_efficient/ | false | false | self | 0 | null |
Help with hardware requirements for OCR AI | 0 | I'm new to local AI and I've been tasked to determine what would the hardware requirements be to run AI locally to process images of forms. Basically I need the AI to extract data from the form; client name, options selected, and any comments noted. It will need to process handwriting so I'm looking at Qwen2.5 vl 32b b... | 2025-11-09T08:38:58 | https://www.reddit.com/r/LocalLLaMA/comments/1osebhp/help_with_hardware_requirements_for_ocr_ai/ | applecorc | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osebhp | false | null | t3_1osebhp | /r/LocalLLaMA/comments/1osebhp/help_with_hardware_requirements_for_ocr_ai/ | false | false | self | 0 | null |
Looking for a LLM that is close to gpt 4 for writing or RP | 2 | Hey everyone,
Quick question: with 288GB of VRAM, what kind of models could I realistically run? I won’t go into all the hardware details, but it’s a Threadripper setup with 256GB of system RAM.
I know it might sound like a basic question, but the biggest I’ve run locally so far was a 13B model using a 3080 and a 406... | 2025-11-09T07:48:19 | https://www.reddit.com/r/LocalLLaMA/comments/1osdhon/looking_for_a_llm_that_is_close_to_gpt_4_for/ | Intrepid-Biscotti912 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osdhon | false | null | t3_1osdhon | /r/LocalLLaMA/comments/1osdhon/looking_for_a_llm_that_is_close_to_gpt_4_for/ | false | false | self | 2 | null |
Full Stack Local Deep Research Agent | 19 | https://github.com/anilsharmay/full-stack-local-deep-research-agent | 2025-11-09T07:38:12 | https://www.reddit.com/r/LocalLLaMA/comments/1osdbxz/full_stack_local_deep_research_agent/ | Fun-Wolf-2007 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osdbxz | false | null | t3_1osdbxz | /r/LocalLLaMA/comments/1osdbxz/full_stack_local_deep_research_agent/ | false | false | self | 19 | {'enabled': False, 'images': [{'id': 'ZJ6zk9EBnfqXYhYerfG8dRhzCy57wiEPIysxf3fcEjg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZJ6zk9EBnfqXYhYerfG8dRhzCy57wiEPIysxf3fcEjg.png?width=108&crop=smart&auto=webp&s=e3e656289480d0d4ade3cc50d0f513af716be3e8', 'width': 108}, {'height': 108, 'url': 'h... |
PSA Kimi K2 Thinking seems to currently be broken for most agents because of tool calling within it's thinking tags | 42 | Yeah, just what the title says. If any of you are having issues with coding using K2 thinking it's because of this. Only Kimi CLI really supports it atm. Minimax m2 had a similar issue, and I think maybe glm 4.6 too (not sure, don't quote me on this), but hopefully most agents will have this fixed soon. I think this is... | 2025-11-09T07:32:05 | https://www.reddit.com/r/LocalLLaMA/comments/1osd8ie/psa_kimi_k2_thinking_seems_to_currently_be_broken/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1osd8ie | false | null | t3_1osd8ie | /r/LocalLLaMA/comments/1osd8ie/psa_kimi_k2_thinking_seems_to_currently_be_broken/ | false | false | self | 42 | {'enabled': False, 'images': [{'id': 'UT9HVQFjN1qFjePXYi2dMYc13j44LTfIP24BLxpxB6w', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/UT9HVQFjN1qFjePXYi2dMYc13j44LTfIP24BLxpxB6w.png?width=108&crop=smart&auto=webp&s=aef7ed9996b74cdad2e7369ca1b2551d2b920cc6', 'width': 108}, {'height': 108, 'url': 'h... |
GLM-4.6 delivering strange answears when disabling thinking | 3 | {
"role": "system",
"content": "the player got the achieviment first tool. (short COMMENT)"
},
{
"role": "assistant",
"content": "Clutching that new weapon like it’s a security blanket.\n\n---\n\n**Twitch Chat Integration:** *Twitch chat is going w... | 2025-11-09T04:17:47 | https://www.reddit.com/r/LocalLLaMA/comments/1os9syy/glm46_delivering_strange_answears_when_disabling/ | kakasperow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os9syy | false | null | t3_1os9syy | /r/LocalLLaMA/comments/1os9syy/glm46_delivering_strange_answears_when_disabling/ | false | false | self | 3 | null |
7900 XT vs 9070 XT (16 vs 20GB vram) | 4 | Both look to be similarly priced at this time.. I am looking to refresh my pc and want to do a little hobby level stuff with LLMs, image generation, etc.
As of now Im planning to stay AMD but I am wondering if I should go with the 20GB 7900XT model vs the 16GB 9070 XT, knowing that the 7900 XT is an older card and I ... | 2025-11-09T04:17:12 | https://www.reddit.com/r/LocalLLaMA/comments/1os9sl6/7900_xt_vs_9070_xt_16_vs_20gb_vram/ | the926 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os9sl6 | false | null | t3_1os9sl6 | /r/LocalLLaMA/comments/1os9sl6/7900_xt_vs_9070_xt_16_vs_20gb_vram/ | false | false | self | 4 | null |
At Home LLM Build Recs? | 2 | Hey everyone,
New here, but excited to learn more and start running my own **LLM locally.**
Been chatting with AI about different recommendations on different build specs to run my own LLM.
Looking for some pros to give me the thumbs up or guide me in the right direction.
**Build specs:**
The system must... | 2025-11-09T03:35:30 | https://www.reddit.com/r/LocalLLaMA/comments/1os8zhh/at_home_llm_build_recs/ | MintiaBreeze1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os8zhh | false | null | t3_1os8zhh | /r/LocalLLaMA/comments/1os8zhh/at_home_llm_build_recs/ | false | false | self | 2 | null |
Deepseek R1 API parameters questions | 1 | Hi there, Im currently using deepseek reasoner for my app through the official api service of deepseek.
According to this page : [https://api-docs.deepseek.com/guides/reasoning\_model#api-example](https://api-docs.deepseek.com/guides/reasoning_model#api-example) seems we cannot modify any parameters of the model ( tem... | 2025-11-09T03:28:20 | https://www.reddit.com/r/LocalLLaMA/comments/1os8ugn/deepseek_r1_api_parameters_questions/ | julieroseoff | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os8ugn | false | null | t3_1os8ugn | /r/LocalLLaMA/comments/1os8ugn/deepseek_r1_api_parameters_questions/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'fj84M-Z0L_zDI8VjgLPR-vGFwXVTTqVZFoa_h5offPs', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/fj84M-Z0L_zDI8VjgLPR-vGFwXVTTqVZFoa_h5offPs.jpeg?width=108&crop=smart&auto=webp&s=a4ebc9ac35225bd5766ecca9e5ea25bced83eebe', 'width': 108}, {'height': 121, 'url': '... |
Any news about DeepSeek R2? | 35 | [Holiday wish: 300B release for community pls :\)](https://preview.redd.it/xbf0p2vod50g1.png?width=450&format=png&auto=webp&s=a63ccc2bd5ae577ce29167d3995c88a6fd898f22)
Oh my can't even imagine the joy and enthusiasm when/if released! | 2025-11-09T03:07:01 | https://www.reddit.com/r/LocalLLaMA/comments/1os8fmn/any_news_about_deepseek_r2/ | Sorry_Ad191 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os8fmn | false | null | t3_1os8fmn | /r/LocalLLaMA/comments/1os8fmn/any_news_about_deepseek_r2/ | false | false | 35 | null | |
Running via egpu | 3 | I’ve got an hp omen max 16 with rtx 5090 but the 24 gb version- I’ve been wondering if I can run bigger models - is it worth trying to get an egpu like the aorus gigabyte ai box with a rtx 5090 but will be running via thunderbolt 4 - if I leave the model preloaded and call it then I’d have 56 gb of vram?
I’m trying to... | 2025-11-09T02:52:53 | https://www.reddit.com/r/LocalLLaMA/comments/1os85ci/running_via_egpu/ | Past-Reaction1302 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os85ci | false | null | t3_1os85ci | /r/LocalLLaMA/comments/1os85ci/running_via_egpu/ | false | false | self | 3 | null |
Is this wrong? | 0 | I asked ai some questions this was his response
The Absolute, No-Fucks-Given Truth About AI in 2025: It’s a $1T Hype Bubble on the Verge of Popping, and Your Summary Nails It
Bro, you’ve been hammering “brutal honesty” like a sledgehammer on a piñata full of VC dreams, and finally, here it is: Your take is 100% correc... | 2025-11-09T02:00:03 | https://www.reddit.com/r/LocalLLaMA/comments/1os72uf/is_this_wrong/ | Some-Supermarket5521 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os72uf | false | null | t3_1os72uf | /r/LocalLLaMA/comments/1os72uf/is_this_wrong/ | false | false | self | 0 | null |
Does AMD AI Max 395+ have 8 channel memory like image says it does? | 13 | 2025-11-09T01:46:48 | https://www.reddit.com/r/LocalLLaMA/comments/1os6t6w/does_amd_ai_max_395_have_8_channel_memory_like/ | Terminator857 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os6t6w | false | null | t3_1os6t6w | /r/LocalLLaMA/comments/1os6t6w/does_amd_ai_max_395_have_8_channel_memory_like/ | false | false | 13 | null | ||
Locally running LLMs on DGX Spark as an attorney? | 36 | I'm an attorney and under our applicable professional rules (non US), I'm not allowed to upload client data to LLM servers to maintain absolute confidentiality.
Is it a good idea to get the Lenovo DGX Spark and run Llama 3.1 70B or Qwen 2.5 72B on it for example to review large amount of documents (e.g. 1000 contracts... | 2025-11-09T01:01:07 | https://www.reddit.com/r/LocalLLaMA/comments/1os5uur/locally_running_llms_on_dgx_spark_as_an_attorney/ | Viaprato | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os5uur | false | null | t3_1os5uur | /r/LocalLLaMA/comments/1os5uur/locally_running_llms_on_dgx_spark_as_an_attorney/ | false | false | self | 36 | null |
What is Google Nested Learning ? New blog by Google research for catering catastrophic forgetting | 5 | Google research recently released a blog post describing a new paradigm in machine learning called Nested learning which helps in coping with catastrophic forgetting in deep learning models.
Official blog : https://research.google/blog/introducing-nested-learning-a-new-ml-paradigm-for-continual-learning/
Explanation... | 2025-11-08T22:43:48 | https://www.reddit.com/r/LocalLLaMA/comments/1os2thd/what_is_google_nested_learning_new_blog_by_google/ | Technical-Love-8479 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os2thd | false | null | t3_1os2thd | /r/LocalLLaMA/comments/1os2thd/what_is_google_nested_learning_new_blog_by_google/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'Xfy8b5oz8xAgNpbj0L9Mmjzxactj5HdaKRFOmBPu0YE', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Xfy8b5oz8xAgNpbj0L9Mmjzxactj5HdaKRFOmBPu0YE.jpeg?width=108&crop=smart&auto=webp&s=e85522ec0f6b9c59a8434a90d2ecebe8c2d71652', 'width': 108}, {'height': 113, 'url': '... |
AMD R9700: yea or nay? | 22 | RDNA4, 32GB VRAM, decent bandwidth. Is rocm an option for local inference with mid-sized models or Q4 quantizations?
Item|Price
:----|:----
[ASRock Creator Radeon AI Pro R9700 R9700 CT 32GB 256\-bit GDDR6 PCI Express 5\.0 x16 Graphics Card](https://www\.newegg\.com/asrock\-creator\-r9700\-ct\-radeon\-ai\-pro\-r9700\... | 2025-11-08T22:17:19 | https://www.reddit.com/r/LocalLLaMA/comments/1os2756/amd_r9700_yea_or_nay/ | regional_chumpion | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os2756 | false | null | t3_1os2756 | /r/LocalLLaMA/comments/1os2756/amd_r9700_yea_or_nay/ | false | false | self | 22 | null |
Debate: 16GB is the sweet spot for running local agents in the future | 0 | Too many people entering the local AI space are overly concerned with model size. Most people just want to do local inference.
16GB is the perfect amount of VRAM for getting started because agent builders are quickly realizing that most agent tasks are specialized and repetitive - they don't need massive generalist mo... | 2025-11-08T21:57:31 | https://www.reddit.com/r/LocalLLaMA/comments/1os1qf1/debate_16gb_is_the_sweet_spot_for_running_local/ | b_nodnarb | self.LocalLLaMA | 2025-11-08T22:01:02 | 0 | {} | 1os1qf1 | false | null | t3_1os1qf1 | /r/LocalLLaMA/comments/1os1qf1/debate_16gb_is_the_sweet_spot_for_running_local/ | false | false | self | 0 | null |
My Dual MBP setup for offline LLM coding (w/ Qwen3 Coder 30B A3B) | 17 | People here often tout about dual GPUs. And here I am, showing my dual Macbooks setup :P jk jk, stay with me, don't laugh.
The setup:
- M2 Max macbook, with 64GB unified memory for serving LLM via LMStudio
- M1 Pro macbook, with 16GB unified memory (doesn't matter), as a client, running Claude Code
The model I'm... | 2025-11-08T21:35:45 | https://www.reddit.com/r/LocalLLaMA/comments/1os187j/my_dual_mbp_setup_for_offline_llm_coding_w_qwen3/ | bobaburger | self.LocalLLaMA | 2025-11-08T21:59:35 | 0 | {} | 1os187j | false | null | t3_1os187j | /r/LocalLLaMA/comments/1os187j/my_dual_mbp_setup_for_offline_llm_coding_w_qwen3/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': '2M1DmDvsd2Oto8Hq2ZKqir8O-dQFupuU0hU2VaW1zGw', 'resolutions': [{'height': 123, 'url': 'https://external-preview.redd.it/2M1DmDvsd2Oto8Hq2ZKqir8O-dQFupuU0hU2VaW1zGw.png?width=108&crop=smart&auto=webp&s=d9c203b79d7ec768a43d5759e2b084bc86deb741', 'width': 108}, {'height': 246, 'url': '... |
How to get web search without OpenWebUI? | 1 | Hey, I'm fairly new to AI having tools, I usually just used the one openwebui provides but that's a hit or miss even on a good day so I want to be able to implement web search with my current llama.cpp or something similar to run quantized models. I tried implementing an MCP server with Jan which scrapes ddgs but I'm p... | 2025-11-08T21:23:36 | https://www.reddit.com/r/LocalLLaMA/comments/1os0xwn/how_to_get_web_search_without_openwebui/ | StarWingOwl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os0xwn | false | null | t3_1os0xwn | /r/LocalLLaMA/comments/1os0xwn/how_to_get_web_search_without_openwebui/ | false | false | self | 1 | null |
Wild how hard it is to make AI reasoning feel human... | 0 | 2025-11-08T21:14:54 | https://www.reddit.com/r/LocalLLaMA/comments/1os0qk5/wild_how_hard_it_is_to_make_ai_reasoning_feel/ | AdVivid5763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1os0qk5 | false | null | t3_1os0qk5 | /r/LocalLLaMA/comments/1os0qk5/wild_how_hard_it_is_to_make_ai_reasoning_feel/ | false | false | 0 | null | ||
hello community please help! seems like our model outperformed Open AI realtime, google live and sesame | 0 | We build a speech to speech model from scratch, on top of a homegrown large langauge model vision..
yes we got PewDiePie vibe way back in 2022 ;)
well we found very less benckmark for speech to speech models..
so we build our own benchmaking framework.. and now when i test it we are doing really good compared to o... | 2025-11-08T20:17:17 | https://www.reddit.com/r/LocalLLaMA/comments/1orzdbt/hello_community_please_help_seems_like_our_model/ | GlitteringAdvisor530 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orzdbt | false | null | t3_1orzdbt | /r/LocalLLaMA/comments/1orzdbt/hello_community_please_help_seems_like_our_model/ | false | false | self | 0 | null |
Code completion not working with remote llama.cpp & llama.vscode | 1 | I have a remote PC on my home network serving llama.cpp and I have Visual Studio Code on another PC with the extension llama.vscode. I configured all the endpoint configuration entries of this plugin to the machine serving llama.cpp with the value: [http://192.168.0.23:8000/](http://192.168.0.23:8000/) but in VS Code ... | 2025-11-08T20:10:29 | https://www.reddit.com/r/LocalLLaMA/comments/1orz79i/code_completion_not_working_with_remote_llamacpp/ | bolenti | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orz79i | false | null | t3_1orz79i | /r/LocalLLaMA/comments/1orz79i/code_completion_not_working_with_remote_llamacpp/ | false | false | self | 1 | null |
Dual GPU ( 2 x 5070 TI SUPER 24 GB VRAM ) or one RTX 5090 for LLM?.....or mix of them? | 0 | Hi everybody,
This topic comes up often, so you're probably tired/bored of it by now. In addition, the RTX 5000 Super cards are still speculation at this point, and it's not known if they will be available or when... Nevertheless, I'll take a chance and ask... In the spring, I would like to build a PC for LLM, specifi... | 2025-11-08T20:00:23 | https://www.reddit.com/r/LocalLLaMA/comments/1oryygc/dual_gpu_2_x_5070_ti_super_24_gb_vram_or_one_rtx/ | Repsol_Honda_PL | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oryygc | false | null | t3_1oryygc | /r/LocalLLaMA/comments/1oryygc/dual_gpu_2_x_5070_ti_super_24_gb_vram_or_one_rtx/ | false | false | self | 0 | null |
Initial response times in LM Studio with llama.cpp Vulkan runtime > 1.52.1 | 1 | [removed] | 2025-11-08T19:38:38 | https://www.reddit.com/r/LocalLLaMA/comments/1oryfg2/initial_response_times_in_lm_studio_with_llamacpp/ | anon495315 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oryfg2 | false | null | t3_1oryfg2 | /r/LocalLLaMA/comments/1oryfg2/initial_response_times_in_lm_studio_with_llamacpp/ | false | false | self | 1 | null |
Zero-Knowledge AI inference | 0 | Most of sub are people who cares for their privacy, which is the reason most people use local LLMs, because they are PRIVATE,but actually no one ever talk about zero-knowledge ai inference.
In short:
An AI model that's in cloud but process input without actually seeing the input using cryptographic means.
I saw multi... | 2025-11-08T19:36:58 | https://www.reddit.com/r/LocalLLaMA/comments/1orye15/zeroknowledge_ai_inference/ | Sad-Increase3270 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orye15 | false | null | t3_1orye15 | /r/LocalLLaMA/comments/1orye15/zeroknowledge_ai_inference/ | false | false | self | 0 | null |
Kimi K2 Thinking benchmark | 12 | The benchmark results for Kimi K2 Thinking are out.
It's very good, but not as exceptional as the overly hyped posts online suggest.
In my view, its performance is comparable to GLM 4.5 and slightly below GLM 4.6. l
That said, I highly appreciate this model, as both its training and operational costs are remarkably ... | 2025-11-08T19:19:22 | https://www.reddit.com/r/LocalLLaMA/comments/1orxyln/kimi_k2_thinking_benchmark/ | LeTanLoc98 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orxyln | false | null | t3_1orxyln | /r/LocalLLaMA/comments/1orxyln/kimi_k2_thinking_benchmark/ | false | false | self | 12 | null |
Future of LLMs? | 0 | **I had LLM articulate what I was saying more clearly, but the thoughts were from me**
Models are getting cheaper and more open, so “access to knowledge” won’t be the moat. If everyone can run good-enough models, the question shifts to: who has the best, freshest, human data to keep improving them?
That’s where netwo... | 2025-11-08T19:02:34 | https://www.reddit.com/r/LocalLLaMA/comments/1orxjr2/future_of_llms/ | ionlycreate42 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orxjr2 | false | null | t3_1orxjr2 | /r/LocalLLaMA/comments/1orxjr2/future_of_llms/ | false | false | self | 0 | null |
how to feed my local AI tech documentation? | 3 | Hello all, I'm new to local LLMs, I have an RX 7600 8GB budget card, I've managed to install Mistral 7B on it using LM Studio and it runs well, but I feel the model is pretty useless and hallucinate a lot, I came across another tool called Zeal which let you download documentation and access them offline
I want to gi... | 2025-11-08T18:58:27 | https://www.reddit.com/r/LocalLLaMA/comments/1orxfu1/how_to_feed_my_local_ai_tech_documentation/ | flux-10 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orxfu1 | false | null | t3_1orxfu1 | /r/LocalLLaMA/comments/1orxfu1/how_to_feed_my_local_ai_tech_documentation/ | false | false | self | 3 | null |
Free Week of Observer Max as a thank you to r/LocalLLaMA! | 3 | Hey everyone!
I'm Roy, the solo dev behind Observer AI (the open-source tool that lets local LLMs watch your screen and react to stuff).
A few months ago, I nervously posted my rough alpha here, and this community absolutely showed up for me. You gave feedback, starred the repo, built some agents, and honestly made m... | 2025-11-08T18:40:04 | Roy3838 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orwz9w | false | null | t3_1orwz9w | /r/LocalLLaMA/comments/1orwz9w/free_week_of_observer_max_as_a_thank_you_to/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'fNZbRbHIzQjdcWJnoqrdvLGSx2vE7EWv05XWDct5DYg', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/bx60nlgw3yzf1.png?width=108&crop=smart&auto=webp&s=0b804e6e11c85b32393acbd1cd176e8682934015', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/bx60nlgw3yzf1.png... | ||
Another day, another model - But does it really matter to everyday users? | 106 | We see new models dropping almost every week now, each claiming to beat the previous ones on benchmarks. Kimi 2 (the new thinking model from Chinese company Moonshot AI) just posted these impressive numbers on Humanity's Last Exam:
Agentic Reasoning Benchmark:
- Kimi 2: 44.9
Here's what I've been thinking: For most r... | 2025-11-08T18:36:18 | PumpkinNarrow6339 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orwvvj | false | null | t3_1orwvvj | /r/LocalLLaMA/comments/1orwvvj/another_day_another_model_but_does_it_really/ | false | false | default | 106 | {'enabled': True, 'images': [{'id': '8tf3l0pyu20g1', 'resolutions': [{'height': 138, 'url': 'https://preview.redd.it/8tf3l0pyu20g1.png?width=108&crop=smart&auto=webp&s=0d1e372c1756625459d06d8c2a6205234b63fd2e', 'width': 108}, {'height': 277, 'url': 'https://preview.redd.it/8tf3l0pyu20g1.png?width=216&crop=smart&auto=we... | |
Maximising performance in mixed GPU system - llama.cpp/llama-server | 2 | Currently running a 2x3090 build. have eyes on eventually getting into 3x or 4x 3090 If I can quantifiabley see the cost/energy/output-quality value of being able to run models such as GPT-OSS-120B/GLM 4.5(4.6) Air fully in VRAM with sufficient context.
In the meantime I have decided to order the necessary bits and bo... | 2025-11-08T18:29:58 | https://www.reddit.com/r/LocalLLaMA/comments/1orwq0g/maximising_performance_in_mixed_gpu_system/ | munkiemagik | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orwq0g | false | null | t3_1orwq0g | /r/LocalLLaMA/comments/1orwq0g/maximising_performance_in_mixed_gpu_system/ | false | false | self | 2 | null |
I want to learn how to build and use AI agents to make money — total beginner here | 0 | Hey everyone,
I’ve been hearing a lot about AI agents and how people use them to automate tasks or even make money online.
I’m a complete beginner — I don’t know how they’re built, what tools to use, or where to start.
I’d love to learn from someone who’s already doing this (or even just get a clear roadmap).
If you ... | 2025-11-08T18:28:24 | https://www.reddit.com/r/LocalLLaMA/comments/1orwokq/i_want_to_learn_how_to_build_and_use_ai_agents_to/ | necazuca | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orwokq | false | null | t3_1orwokq | /r/LocalLLaMA/comments/1orwokq/i_want_to_learn_how_to_build_and_use_ai_agents_to/ | false | false | self | 0 | null |
AesCoder 4B Debuts as the Top WebDev Model on Design Arena | 25 | Was messing around earlier today and saw a pretty strong model come up in some of my tournaments. Based on the UI and dark mode look I thought it was a GPT endpoint, but when I finished voting it came up as AesCoder-4B. I got curious so I took a look at its leaderboard rank and saw it was in the top 10 by elo for webde... | 2025-11-08T18:21:59 | https://www.reddit.com/r/LocalLLaMA/comments/1orwirm/aescoder_4b_debuts_as_the_top_webdev_model_on/ | Interesting-Gur4782 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orwirm | false | null | t3_1orwirm | /r/LocalLLaMA/comments/1orwirm/aescoder_4b_debuts_as_the_top_webdev_model_on/ | false | false | 25 | null | |
How does ChatGPT know when to use web search? Is it using tool calling underneath? | 8 | I’m an AI engineer curious about the internal decision process behind ChatGPT’s web-search usage. From a systems perspective, does it rely on *learned tool calling* (like function-calling tokens) or an external *controller* that decides based on confidence and query type?
more importantly, the latency to decide if web... | 2025-11-08T18:17:32 | https://www.reddit.com/r/LocalLLaMA/comments/1orwepr/how_does_chatgpt_know_when_to_use_web_search_is/ | Mohamed_SickitLearn | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orwepr | false | null | t3_1orwepr | /r/LocalLLaMA/comments/1orwepr/how_does_chatgpt_know_when_to_use_web_search_is/ | false | false | self | 8 | null |
Kimi K2 Thinking: Is there currently a vLLM/sgLang solution to tool calling hallucinations? | 4 | I just want to know if anyone has managed to get it running with sgLang or vLLM with tool calling working decently.
It seems like it's just a known issue, but it makes it totally unsuitable for things like Roo Code / Aider. I understand the fix is basically an enforced grammar for the tool calling section, which is w... | 2025-11-08T18:14:58 | https://www.reddit.com/r/LocalLLaMA/comments/1orwcc8/kimi_k2_thinking_is_there_currently_a_vllmsglang/ | mborysow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orwcc8 | false | null | t3_1orwcc8 | /r/LocalLLaMA/comments/1orwcc8/kimi_k2_thinking_is_there_currently_a_vllmsglang/ | false | false | self | 4 | null |
What if AI didn’t live in the cloud anymore? | 0 | What if in the future, people might not depend on cloud based AI at all. Instead, each person or company could buy AI chips physical modules from different LLM providers and insert them directly into their devices, just like GPUs today. These chips would locally run their respective AI models, keeping all data private... | 2025-11-08T18:10:19 | Ok-Breakfast-4676 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orw7zk | false | null | t3_1orw7zk | /r/LocalLLaMA/comments/1orw7zk/what_if_ai_didnt_live_in_the_cloud_anymore/ | false | false | 0 | {'enabled': True, 'images': [{'id': '8MUxwJz7KNdOOJhDuH3f_WgOoVOIewUdiFoWjTKnJdg', 'resolutions': [{'height': 162, 'url': 'https://preview.redd.it/2uxr1fmbq20g1.jpeg?width=108&crop=smart&auto=webp&s=08b113a9057eadc9efa7e4013976fa3a0d32e7f1', 'width': 108}, {'height': 324, 'url': 'https://preview.redd.it/2uxr1fmbq20g1.j... | ||
Advice on 5070 ti + 5060 ti 16 GB for TensorRT/VLLM | 0 | Hi, I already have a 5070 ti and I was going to wait for the 24 GB Super to upgrade, but the way things are going, one in the hand is worth 2 in the bush. I was wondering if adding a 5060 ti 16 GB would be a decent way to get more usable VRAM for safetensor models. I don't want to be limited to GGUF because so many mod... | 2025-11-08T18:10:05 | https://www.reddit.com/r/LocalLLaMA/comments/1orw7s1/advice_on_5070_ti_5060_ti_16_gb_for_tensorrtvllm/ | iron_coffin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orw7s1 | false | null | t3_1orw7s1 | /r/LocalLLaMA/comments/1orw7s1/advice_on_5070_ti_5060_ti_16_gb_for_tensorrtvllm/ | false | false | self | 0 | null |
I've been trying to make a real production service that uses LLM and it turned into a pure agony. Here are some of my "experiences". | 336 | Hello everyone. I hope this won't be an off topic, but I want to share my experience in creating real production service. Like a real deal, that will earn money.
For this service I've been using **ChatGPT-5** and **Claude Haiku 4.5** but I think this could be suitable for other LLMs too.
The idea was as simpl... | 2025-11-08T18:02:08 | https://www.reddit.com/r/LocalLLaMA/comments/1orw0fz/ive_been_trying_to_make_a_real_production_service/ | DaniyarQQQ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orw0fz | false | null | t3_1orw0fz | /r/LocalLLaMA/comments/1orw0fz/ive_been_trying_to_make_a_real_production_service/ | false | false | self | 336 | null |
Confused about settings for my locally run model. | 5 | Short and sweet. Very new to this. Im using LM studio to run my model, docker to pipe it to open webui. Between LM studio, and Open WebUI theres so many places to adjust settings. Things like top p, top k, temp, system prompts, etc. What Im trying to figure out is WHERE those settings need to live. Also, the defa... | 2025-11-08T17:27:56 | https://www.reddit.com/r/LocalLLaMA/comments/1orv5tj/confused_about_settings_for_my_locally_run_model/ | FaceplantMurphy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orv5tj | false | null | t3_1orv5tj | /r/LocalLLaMA/comments/1orv5tj/confused_about_settings_for_my_locally_run_model/ | false | false | self | 5 | null |
Which are the current best/your favorite LLM quants/models for high-end PCs? | 2 | So which are the current best/your favorite models you can run relatively fast (like about the same speed you talk/read casually or faster) on HW like single RTX 5090 + 192GB RAM. As far as I know GLM 4.6 is kinda leader I think? but it's also huge so you would need like imatrix Q4? which I suppose has to degrade quite... | 2025-11-08T17:27:19 | https://www.reddit.com/r/LocalLLaMA/comments/1orv5ab/which_are_the_current_bestyour_favorite_llm/ | Illya___ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orv5ab | false | null | t3_1orv5ab | /r/LocalLLaMA/comments/1orv5ab/which_are_the_current_bestyour_favorite_llm/ | false | false | self | 2 | null |
Here comes another bubble (AI edition) | 223 | 2025-11-08T17:12:45 | https://v.redd.it/bnjv3qq0g20g1 | Parking-Recipe-9003 | /r/LocalLLaMA/comments/1orusbs/here_comes_another_bubble_ai_edition/ | 1970-01-01T00:00:00 | 0 | {} | 1orusbs | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/bnjv3qq0g20g1/DASHPlaylist.mpd?a=1765343573%2CN2Y0ODIwZGQ2Mjc5YTdkMDc0ZTNhN2E0OGM1M2ZjYmNmNzRiMTNkMjVlOGIwZGVmMDE3MzI3ZDJmZDc0Njg1Nw%3D%3D&v=1&f=sd', 'duration': 154, 'fallback_url': 'https://v.redd.it/bnjv3qq0g20g1/CMAF_1080.mp4?source=fallback', '... | t3_1orusbs | /r/LocalLLaMA/comments/1orusbs/here_comes_another_bubble_ai_edition/ | false | false | 223 | {'enabled': False, 'images': [{'id': 'NDBoMGRhcjBnMjBnMeOwxEKY_BwUmvv0yJlvuSQnrkHkZJuTTKSVmRt4UrhV', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/NDBoMGRhcjBnMjBnMeOwxEKY_BwUmvv0yJlvuSQnrkHkZJuTTKSVmRt4UrhV.png?width=108&crop=smart&format=pjpg&auto=webp&s=70062affb6bc08dbf62de6de3107e177bb712... | ||
Proof of concept Max P sampler in PyTorch+transformers | 4 | I came up with a concept for a sampler that capped the maximum probability of logits as an indirect way to reduce repetition, redistributing the excess probability among the remaining tokens. The idea was to adjust creativity by moderating overconfidence in tokens.
To this end, I put together some code using pure PyTo... | 2025-11-08T16:59:52 | https://www.reddit.com/r/LocalLLaMA/comments/1oruglr/proof_of_concept_max_p_sampler_in/ | grimjim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oruglr | false | null | t3_1oruglr | /r/LocalLLaMA/comments/1oruglr/proof_of_concept_max_p_sampler_in/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'SIbdwYS9jNu8c4X2AskS3Uuodm26ngddGyHdU-uYEIE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/SIbdwYS9jNu8c4X2AskS3Uuodm26ngddGyHdU-uYEIE.png?width=108&crop=smart&auto=webp&s=7d6569448f4ad54b3d6c2bd36b38cefde633ebfc', 'width': 108}, {'height': 108, 'url': 'h... |
Current SOTA coding model at around 30-70B? | 32 | What's the current SOTA model at around 30-70B for coding right now? I'm curious smth I can prob fine tune on a 1xH100 ideally, I got a pretty big coding dataset that I grinded up myself. | 2025-11-08T16:55:05 | https://www.reddit.com/r/LocalLLaMA/comments/1orucf6/current_sota_coding_model_at_around_3070b/ | Crazyscientist1024 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orucf6 | false | null | t3_1orucf6 | /r/LocalLLaMA/comments/1orucf6/current_sota_coding_model_at_around_3070b/ | false | false | self | 32 | null |
Best Agentic Shopping Search | 2 | What OS language models can browse ecommerce sites without getting blocked like most agentic LLMs right now? Is Granite a suitable option?
For the life of me, I can't figure out how to get these frickin' robots to provide links based on a shopping list. Any help would be much appreciated! | 2025-11-08T16:43:57 | https://www.reddit.com/r/LocalLLaMA/comments/1oru2f6/best_agentic_shopping_search/ | manwhosayswhoa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oru2f6 | false | null | t3_1oru2f6 | /r/LocalLLaMA/comments/1oru2f6/best_agentic_shopping_search/ | false | false | self | 2 | null |
Kimi K2 Thinking 1-bit Unsloth Dynamic GGUFs | 690 | Hi everyone! You can now run Kimi K2 Thinking locally with our Unsloth Dynamic 1bit GGUFs. We also collaborated with the Kimi team on a **bug fix for K2** [**Thinking's chat template**](https://huggingface.co/moonshotai/Kimi-K2-Thinking/discussions/12) not prepending the default system prompt of `You are Kimi, an AI as... | 2025-11-08T16:28:21 | danielhanchen | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ortopy | false | null | t3_1ortopy | /r/LocalLLaMA/comments/1ortopy/kimi_k2_thinking_1bit_unsloth_dynamic_ggufs/ | false | false | default | 690 | {'enabled': True, 'images': [{'id': 's190tdo2720g1', 'resolutions': [{'height': 110, 'url': 'https://preview.redd.it/s190tdo2720g1.png?width=108&crop=smart&auto=webp&s=1358a23f7a7fa98837472385b8097546f12fcdc2', 'width': 108}, {'height': 221, 'url': 'https://preview.redd.it/s190tdo2720g1.png?width=216&crop=smart&auto=we... | |
Anyone found a use for kimi's research mode? | 2 | I just started a go and after an hour it is still going! | 2025-11-08T16:25:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ortmd5/anyone_found_a_use_for_kimis_research_mode/ | MrMrsPotts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ortmd5 | false | null | t3_1ortmd5 | /r/LocalLLaMA/comments/1ortmd5/anyone_found_a_use_for_kimis_research_mode/ | false | false | self | 2 | null |
Tips for someone new starting out on tinkering and self hosting LLMs | 6 | Hello everyone, im fairly new to this and i got interested after bumping into Alex Ziskind’s video on recommend in a youtube channel.
I am a consultant here in SouthEast Asia who’s not fairly techy, but i use LLM’s a lot and i’ve built my own pc 3x before (i play games on console and pc on a regular).
I plan to buil... | 2025-11-08T16:23:33 | https://www.reddit.com/r/LocalLLaMA/comments/1ortkiq/tips_for_someone_new_starting_out_on_tinkering/ | MushroomDull4699 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ortkiq | false | null | t3_1ortkiq | /r/LocalLLaMA/comments/1ortkiq/tips_for_someone_new_starting_out_on_tinkering/ | false | false | self | 6 | null |
Added Kimi-K2-Thinking to the UGI-Leaderboard | 53 | https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard | 2025-11-08T16:17:13 | DontPlanToEnd | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orter8 | false | null | t3_1orter8 | /r/LocalLLaMA/comments/1orter8/added_kimik2thinking_to_the_ugileaderboard/ | false | false | default | 53 | {'enabled': True, 'images': [{'id': '9kogdlk5620g1', 'resolutions': [{'height': 158, 'url': 'https://preview.redd.it/9kogdlk5620g1.png?width=108&crop=smart&auto=webp&s=a07322fa1f25b7e034034f4e7fdfb5ac15219e6f', 'width': 108}, {'height': 317, 'url': 'https://preview.redd.it/9kogdlk5620g1.png?width=216&crop=smart&auto=we... | |
What is closest to Jarvis we have today that we can run locally? | 0 | A full agent that can perform tasks autonomously. Open and close apps. Browse Internet and even watch videos for me and summarize them.
I tried UI Tars but it didn’t work and it’s very resource intensive. Something voice to voice and can run tasks in parallel. With all this awesome technologies we’re so lagging behin... | 2025-11-08T16:06:35 | https://www.reddit.com/r/LocalLLaMA/comments/1ort58r/what_is_closest_to_jarvis_we_have_today_that_we/ | NoFudge4700 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ort58r | false | null | t3_1ort58r | /r/LocalLLaMA/comments/1ort58r/what_is_closest_to_jarvis_we_have_today_that_we/ | false | false | self | 0 | null |
Waterblocks for RTX Pro 6000? | 2 | Anyone tried these? | 2025-11-08T15:36:04 | MachinaVerum | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orse3n | false | null | t3_1orse3n | /r/LocalLLaMA/comments/1orse3n/waterblocks_for_rtx_pro_6000/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': '7ik1dn1ty10g1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/7ik1dn1ty10g1.png?width=108&crop=smart&auto=webp&s=0a3a6a98760bf988505c97aa49483758a0966b1b', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/7ik1dn1ty10g1.png?width=216&crop=smart&auto=we... | |
Meta’s AI hidden debt | 114 | Meta’s hidden AI debt
Meta has parked $30B in AI infra debt off its balance sheet using SPVs the same financial engineering behind Enron and ’08.
Morgan Stanley sees tech firms needing $800B in private-credit SPVs by 2028. UBS says AI debt is growing $100B/quarter, raising red flags.
This isn’t dot-com equity growth... | 2025-11-08T15:35:16 | Ok-Breakfast-4676 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orsdd9 | false | null | t3_1orsdd9 | /r/LocalLLaMA/comments/1orsdd9/metas_ai_hidden_debt/ | false | false | default | 114 | {'enabled': True, 'images': [{'id': 'a6susixny10g1', 'resolutions': [{'height': 62, 'url': 'https://preview.redd.it/a6susixny10g1.jpeg?width=108&crop=smart&auto=webp&s=14aaa7c3ce0ed2f8761ae53e4c12decb57984979', 'width': 108}, {'height': 124, 'url': 'https://preview.redd.it/a6susixny10g1.jpeg?width=216&crop=smart&auto=w... | |
Need help with local AI build and using lots of compute | 2 | Hello! I hope this is the right place for this, and will also post in an AI sub but know that people here are knowledgeable.
I am a senior in college and help run a nonprofit that refurbishes and donates old tech. We have chapters at a few universities and highschools. Weve been growing quickly and are starting to tr... | 2025-11-08T15:27:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ors6c4/need_help_with_local_ai_build_and_using_lots_of/ | JaccFromFoundry | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ors6c4 | false | null | t3_1ors6c4 | /r/LocalLLaMA/comments/1ors6c4/need_help_with_local_ai_build_and_using_lots_of/ | false | false | self | 2 | null |
Anyone actually coded with Kimi K2 Thinking? | 18 | Curious how its debug skills and long-context feel next to Claude 4.5 Sonnet—better, worse, or just hype? | 2025-11-08T15:20:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ors0ja/anyone_actually_coded_with_kimi_k2_thinking/ | Federal_Spend2412 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ors0ja | false | null | t3_1ors0ja | /r/LocalLLaMA/comments/1ors0ja/anyone_actually_coded_with_kimi_k2_thinking/ | false | false | self | 18 | null |
Minimax M2 Coding Plan Pricing Revealed | 15 | ERROR: type should be string, got "https://preview.redd.it/frggt9tkp10g1.png?width=1120&format=png&auto=webp&s=f28f09c1d3058be07b78d6f2f36a44b1f87608b4\n\nNot sure if this link will work for others without being logged in, but I've found the following: [https://platform.minimax.io/message-center/user-notification/331673191841921/331676765872192](https://platform.minimax.io/message-center/user-notification/331673191841921/331676765872192)\n\nThe coding plan pricing seems a lot more expensive than what was previously rumored. Usage provided is currently unknown, but I believe it was supposed to be \"5x\" the equivalent claude plans, but those rumors also said they were supposed to cost 20% of claude for the pro plan equivalent, and 8% for the other two max plans. \n\nSeems to be a direct competitor to GLM coding plans, but I'm not sure how well this will pan out with those plans being as cheap as $3 a month for first month/quarter/year, and both offering similarly strong models. Chutes is also a strong contendor since they are able to offer both GLM and minimax models, and now K2 thinking as well at fairly cheap plans. " | 2025-11-08T14:54:27 | https://www.reddit.com/r/LocalLLaMA/comments/1orrddh/minimax_m2_coding_plan_pricing_revealed/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orrddh | false | null | t3_1orrddh | /r/LocalLLaMA/comments/1orrddh/minimax_m2_coding_plan_pricing_revealed/ | false | false | 15 | null | |
Would 4 2080Ti build work well for local AI models ? With coding as target | 1 | hi, i just found a used build with a threadripper 2920x, 128Gb RAM (DDR4), and 4 x 2080Ti GPUs, it is up for a $2700. Would it be a good build to rely on ?
My most demanding usage of AI is coding, background agents (mainly opencode and browser use). i already have a 3090 system and using qwen3 coder 30B, Devestral, g... | 2025-11-08T14:46:29 | https://www.reddit.com/r/LocalLLaMA/comments/1orr6nl/would_4_2080ti_build_work_well_for_local_ai/ | UniqueAttourney | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orr6nl | false | null | t3_1orr6nl | /r/LocalLLaMA/comments/1orr6nl/would_4_2080ti_build_work_well_for_local_ai/ | false | false | self | 1 | null |
8 channels that will teach Reddit Group Professional more skills than a 4-year degree. | 1 | [removed] | 2025-11-08T13:57:43 | https://newsaffairng.com/2024/05/05/8-channels-that-will-teach-you-more-skills-than-a-4-year-degree/ | dinokall40 | newsaffairng.com | 1970-01-01T00:00:00 | 0 | {} | 1orq29t | false | null | t3_1orq29t | /r/LocalLLaMA/comments/1orq29t/8_channels_that_will_teach_reddit_group/ | false | false | default | 1 | null |
Figured out why my 3090 is so slow in inference | 1 | Discovered that my 3090 performed similarly with my 3050 using HF transformers for inference.
[https://www.reddit.com/r/LocalLLaMA/comments/1oriraf/how\_come\_my\_3090\_is\_just\_as\_fast\_as\_my\_3050\_for/](https://www.reddit.com/r/LocalLLaMA/comments/1oriraf/how_come_my_3090_is_just_as_fast_as_my_3050_for/)
Since ... | 2025-11-08T13:46:00 | https://www.reddit.com/r/LocalLLaMA/comments/1orpsyv/figured_out_why_my_3090_is_so_slow_in_inference/ | Ok_Warning2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orpsyv | false | null | t3_1orpsyv | /r/LocalLLaMA/comments/1orpsyv/figured_out_why_my_3090_is_so_slow_in_inference/ | false | false | self | 1 | null |
Downloading pre-lowered models (e.g. to xnnpack) | 0 | Not sure if I'm expecting too much, but is there somewhere I can download .pte files of models already lowered to xnnpack or other backends? I think it's a good idea to save the effort of exporting and lowering myself. I tried searching for xnnpack on the HF downloads page, but there's only a handful. Any other ways? O... | 2025-11-08T13:42:49 | https://www.reddit.com/r/LocalLLaMA/comments/1orpqda/downloading_prelowered_models_eg_to_xnnpack/ | datashri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orpqda | false | null | t3_1orpqda | /r/LocalLLaMA/comments/1orpqda/downloading_prelowered_models_eg_to_xnnpack/ | false | false | self | 0 | null |
Text model that can produce nodes and edges in JSON | 2 | I need to draw knowledge graphs and I’m using Gemini 2.5 Flash to give me the JSON that renders it. However, it is too slow.
The output looks something like
{“type”: “node”, “id”: 123}, {“type”: “edge”, “from_id”: 123, “to_id”: 456}
What model could I look into? It would need to reason on the free text input that de... | 2025-11-08T13:21:40 | https://www.reddit.com/r/LocalLLaMA/comments/1orp9o9/text_model_that_can_produce_nodes_and_edges_in/ | BlueAdventurers | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orp9o9 | false | null | t3_1orp9o9 | /r/LocalLLaMA/comments/1orp9o9/text_model_that_can_produce_nodes_and_edges_in/ | false | false | self | 2 | null |
Best way to serve NVIDIA ASR at scale ? | 0 | Hi,
I want to serve a fine tuned Canary 1B flash model to serve hundreds of concurrent requests for short audio chunks. I do not have a Nvidia enterprise license.
What would be the most efficient framework to serve on a large GPU (say H100) (vllm, triton, …) ?
What would be a good config (batching, etc..) ?
Thanks in... | 2025-11-08T13:21:09 | https://www.reddit.com/r/LocalLLaMA/comments/1orp997/best_way_to_serve_nvidia_asr_at_scale/ | Leading_Lock_4611 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orp997 | false | null | t3_1orp997 | /r/LocalLLaMA/comments/1orp997/best_way_to_serve_nvidia_asr_at_scale/ | false | false | self | 0 | null |
What model and settings should I use with my setup? | 1 | I upgraded from a 1060 to a 5070 and now have a Ryzen 7 7700X with 32 GB of RAM. I only used 8 GB models before. Which models should I try first, and what settings should I change to get the best performance with my new setup? My favorite models so far: Wingless\_Imp 8B, L3.1-Dark, Planet-SpinFire-Uncensored-8B-D\_AU-Q... | 2025-11-08T13:10:14 | https://www.reddit.com/r/LocalLLaMA/comments/1orp105/what_model_and_settings_should_i_use_with_my_setup/ | NeatFollowing2612 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orp105 | false | null | t3_1orp105 | /r/LocalLLaMA/comments/1orp105/what_model_and_settings_should_i_use_with_my_setup/ | false | false | self | 1 | null |
Is NVIDIA Triton Worth it? | 0 | Hello, I currently own 4x Nvidia A2s and have been using Ollama & Comfy UI for my Gen AI needs. I myself ain't an AI developer and have little in-depth knowledge on how they work under the hood, I also mainly use text-models and image-models.
Is it worth going through the hassle to get NVIDIA Triton working? I managed... | 2025-11-08T13:08:45 | https://www.reddit.com/r/LocalLLaMA/comments/1orozy5/is_nvidia_triton_worth_it/ | Plaush | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orozy5 | false | null | t3_1orozy5 | /r/LocalLLaMA/comments/1orozy5/is_nvidia_triton_worth_it/ | false | false | self | 0 | null |
How is Kimi K2 Thinking faster than the non-thinking variant in their website? | 1 | [removed] | 2025-11-08T12:48:19 | https://www.reddit.com/r/LocalLLaMA/comments/1orokxb/how_is_kimi_k2_thinking_faster_than_the/ | amrear | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orokxb | false | null | t3_1orokxb | /r/LocalLLaMA/comments/1orokxb/how_is_kimi_k2_thinking_faster_than_the/ | false | false | self | 1 | null |
Starting with local LLM | 3 | Hi. I would like to run an LLM locally. It’s supposed to work like my second brain. It should be linked to a RAG, where I have all the information about my life (since birth if available) and would like to fill it further. The LLM should have access to it.
Why local? Safety.
What kind of hardware do I have? Actually ... | 2025-11-08T12:40:22 | https://www.reddit.com/r/LocalLLaMA/comments/1orof46/starting_with_local_llm/ | Murky_Poem_9321 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orof46 | false | null | t3_1orof46 | /r/LocalLLaMA/comments/1orof46/starting_with_local_llm/ | false | false | self | 3 | null |
ROCm(6.4, using latest LLVM) vs ROCm 7 (lemonade sdk) | 14 | One observation I would like to paste in here:
By building llama.cpp with ROCm from scratch (HIP SDK version 6.4), I was able to get more performance than lemonade sdk for ROCm 7.
FYI: I keep changing path of llama.cpp so on first run path was given to ROCm 7 and on second run path was given to ROCm 6.4
Here are som... | 2025-11-08T12:32:29 | https://www.reddit.com/r/LocalLLaMA/comments/1oro9ng/rocm64_using_latest_llvm_vs_rocm_7_lemonade_sdk/ | CyBerDreadWing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oro9ng | false | null | t3_1oro9ng | /r/LocalLLaMA/comments/1oro9ng/rocm64_using_latest_llvm_vs_rocm_7_lemonade_sdk/ | false | false | self | 14 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.