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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
How good Orange Pi 6 for local llm? | 4 | Has anyone tried the Orange Pi 6 (like this one from amazon) for llm? Is it possible to run 3B or 8B LLMs in this?
| 2025-11-08T12:26:28 | Middle_Investment_81 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oro5iz | false | null | t3_1oro5iz | /r/LocalLLaMA/comments/1oro5iz/how_good_orange_pi_6_for_local_llm/ | false | false | default | 4 | {'enabled': True, 'images': [{'id': 'xn6cjjgz010g1', 'resolutions': [{'height': 59, 'url': 'https://preview.redd.it/xn6cjjgz010g1.jpeg?width=108&crop=smart&auto=webp&s=868fa1a1386d313bc02c4c1d3007ea9e30e07515', 'width': 108}, {'height': 119, 'url': 'https://preview.redd.it/xn6cjjgz010g1.jpeg?width=216&crop=smart&auto=w... | |
Best GUI for LLM based story writing that can access external models? | 5 | Most GUIs want to run the models themself, but I'd like to run it myself or use an on campus service that provide an OpenAI compatible API access. And for my Ooba installation the Playground extension isn't working at the moment.
So, long story short:
What are your recommendations for a GUI tool that's helping me to ... | 2025-11-08T12:11:29 | https://www.reddit.com/r/LocalLLaMA/comments/1ornvm0/best_gui_for_llm_based_story_writing_that_can/ | StableLlama | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ornvm0 | false | null | t3_1ornvm0 | /r/LocalLLaMA/comments/1ornvm0/best_gui_for_llm_based_story_writing_that_can/ | false | false | self | 5 | null |
Handy : Free, Offline AI dictation app for PC, supports Whisper and Parakeet models | 34 | Handy is a trending GitHub repo which is a free alternate for Wispr Flow for AI dictation. The app size is quite small and it supports all Parakeet (nvidia) and Whisper model for speech to text.
GitHub : https://github.com/cjpais/Handy
Demo : https://youtu.be/1QzXdhVeOkI?si=yli8cfejvOy3ERbo | 2025-11-08T11:32:08 | https://www.reddit.com/r/LocalLLaMA/comments/1orn6q4/handy_free_offline_ai_dictation_app_for_pc/ | Technical-Love-8479 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orn6q4 | false | null | t3_1orn6q4 | /r/LocalLLaMA/comments/1orn6q4/handy_free_offline_ai_dictation_app_for_pc/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'hFauF7dmVtT_NpKwLXwWj1k200bWFLqifX4gF1Eb7YE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/hFauF7dmVtT_NpKwLXwWj1k200bWFLqifX4gF1Eb7YE.png?width=108&crop=smart&auto=webp&s=43dee1447ab88ec0e999d6cbd5a633ab22554878', 'width': 108}, {'height': 108, 'url': 'h... |
Kimi K2 Thinking was trained with only $4.6 million | 647 | OpenAI: "We need government support to cover $1.4 trillion in chips and data centers."
Kimi:
https://preview.redd.it/03swwvpfo00g1.png?width=1199&format=png&auto=webp&s=f97e99e5a5aac5bb23a62ff58df048f5db678e09
| 2025-11-08T11:16:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ormxoq/kimi_k2_thinking_was_trained_with_only_46_million/ | InternationalAsk1490 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ormxoq | false | null | t3_1ormxoq | /r/LocalLLaMA/comments/1ormxoq/kimi_k2_thinking_was_trained_with_only_46_million/ | false | false | 647 | null | |
Introducing Crane: An All-in-One Rust Engine for Local AI | 1 | [removed] | 2025-11-08T11:10:27 | https://www.reddit.com/r/LocalLLaMA/comments/1ormtrt/introducing_crane_an_allinone_rust_engine_for/ | LewisJin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ormtrt | false | null | t3_1ormtrt | /r/LocalLLaMA/comments/1ormtrt/introducing_crane_an_allinone_rust_engine_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'KzjmVQ0CPFWzhCTQQ4uDeG1fchbaMketLdAXtOh9mqc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KzjmVQ0CPFWzhCTQQ4uDeG1fchbaMketLdAXtOh9mqc.png?width=108&crop=smart&auto=webp&s=bddf14f8ee6db387faa821dffa5277789dfdbfa1', 'width': 108}, {'height': 108, 'url': 'h... |
Honey we shrunk MiniMax M2 | 160 | Hi folks, we pruned MiniMax M2 from 250B to 192B (~25%) with only ~5% loss in coding quality. We did this with $200 worth of 8XH200 compute. Our 50% pruned model is ETA 5 more days. Would love to hear your feedback and would you want a 50% pruned Kimi K2 Thinking?
| 2025-11-08T10:04:06 | https://huggingface.co/collections/VibeStudio/thrift | arjunainfinity | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1orlqmh | false | null | t3_1orlqmh | /r/LocalLLaMA/comments/1orlqmh/honey_we_shrunk_minimax_m2/ | false | false | default | 160 | {'enabled': False, 'images': [{'id': 'ehjUFeUe3VAS2s784qCwiz1JNp5TRqMKwWsfk9mVQNM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/ehjUFeUe3VAS2s784qCwiz1JNp5TRqMKwWsfk9mVQNM.png?width=108&crop=smart&auto=webp&s=ee2bd2a3c053601dc326d886fd0014fd8ce175ab', 'width': 108}, {'height': 116, 'url': 'h... |
Terminal based inference on a Mac with lots of model options | 0 | Hi friends,
I've been using my 128GB M4 Max with Ollama for some time and I have weaved local models into my work especially whilst travelling or in places without stable internet. It's been great, plus privacy which is important.
However, recently I'm constantly disappointed by Ollama's selection of models (n... | 2025-11-08T09:55:42 | https://www.reddit.com/r/LocalLLaMA/comments/1orllo7/terminal_based_inference_on_a_mac_with_lots_of/ | anonXMR | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orllo7 | false | null | t3_1orllo7 | /r/LocalLLaMA/comments/1orllo7/terminal_based_inference_on_a_mac_with_lots_of/ | false | false | self | 0 | null |
New build LLaMA - Lenovo P920 base - How to make for max large context? | 1 | Im building a local server, as I am doing some AI stuff and need really long context windows.
I have a decent desktop.. 7800x3d 192Gb DDR5 6000 5070ti.. but its not quite there for really big models and really big context windows. Plus given these will mostly be CPU hosted, I don't want to tie up my main box for days... | 2025-11-08T09:18:29 | https://www.reddit.com/r/LocalLLaMA/comments/1orl0r9/new_build_llama_lenovo_p920_base_how_to_make_for/ | phido3000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orl0r9 | false | null | t3_1orl0r9 | /r/LocalLLaMA/comments/1orl0r9/new_build_llama_lenovo_p920_base_how_to_make_for/ | false | false | self | 1 | null |
Ready-to-use local Claude Code or Codex like agent that can grind for hours and actually deliver | 2 | First up: I’m very comfortable with LLMs and local AI like ComfyUI and other machine learning stuff, and I’ve got an RTX 5090 + 4060 Ti I want to put to good use.
So what I’m wondering if it exists is a mostly ready-to-use, Gemini CLI / Claude Code–like system that prioritizes output quality over speed and can run for... | 2025-11-08T08:27:48 | https://www.reddit.com/r/LocalLLaMA/comments/1ork81m/readytouse_local_claude_code_or_codex_like_agent/ | Elwii04 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ork81m | false | null | t3_1ork81m | /r/LocalLLaMA/comments/1ork81m/readytouse_local_claude_code_or_codex_like_agent/ | false | false | self | 2 | null |
Audio to audio conversation model | 0 | Are there any open source or open weights audio to audio conversation models like chatgpts audio chat? How much VRAM do they need and which quant is ok to use? | 2025-11-08T08:23:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ork5fm/audio_to_audio_conversation_model/ | IKerimI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ork5fm | false | null | t3_1ork5fm | /r/LocalLLaMA/comments/1ork5fm/audio_to_audio_conversation_model/ | false | false | self | 0 | null |
Grammar for structured output in llama.cpp: useful? | 2 | I’ve been exploring the grammar-based output constraint feature in **llama.cpp**, which allows guiding model output using **GEBNF** grammars. On paper it sounds super useful for ensuring structured output, preventing hallucinated fields, or enforcing strict JSON/XML schemas.
Feature reference:
[https://github.com/gger... | 2025-11-08T08:04:56 | https://www.reddit.com/r/LocalLLaMA/comments/1orjv37/grammar_for_structured_output_in_llamacpp_useful/ | -lq_pl- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orjv37 | false | null | t3_1orjv37 | /r/LocalLLaMA/comments/1orjv37/grammar_for_structured_output_in_llamacpp_useful/ | false | false | self | 2 | null |
How come my 3090 is just as fast as my 3050 for Qwen3-1.7B? | 0 | Both are running at 5t/s inference when 3090 has 936GB/s and 3050 6GB only 168GB/s. Is there something wrong with my inference script?
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
import time
model_name = "Qwen/Qwen3-1.7B"
# load the tokenizer and the model
... | 2025-11-08T06:57:04 | https://www.reddit.com/r/LocalLLaMA/comments/1oriraf/how_come_my_3090_is_just_as_fast_as_my_3050_for/ | Ok_Warning2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oriraf | false | null | t3_1oriraf | /r/LocalLLaMA/comments/1oriraf/how_come_my_3090_is_just_as_fast_as_my_3050_for/ | false | false | self | 0 | null |
Building ToolNeuron: a modular, plugin‑based AI assistant ecosystem for Android. Early stage — looking for feedback from devs & power users. | 0 | Hey everyone,
I’m building **ToolNeuron**, a local/online AI assistant platform for Android. It’s designed to support plugins, private data sets, and modular architecture. Right now, we have a proof-of-concept and a GitHub repo, and I’m curious whether devs/users find value in this approach.
Some questions I’d love y... | 2025-11-08T06:32:56 | https://www.reddit.com/r/LocalLLaMA/comments/1oricyh/building_toolneuron_a_modular_pluginbased_ai/ | DarkEngine774 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oricyh | false | null | t3_1oricyh | /r/LocalLLaMA/comments/1oricyh/building_toolneuron_a_modular_pluginbased_ai/ | false | false | self | 0 | null |
Ollama vs vLLM for Linux distro | 0 | hi Guyz, just wanted to ask which service would be better in my case of building a Linux distro integrated with llama 3 8B ik vLLm has higher token/sec but the fp16 makes it a huge dealbreaker any solutions | 2025-11-08T05:56:07 | https://www.reddit.com/r/LocalLLaMA/comments/1orhpq8/ollama_vs_vllm_for_linux_distro/ | Enough-Ant-1512 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orhpq8 | false | null | t3_1orhpq8 | /r/LocalLLaMA/comments/1orhpq8/ollama_vs_vllm_for_linux_distro/ | false | false | self | 0 | null |
Built a Easy Ai Library for Mobile Developers | 3 | Here I the demo video, right now the library supports
- Text & Image Embedding
- VLM
- Text Generation
- Tool Calling
- TTS & STT
The aim of making this library to Unify All Offline Ai Provider into a single library, that is easy to use for new Mobile App Developers | 2025-11-08T05:30:57 | https://v.redd.it/o3dsareuyyzf1 | DarkEngine774 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1orha0x | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/o3dsareuyyzf1/DASHPlaylist.mpd?a=1765171871%2CZmY3YjE0Mjk4NGZhNGIxODMyMWM0MTYzZGE3YzkxODRiYmM0OGIzOWVmZDQ5NTEwMWQyNWFhY2I2NDU5NTdiMQ%3D%3D&v=1&f=sd', 'duration': 47, 'fallback_url': 'https://v.redd.it/o3dsareuyyzf1/CMAF_720.mp4?source=fallback', 'ha... | t3_1orha0x | /r/LocalLLaMA/comments/1orha0x/built_a_easy_ai_library_for_mobile_developers/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'YWloZ3A2ZHV5eXpmMW0lUWiw7bwD4bSpINkIhCOddcAHqk5kgwOu2OsKBruV', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/YWloZ3A2ZHV5eXpmMW0lUWiw7bwD4bSpINkIhCOddcAHqk5kgwOu2OsKBruV.png?width=108&crop=smart&format=pjpg&auto=webp&s=86b671668491b5c3584ba5e9b432d649b708... | |
Training framework that monitors itself and auto-fixes issues (gradient explosions, OOM, MoE imbalance) - looking for feedback | 11 | # I built a training framework that automatically fixes gradient explosions, OOM errors, and MoE expert collapse
Hey LocalLLaMA! Tired of babysitting training runs? I built **LuminaAI** \- a framework where the system monitors itself and makes real-time decisions to keep training stable.
# What it does:
**Autonomous... | 2025-11-08T02:55:02 | https://www.reddit.com/r/LocalLLaMA/comments/1ore9xo/training_framework_that_monitors_itself_and/ | Huge_Protection2600 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ore9xo | false | null | t3_1ore9xo | /r/LocalLLaMA/comments/1ore9xo/training_framework_that_monitors_itself_and/ | false | false | self | 11 | {'enabled': False, 'images': [{'id': 'ZAs0CL2a8oIvlDAplY9gJJoD_oWB6ghFrLTQRVaVYcY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ZAs0CL2a8oIvlDAplY9gJJoD_oWB6ghFrLTQRVaVYcY.png?width=108&crop=smart&auto=webp&s=8bb862ade0f5e89d9f3c39d3d1e0436e59b4ad2f', 'width': 108}, {'height': 108, 'url': 'h... |
Kimi K2 thinking repeatedly goes into infinite thinking look on fairly simple tasks | 1 | 2025-11-08T02:23:23 | https://www.reddit.com/r/LocalLLaMA/comments/1ordmuz/kimi_k2_thinking_repeatedly_goes_into_infinite/ | championswimmer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ordmuz | false | null | t3_1ordmuz | /r/LocalLLaMA/comments/1ordmuz/kimi_k2_thinking_repeatedly_goes_into_infinite/ | false | false | 1 | null | ||
We got this, we can do it! When is the REAP’d iQ_001_XXS GGUF dropping? | 1,073 | 2025-11-08T02:15:28 | Porespellar | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ordgys | false | null | t3_1ordgys | /r/LocalLLaMA/comments/1ordgys/we_got_this_we_can_do_it_when_is_the_reapd_iq_001/ | false | false | 1,073 | {'enabled': True, 'images': [{'id': 'YVLalEujkoOmjNi9AgtYkJNaIgUzmy_3-MdwRgaZ2aE', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/qfahc43zzxzf1.jpeg?width=108&crop=smart&auto=webp&s=005e45deb6404261caa9171b31e72a0573a8b99e', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/qfahc43zzxzf1.j... | |||
[Web Demo] Qwen-Image-Edit — Camera angle control (HF Space) | 17 | Very Cool Tool.
https://preview.redd.it/z1nmida0zxzf1.png?width=900&format=png&auto=webp&s=fc5f06a9e2105a5db39e4644ef805606c65873eb
Upload an image, then tweak **camera motion/rotation/lens** sliders to generate new viewpoints—right in your browser. [Hugging Face](https://huggingface.co/spaces/linoyts/Qwen-Image-E... | 2025-11-08T02:10:18 | https://www.reddit.com/r/LocalLLaMA/comments/1ordd5x/web_demo_qwenimageedit_camera_angle_control_hf/ | freesysck | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ordd5x | false | null | t3_1ordd5x | /r/LocalLLaMA/comments/1ordd5x/web_demo_qwenimageedit_camera_angle_control_hf/ | false | false | 17 | null | |
China winning the race? Or a bubble about to burst? | 0 | With the latest releases — Qwen 3 Max Thinking, Kimi K2 Thinking, and Minimax M2 — China is catching up to the U.S., despite using far fewer chips. What can we conclude? Are the Chinese outperforming with limited hardware, or has the bubble reached its peak — explaining why they’ve now matched the Americans? | 2025-11-08T01:20:48 | https://www.reddit.com/r/LocalLLaMA/comments/1orcbkw/china_winning_the_race_or_a_bubble_about_to_burst/ | Objective_Lab_3182 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orcbkw | false | null | t3_1orcbkw | /r/LocalLLaMA/comments/1orcbkw/china_winning_the_race_or_a_bubble_about_to_burst/ | false | false | self | 0 | null |
Loki - An All-in-One, Batteries-Included LLM CLI | 8 | # [Introducing: Loki! An all-in-one, batteries-included LLM CLI tool](https://github.com/Dark-Alex-17/loki)
https://i.redd.it/r4joue0wixzf1.gif
[Loki](https://github.com/Dark-Alex-17/loki) started out as a fork of the fantastic [AIChat CLI](https://github.com/sigoden/aichat), where I just wanted to give it first-clas... | 2025-11-08T01:10:55 | https://www.reddit.com/r/LocalLLaMA/comments/1orc401/loki_an_allinone_batteriesincluded_llm_cli/ | Hamilcar_Barca_17 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orc401 | false | null | t3_1orc401 | /r/LocalLLaMA/comments/1orc401/loki_an_allinone_batteriesincluded_llm_cli/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'LXEUPYvJzyTsJyAiWUpM817Z60b-xoBKT3vo7H-zFd0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/LXEUPYvJzyTsJyAiWUpM817Z60b-xoBKT3vo7H-zFd0.png?width=108&crop=smart&auto=webp&s=db135dcf9e00c010ac5884ca286d420675da904a', 'width': 108}, {'height': 108, 'url': 'h... |
Claude cli with glm and enabled memory? | 0 | Hi all,
I am running Claude cli with glm, trying to explore it doing research and stuff.
I read that’s there’s the memory function, is it possible for me to host a mcp that replicate this feature?
If anyone have done something similar can you kind point me in the direction 😀 | 2025-11-08T01:07:03 | https://www.reddit.com/r/LocalLLaMA/comments/1orc12a/claude_cli_with_glm_and_enabled_memory/ | Alrightly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orc12a | false | null | t3_1orc12a | /r/LocalLLaMA/comments/1orc12a/claude_cli_with_glm_and_enabled_memory/ | false | false | self | 0 | null |
Best local ai for m5? | 0 | Hey guys!
I just got an m5 MacBook Pro with 1tb storage and 24gb ram(I know it’s not ai configured but I am a photographer/video editor so give me a break 😅)
I would like to stop giving OpenAI my money every month to run their ai with no privacy.
What is the best local llm I can run on my hardware?
I would lik... | 2025-11-08T01:05:48 | https://www.reddit.com/r/LocalLLaMA/comments/1orc023/best_local_ai_for_m5/ | Hour-Heron9030 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orc023 | false | null | t3_1orc023 | /r/LocalLLaMA/comments/1orc023/best_local_ai_for_m5/ | false | false | self | 0 | null |
Modules or tips for NSFW text editing? | 0 | Hey LocalLLaMA! While this might not be the "best" place to ask this question. This community seems to have better knowledge around modules and tools.
I've been playing with LM Studio and Ollama (rookie) and struggling with NSFW content even subtle in some of my stories. I've successfully leveraged both tools for doz... | 2025-11-08T00:56:55 | https://www.reddit.com/r/LocalLLaMA/comments/1orbt5y/modules_or_tips_for_nsfw_text_editing/ | Acrobatic-West490 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1orbt5y | false | null | t3_1orbt5y | /r/LocalLLaMA/comments/1orbt5y/modules_or_tips_for_nsfw_text_editing/ | false | false | nsfw | 0 | null |
Unable to get expected output from llama.cpp with audio models | 7 | I'm trying to get audio-input working with llama.cpp. So far I've tried Voxtral and Qwen2.5 Omni. When I try Voxtral via `.\llama\llama-server --model .\Voxtral-Mini-3B-2507-Q4_K_M.gguf --mmproj .\mmproj-Voxtral-Mini-3B-2507-Q8_0.gguf` I end up with a working chat but every time I send in an audio file and ask it to de... | 2025-11-07T23:30:57 | https://www.reddit.com/r/LocalLLaMA/comments/1or9v99/unable_to_get_expected_output_from_llamacpp_with/ | TomatoCo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or9v99 | false | null | t3_1or9v99 | /r/LocalLLaMA/comments/1or9v99/unable_to_get_expected_output_from_llamacpp_with/ | false | false | self | 7 | null |
Kimi K2 Thinking is the #2 open-source model on our leaderboard | 1 | [removed] | 2025-11-07T22:35:01 | https://www.reddit.com/r/LocalLLaMA/comments/1or8imp/kimi_k2_thinking_is_the_2_opensource_model_on_our/ | Direct-Salary-4666 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or8imp | false | null | t3_1or8imp | /r/LocalLLaMA/comments/1or8imp/kimi_k2_thinking_is_the_2_opensource_model_on_our/ | false | false | self | 1 | null |
Artificial Analysis has released a more in-depth benchmark breakdown of Kimi K2 Thinking (2nd image) | 114 | 2025-11-07T22:30:30 | https://www.reddit.com/gallery/1or8ehk | averagebear_003 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1or8ehk | false | null | t3_1or8ehk | /r/LocalLLaMA/comments/1or8ehk/artificial_analysis_has_released_a_more_indepth/ | false | false | default | 114 | null | |
Best LLM API for mass code translation? | 0 | Hello. I need to use an LLM to translate 300k+ code files into a different programming language. The code in all files is rather short and handles common tasks so the task should no be very difficult. Is there a api you can recommend me with a cood cost to performance ratio so i get usable results without going broke?
... | 2025-11-07T22:26:54 | https://www.reddit.com/r/LocalLLaMA/comments/1or8bcf/best_llm_api_for_mass_code_translation/ | CumDrinker247 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or8bcf | false | null | t3_1or8bcf | /r/LocalLLaMA/comments/1or8bcf/best_llm_api_for_mass_code_translation/ | false | false | self | 0 | null |
Working Dockerfile for gpt-oss-120b on 4x RTX 3090 (vLLM + MXFP4) | 0 | Has anyone here successfully set up gpt-oss-120b on ubuntu with 4x RTX 3090 GPUs using Docker and vLLM? Could anyone be kind enough to share their working Dockerfile?
I successfully built the image from this Dockerfile: [https://www.reddit.com/r/LocalLLaMA/comments/1mkefbx/gptoss120b\_running\_on\_4x\_3090\_with\_vllm... | 2025-11-07T21:14:09 | https://www.reddit.com/r/LocalLLaMA/comments/1or6huy/working_dockerfile_for_gptoss120b_on_4x_rtx_3090/ | iamn0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or6huy | false | null | t3_1or6huy | /r/LocalLLaMA/comments/1or6huy/working_dockerfile_for_gptoss120b_on_4x_rtx_3090/ | false | false | self | 0 | null |
Follow-up to the my Dual-RTX 3060 build (originally posted on r/Ollama): Now hitting 30 t/s on 8b models using 145W Power Limiting! | 4 | Hi, everybody!
I wanted to share the updated details of my budget-friendly, high-performance AI server that many of you may remember seeing on r/Ollama a while back.
I've since moved the full guide over to r/FrugalAI, but the core strategy is all about maximizing **local LLM performance per dollar**.
The biggest gam... | 2025-11-07T21:10:25 | https://www.reddit.com/r/FrugalAI/comments/1or4v9u/start_here_my_dualgpu_700_buildthe_frugalai/ | FrugalAI | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1or6ela | false | null | t3_1or6ela | /r/LocalLLaMA/comments/1or6ela/followup_to_the_my_dualrtx_3060_build_originally/ | false | false | default | 4 | null |
Is there a LLM guide for Dummies ? | 3 | I am interested in learning how to use LLM Locally and explore models from hugging face but I’m too dumb. Any step by step guide? | 2025-11-07T21:05:03 | https://www.reddit.com/r/LocalLLaMA/comments/1or69mr/is_there_a_llm_guide_for_dummies/ | Funnytingles | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or69mr | false | null | t3_1or69mr | /r/LocalLLaMA/comments/1or69mr/is_there_a_llm_guide_for_dummies/ | false | false | self | 3 | null |
ROCm installation support on windows. HELP PLS. | 3 | I am really new to this process, and I recently did a cuda llama.cpp build on my 3060 mobile GPU, faced very less issues.
Now I wanted to utilize the VRAM of my main PC GPU which has amd gpu, 7900 gre.
I went away and installed HIP SDK from here:
[Install HIP SDK — HIP SDK installation (Windows)](https://rocm.docs.... | 2025-11-07T20:57:04 | https://www.reddit.com/r/LocalLLaMA/comments/1or61zz/rocm_installation_support_on_windows_help_pls/ | CyBerDreadWing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or61zz | false | null | t3_1or61zz | /r/LocalLLaMA/comments/1or61zz/rocm_installation_support_on_windows_help_pls/ | false | false | self | 3 | null |
Who all agree with this defination of AGI ? | 0 | A paper by [safe Agi and Scale AI](https://www.agidefinition.ai/paper.pdf)
According to them, having a models score maximum in these 10 categories will lead to Artificial General Inteligence.
* General Knowledge (K)
* Reading and Writing Ability (RW)
* Mathematical Ability (M)
* On-the-Spot Reasoning (R)
* Working M... | 2025-11-07T20:44:16 | https://www.reddit.com/r/LocalLLaMA/comments/1or5qab/who_all_agree_with_this_defination_of_agi/ | GlitteringAdvisor530 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or5qab | false | null | t3_1or5qab | /r/LocalLLaMA/comments/1or5qab/who_all_agree_with_this_defination_of_agi/ | false | false | self | 0 | null |
Can someone explain Kokoro Space on HF for me? | 5 | 2025-11-07T20:42:33 | https://www.reddit.com/r/LocalLLaMA/comments/1or5ost/can_someone_explain_kokoro_space_on_hf_for_me/ | dreamyrhodes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or5ost | false | null | t3_1or5ost | /r/LocalLLaMA/comments/1or5ost/can_someone_explain_kokoro_space_on_hf_for_me/ | false | false | 5 | null | ||
Nvidia may cancel the RTX 50 Super due to a shortage of 3GB GDDR7 memory | 146 | For now it's just a rumor, but it seems the RTX Super cards will take a while to be released, if they ever are
https://www.techpowerup.com/342705/gddr7-shortage-could-stop-nvidia-geforce-rtx-50-series-super-rollout
https://www.guru3d.com/story/nvidia-may-cancel-or-delay-geforce-rtx-50-super-series-amid-gddr7-memory-s... | 2025-11-07T20:36:28 | https://www.reddit.com/r/LocalLLaMA/comments/1or5j9z/nvidia_may_cancel_the_rtx_50_super_due_to_a/ | Spiderboyz1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or5j9z | false | null | t3_1or5j9z | /r/LocalLLaMA/comments/1or5j9z/nvidia_may_cancel_the_rtx_50_super_due_to_a/ | false | false | self | 146 | {'enabled': False, 'images': [{'id': 'WjxfTpGZXDYcseppN_BS-JwjKz--VJljF1AheGesi7s', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/WjxfTpGZXDYcseppN_BS-JwjKz--VJljF1AheGesi7s.jpeg?width=108&crop=smart&auto=webp&s=044f5b39fa5a02ae74231c08af7b8abd82dab14a', 'width': 108}, {'height': 127, 'url': '... |
Vulkan vs. Rocm with R9700 AI Pro | 2 | Vulkan is small and fast, you can use models damn near the maximum 32 G vram with a 30k context window or even go beyond that with a 39 gb model to do partial vram offloading and it will still work with 2-3 tokens/s. Rocm is big, and you cant use model even if it's like 30 gb in size, it has to be substantially lower t... | 2025-11-07T20:30:53 | OldEffective9726 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1or5eat | false | null | t3_1or5eat | /r/LocalLLaMA/comments/1or5eat/vulkan_vs_rocm_with_r9700_ai_pro/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': '4b0vdrjp9wzf1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/4b0vdrjp9wzf1.jpeg?width=108&crop=smart&auto=webp&s=62b765914c099888760ba626741d8b8d8f6b145c', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/4b0vdrjp9wzf1.jpeg?width=216&crop=smart&auto=... | |
no cuda0 found just vulkan driver. easy question for a noob | 0 | Hello, i have this trouble and i don't know how to resolve it. sure it's a stupid question but i 've lost too many hours tryng different ways.
I have cuda 13 installed and latest nvidia drivers.
Fresh w10 installation.
I can use only vulcan driver... | 2025-11-07T20:27:34 | Flimsy_Leadership_81 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1or5b9n | false | null | t3_1or5b9n | /r/LocalLLaMA/comments/1or5b9n/no_cuda0_found_just_vulkan_driver_easy_question/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'jmo6y8e89wzf1', 'resolutions': [{'height': 9, 'url': 'https://preview.redd.it/jmo6y8e89wzf1.png?width=108&crop=smart&auto=webp&s=ee87b8416d11b4a59ba025f2e4842177d7100f87', 'width': 108}, {'height': 18, 'url': 'https://preview.redd.it/jmo6y8e89wzf1.png?width=216&crop=smart&auto=webp&... | |
What is dreaming? Synthetic data generation. | 4 | DreamGym from Meta is a new framework that lets AI agents train via synthetic reasoning-based experiences: [https://x.com/jiqizhixin/status/1986686971331195223](https://x.com/jiqizhixin/status/1986686971331195223)
Paper: [https://arxiv.org/abs/2511.03773](https://arxiv.org/abs/2511.03773) | 2025-11-07T20:22:07 | https://www.reddit.com/r/LocalLLaMA/comments/1or566s/what_is_dreaming_synthetic_data_generation/ | Terminator857 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or566s | false | null | t3_1or566s | /r/LocalLLaMA/comments/1or566s/what_is_dreaming_synthetic_data_generation/ | false | false | self | 4 | null |
Open-sourcing how we ship multi-user MCP servers to production with Oauth and secrets management built-in | 1 | [removed] | 2025-11-07T20:21:27 | https://www.reddit.com/r/LocalLLaMA/comments/1or55jk/opensourcing_how_we_ship_multiuser_mcp_servers_to/ | MostlyGreat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or55jk | false | null | t3_1or55jk | /r/LocalLLaMA/comments/1or55jk/opensourcing_how_we_ship_multiuser_mcp_servers_to/ | false | false | self | 1 | null |
Open-sourcing how we ship multi-user MCP servers to production with Oauth and secrets management built-in | 1 | [removed] | 2025-11-07T20:20:30 | https://www.reddit.com/r/LocalLLaMA/comments/1or54no/opensourcing_how_we_ship_multiuser_mcp_servers_to/ | MostlyGreat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or54no | false | null | t3_1or54no | /r/LocalLLaMA/comments/1or54no/opensourcing_how_we_ship_multiuser_mcp_servers_to/ | false | false | self | 1 | null |
Strange Issue with VRAM (ecc with non-ecc) Types on Vega VII and Mi50s | 0 | I posted this as an issue in llama cpp but I wanted to post it here to see if anyone has seen this issue before because it could just be something simple. I have a system with a Vega VII card (32 GB) and two Mi50s. I build llama cpp for gfx906 which is the same for all the cards. They are nearly identical, in a sense. ... | 2025-11-07T20:18:50 | https://www.reddit.com/r/LocalLLaMA/comments/1or534m/strange_issue_with_vram_ecc_with_nonecc_types_on/ | dionysio211 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or534m | false | null | t3_1or534m | /r/LocalLLaMA/comments/1or534m/strange_issue_with_vram_ecc_with_nonecc_types_on/ | false | false | self | 0 | null |
Best model for voice line generation | 1 | I'm trying to generate voice lines for a video game character. The only requirement is that I can adjust the emotions of the voice line. It also has to able to run on my RTX 2060 6gb. Kokoro sounds good but it seems like I can't adjust the emotions. I don't need voice cloning or training if it already has good voices ... | 2025-11-07T20:06:12 | https://www.reddit.com/r/LocalLLaMA/comments/1or4rcn/best_model_for_voice_line_generation/ | oldchicken34 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or4rcn | false | null | t3_1or4rcn | /r/LocalLLaMA/comments/1or4rcn/best_model_for_voice_line_generation/ | false | false | self | 1 | null |
Kimi K2 Thinking SECOND most intelligent LLM according to Artificial Analysis | 153 | 2025-11-07T20:04:53 | https://www.reddit.com/r/LocalLLaMA/comments/1or4q4m/kimi_k2_thinking_second_most_intelligent_llm/ | teatime1983 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or4q4m | false | null | t3_1or4q4m | /r/LocalLLaMA/comments/1or4q4m/kimi_k2_thinking_second_most_intelligent_llm/ | false | false | 153 | null | ||
Cerebras/Kimi-Linear-REAP-35B-A3B-Instruct · Hugging Face | 103 | 2025-11-07T19:44:19 | https://huggingface.co/cerebras/Kimi-Linear-REAP-35B-A3B-Instruct | maroule | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1or46rv | false | null | t3_1or46rv | /r/LocalLLaMA/comments/1or46rv/cerebraskimilinearreap35ba3binstruct_hugging_face/ | false | false | 103 | {'enabled': False, 'images': [{'id': 'A5NFpNf7XiO2gm9NBBYXrtttQxX4Zw8QmamAzVNdgao', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/A5NFpNf7XiO2gm9NBBYXrtttQxX4Zw8QmamAzVNdgao.png?width=108&crop=smart&auto=webp&s=fc3a89a07d3aee9e512db40844a7b15968d0f00a', 'width': 108}, {'height': 116, 'url': 'h... | ||
I just wanted to say - Hi - to Kimi K2 Thinking | 13 | Man... The existential angst is palpable... *sigh*
><think>The user said "Hi" in English. The AI Bot is supposed to be helpful and intelligent, and always answer in German.
>So I should respond to the greeting in German. A natural German response to "Hi" would be something like "Hallo!" or "Guten Tag!" Since the user... | 2025-11-07T19:42:40 | https://www.reddit.com/r/LocalLLaMA/comments/1or45ci/i_just_wanted_to_say_hi_to_kimi_k2_thinking/ | harlekinrains | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or45ci | false | null | t3_1or45ci | /r/LocalLLaMA/comments/1or45ci/i_just_wanted_to_say_hi_to_kimi_k2_thinking/ | false | false | self | 13 | null |
The best tools I’ve found for evaluating AI voice agents | 5 | I’ve been working on a voice agent project recently and quickly realized that building the pipeline (STT → LLM → TTS) is the easy part. The real challenge is evaluation, making sure the system performs reliably across accents, contexts, and multi-turn conversations.
I went down the rabbit hole of voice eval tools and ... | 2025-11-07T19:31:35 | https://www.reddit.com/r/LocalLLaMA/comments/1or3uyd/the_best_tools_ive_found_for_evaluating_ai_voice/ | llamacoded | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or3uyd | false | null | t3_1or3uyd | /r/LocalLLaMA/comments/1or3uyd/the_best_tools_ive_found_for_evaluating_ai_voice/ | false | false | self | 5 | null |
Zero Configuration AI | 1 | [removed] | 2025-11-07T19:30:43 | https://www.reddit.com/r/LocalLLaMA/comments/1or3u4z/zero_configuration_ai/ | NorthComplaint7631 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or3u4z | false | null | t3_1or3u4z | /r/LocalLLaMA/comments/1or3u4z/zero_configuration_ai/ | false | false | 1 | null | |
Some of the best tools for simulating LLM agents to test and evaluate behavior | 1 |
I've been looking for tools that go beyond one-off runs or traces, something that lets you simulate full tasks, test agents under different conditions, and evaluate performance as prompts or models change.
Here’s what I’ve found so far:
* LangSmith – Strong tracing and some evaluation support, but tightly coupled w... | 2025-11-07T19:21:39 | https://www.reddit.com/r/LocalLLaMA/comments/1or3ls7/some_of_the_best_tools_for_simulating_llm_agents/ | Educational-Bison786 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or3ls7 | false | null | t3_1or3ls7 | /r/LocalLLaMA/comments/1or3ls7/some_of_the_best_tools_for_simulating_llm_agents/ | false | false | self | 1 | null |
How do I use the NPU in my s25 for AI inference? | 0 | Basically I want to run LLM in the NPU but I really don't know what app to use, I've be using pocketpal but it support GPU only.
I also ran local dream for NPU SD inference with success, even though I was mentally unable to convert bigger SD models to the weird format used by the app.
any suggestion about what apps ... | 2025-11-07T19:09:33 | https://www.reddit.com/r/LocalLLaMA/comments/1or3a78/how_do_i_use_the_npu_in_my_s25_for_ai_inference/ | weener69420 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or3a78 | false | null | t3_1or3a78 | /r/LocalLLaMA/comments/1or3a78/how_do_i_use_the_npu_in_my_s25_for_ai_inference/ | false | false | self | 0 | null |
Recently built my first LLM and im wondering why there hasn't been more innovation on moving away from transformers and gradient descent? | 53 | So please excuse my lack of knowledge in this area as im new to AI/LLMs but I just recently build my first micro llm and I dunno something about them seems wrong.
Is the industry stuck on transformers and gradient descent because coming up with alternatives is a hugely difficult problem or is the industry just having ... | 2025-11-07T19:01:17 | https://www.reddit.com/r/LocalLLaMA/comments/1or323v/recently_built_my_first_llm_and_im_wondering_why/ | CelebrationMinimum50 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or323v | false | null | t3_1or323v | /r/LocalLLaMA/comments/1or323v/recently_built_my_first_llm_and_im_wondering_why/ | false | false | self | 53 | null |
Finally, an open-source voice AI that controls more than just the basics on Android | 3 | Hey everyone,
Just wanted to share something really cool my friend is building. It's an open-source AI assistant for Android called Panda. The way it works is pretty neat: you can control your phone just with your voice.
And I don't just mean "set a timer" or basic commands. It's smart enough to actually use your app... | 2025-11-07T18:30:12 | https://v.redd.it/sl9cwkgbnvzf1 | nik-55 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1or28k8 | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/sl9cwkgbnvzf1/DASHPlaylist.mpd?a=1765132227%2CYmI2M2M3YTQ4OWFhOTYxZTNjZDM2Y2MyN2E5MmIwM2Q1MjQzOTdlNjU2MzI3MzZkYjZhMzVhODA4MzU0Y2FlMg%3D%3D&v=1&f=sd', 'duration': 103, 'fallback_url': 'https://v.redd.it/sl9cwkgbnvzf1/CMAF_480.mp4?source=fallback', 'h... | t3_1or28k8 | /r/LocalLLaMA/comments/1or28k8/finally_an_opensource_voice_ai_that_controls_more/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'N3Y0YXhqZ2JudnpmMTsf1aLVBAVrwUC9PJG-THjLWebDOsH4aUcJPSJRtcXC', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/N3Y0YXhqZ2JudnpmMTsf1aLVBAVrwUC9PJG-THjLWebDOsH4aUcJPSJRtcXC.png?width=108&crop=smart&format=pjpg&auto=webp&s=779bd7bb6792fc46b1f5f4d70b3a799756bb2... | |
Want to Learn More About Agentic AI | 5 | Hey everyone — I’ve built a few agentic AI systems around SaaS automation and coding tools.
I’m familiar with LangChain, LangGraph, RAG, tool calling, and MCP, but I want to learn more by contributing to real projects.
If you’re working on something in this space or know an open-source project looking for contributors... | 2025-11-07T18:21:38 | https://www.reddit.com/r/LocalLLaMA/comments/1or2077/want_to_learn_more_about_agentic_ai/ | Superb_Practice_4544 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or2077 | false | null | t3_1or2077 | /r/LocalLLaMA/comments/1or2077/want_to_learn_more_about_agentic_ai/ | false | false | self | 5 | null |
Custom AM5 x SXM2 Motherboard for a Budget AI Rig | 1 | Hey everyone, I'm looking for some feedback on my idea of making a custom motherboard that combines the AM5 socket with the SXM2 socket for an affordable and cost-effective AI rig for Ryzen CPU and V100 GPU. I'm a bit new to local AIs, and I'm also tight on budget.
While there are a lot of people using the SXM2-PCIe a... | 2025-11-07T18:04:33 | https://www.reddit.com/r/LocalLLaMA/comments/1or1jtc/custom_am5_x_sxm2_motherboard_for_a_budget_ai_rig/ | aero-spike | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or1jtc | false | null | t3_1or1jtc | /r/LocalLLaMA/comments/1or1jtc/custom_am5_x_sxm2_motherboard_for_a_budget_ai_rig/ | false | false | self | 1 | null |
I fine-tuned Gemma 3 1B for CLI command translation... but it runs 100% locally. 810MB, 1.5s inference on CPU. | 98 | **I built a locally-running NL→CLI translator by fine-tuning Gemma 3 1B with QLoRA.**
[\[Link to repo\]](https://github.com/pranavkumaarofficial/nlcli-wizard)
**TL;DR:** Built a privacy-first CLI copilot. No API calls, no subscriptions. Just 810MB of local AI that converts natural language to CLI commands.
https://p... | 2025-11-07T17:58:57 | https://www.reddit.com/r/LocalLLaMA/comments/1or1e7p/i_finetuned_gemma_3_1b_for_cli_command/ | theRealSachinSpk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or1e7p | false | null | t3_1or1e7p | /r/LocalLLaMA/comments/1or1e7p/i_finetuned_gemma_3_1b_for_cli_command/ | false | false | 98 | null | |
FULL Cursor Agent 2.0 System Prompt and Internal Tools | 4 | Latest update: 07/11/2025
I’ve just extracted and published the FULL Cursor Agent 2.0 System prompt and Internal tools. Over 8,000 tokens.
You can check it out here: [https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools](https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools) | 2025-11-07T17:58:44 | https://www.reddit.com/r/LocalLLaMA/comments/1or1e0s/full_cursor_agent_20_system_prompt_and_internal/ | Independent-Box-898 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or1e0s | false | null | t3_1or1e0s | /r/LocalLLaMA/comments/1or1e0s/full_cursor_agent_20_system_prompt_and_internal/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': '5Jh1Fs1KAd1szZuZCSTbpsNZWlumD-G_pA3yaiXlVYU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5Jh1Fs1KAd1szZuZCSTbpsNZWlumD-G_pA3yaiXlVYU.png?width=108&crop=smart&auto=webp&s=0478b64ed5d2278330356b088ab4b7f8149afc20', 'width': 108}, {'height': 108, 'url': 'h... |
fp8 native matmul accelerators are not coming until the release of m6 Macs? | 2 | Although Apple has added native matmuls for fp16 for m5s , but they still dont have native support for fp8 yet.. Perhaps by m6 they will have fp8 support, then fp4 for m7 in 2027?I hope they accelerate their hardware more and offer more affordable ram with their models! | 2025-11-07T17:47:27 | https://www.reddit.com/r/LocalLLaMA/comments/1or13gu/fp8_native_matmul_accelerators_are_not_coming/ | power97992 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or13gu | false | null | t3_1or13gu | /r/LocalLLaMA/comments/1or13gu/fp8_native_matmul_accelerators_are_not_coming/ | false | false | self | 2 | null |
How LLMs helped me diagnose what optometrists never did for me, until now | 0 | I have asymmetric astigmatism, and I also play video games quite a bit in addition to being an LLM hobbyist (and i'll be an ML engineer soon). I peaked top 3000 in Fortnite, and now I play Valorant and hover around ascendant. I never understood why I hit a wall right under competitive viability. I felt like I’d get fat... | 2025-11-07T17:36:29 | https://www.reddit.com/r/LocalLLaMA/comments/1or0sy0/how_llms_helped_me_diagnose_what_optometrists/ | m1tm0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or0sy0 | false | null | t3_1or0sy0 | /r/LocalLLaMA/comments/1or0sy0/how_llms_helped_me_diagnose_what_optometrists/ | false | false | self | 0 | null |
Kimi K2 reasoning local on a MBP / Mac Studio “cluster” at 20t/s ??!! | 0 | I do not understand how that is even possible, yes, I know the total 1 Trillion parameters are not active … so that helps, but how can you get that speed in a networked setup??!! Also the part that runs on the MBP, even if it is a M4Max 40 core should be way slower, defining the overall speed, no?
[https://www.you... | 2025-11-07T17:26:13 | https://www.reddit.com/r/LocalLLaMA/comments/1or0j04/kimi_k2_reasoning_local_on_a_mbp_mac_studio/ | Careless_Garlic1438 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or0j04 | false | null | t3_1or0j04 | /r/LocalLLaMA/comments/1or0j04/kimi_k2_reasoning_local_on_a_mbp_mac_studio/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '6GihBwRlwmb6XiQl2g55cXa0dtpwZrKAMJrBEFq4hCY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/6GihBwRlwmb6XiQl2g55cXa0dtpwZrKAMJrBEFq4hCY.jpeg?width=108&crop=smart&auto=webp&s=9fdfb17aa879317ed928b9cc2e9ee9d37e1ea97a', 'width': 108}, {'height': 162, 'url': '... |
OpenAI Pushes to Label Datacenters as ‘American Manufacturing’ Seeking Federal Subsidies After Preaching Independence | 306 | OpenAI is now lobbying to classify datacenter spending as “American manufacturing.”
In their recent submission, they explicitly advocate for Federal loan guarantees the same kind used to subsidize large-scale industrial projects.
So after all the talk about independence and no need for government help… Sam lied. Agai... | 2025-11-07T17:15:05 | Ok-Breakfast-4676 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1or08aq | false | null | t3_1or08aq | /r/LocalLLaMA/comments/1or08aq/openai_pushes_to_label_datacenters_as_american/ | false | false | 306 | {'enabled': True, 'images': [{'id': 'mvMjw-9S9JAa58u0p4WxQ8oKo9q_tlga4IRYJqkcT1U', 'resolutions': [{'height': 137, 'url': 'https://preview.redd.it/jq1jrz6kbvzf1.jpeg?width=108&crop=smart&auto=webp&s=032200c0e4d20fe649beda865e16be1b4806a19c', 'width': 108}, {'height': 274, 'url': 'https://preview.redd.it/jq1jrz6kbvzf1.j... | ||
huggingface models spouting gibberish? | 1 | hello everybody. im currently trying to train a 14b LoRA and have been running into some issues that just started last week and wanted to know if anybody else was running into similar.
i seem to only be able to load and use a model once, as when i close and re-serve it *something* happens and it begins to spew gibberi... | 2025-11-07T17:14:27 | https://www.reddit.com/r/LocalLLaMA/comments/1or07q1/huggingface_models_spouting_gibberish/ | videeternel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1or07q1 | false | null | t3_1or07q1 | /r/LocalLLaMA/comments/1or07q1/huggingface_models_spouting_gibberish/ | false | false | self | 1 | null |
New stealth model Polaris Alpha from Openrouter | 0 | New stealth model Polaris Alpha from Openrouter | 2025-11-07T16:44:02 | https://v.redd.it/w4hp2m7w5vzf1 | sirjoaco | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oqzedw | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/w4hp2m7w5vzf1/DASHPlaylist.mpd?a=1765125858%2CNWE1YWVhN2E0OTQ4MTI0ZjU2OGM1N2MwOTBlNjU1Nzk4OTRkNjA3ZjgyMDhkZjViZTMzMTRjNmZjMjA0ZDY3Mg%3D%3D&v=1&f=sd', 'duration': 27, 'fallback_url': 'https://v.redd.it/w4hp2m7w5vzf1/CMAF_1080.mp4?source=fallback', 'h... | t3_1oqzedw | /r/LocalLLaMA/comments/1oqzedw/new_stealth_model_polaris_alpha_from_openrouter/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'bTdzOWxtN3c1dnpmMWaLRFtlOaNnELcut79whFpV_-6R32Ak6GAiQHe4R0Dv', 'resolutions': [{'height': 66, 'url': 'https://external-preview.redd.it/bTdzOWxtN3c1dnpmMWaLRFtlOaNnELcut79whFpV_-6R32Ak6GAiQHe4R0Dv.png?width=108&crop=smart&format=pjpg&auto=webp&s=6f2855571f51486f709b6a85b17a0e5f90d7a... | |
Any Suggestions for Running Ai Models Completely Offline | 0 | Like is there a Android App That let's you run any Ai Model Completely Offline on Android Devices ?? | 2025-11-07T16:29:08 | https://www.reddit.com/r/LocalLLaMA/comments/1oqz04y/any_suggestions_for_running_ai_models_completely/ | DarkEngine774 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqz04y | false | null | t3_1oqz04y | /r/LocalLLaMA/comments/1oqz04y/any_suggestions_for_running_ai_models_completely/ | false | false | self | 0 | null |
Built a multi-LLM control center for €1,000 while funded startups burn €500k on the same thing | 0 | OpenAI dropped AgentKit and LinkedIn immediately declared it the "n8n killer" before even testing it.
This drives me crazy. Not because AgentKit is bad, but because everyone acts like OpenAI is the only option. You're either locked into their API or you're not building AI tools.
We started Navigator a few months ago ... | 2025-11-07T16:11:40 | https://www.reddit.com/r/LocalLLaMA/comments/1oqyjf1/built_a_multillm_control_center_for_1000_while/ | zakjaquejeobaum | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqyjf1 | false | null | t3_1oqyjf1 | /r/LocalLLaMA/comments/1oqyjf1/built_a_multillm_control_center_for_1000_while/ | false | false | self | 0 | null |
How practical is finetuning larger models with 4x 3090 setup? | 9 | I am thinking of building 4x3090 setup cause other options with large VRAM are quite expensive and not worth the buck. For instance, pro 6000 has 96gigs but costs around 10,000. OTH, 3090's VRAM could be pooled together so 4x3090 would have same VRAM (a bit slower though) but significantly cheaper.
Is it practical... | 2025-11-07T16:11:13 | https://www.reddit.com/r/LocalLLaMA/comments/1oqyix9/how_practical_is_finetuning_larger_models_with_4x/ | Specialist-Let9791 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqyix9 | false | null | t3_1oqyix9 | /r/LocalLLaMA/comments/1oqyix9/how_practical_is_finetuning_larger_models_with_4x/ | false | false | self | 9 | null |
AMA Announcement: Moonshot AI, The Opensource Frontier Lab Behind Kimi K2 Thinking SoTA Model (Monday, 8AM-11AM PST) | 353 | 2025-11-07T15:53:33 | XMasterrrr | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oqy1k7 | false | null | t3_1oqy1k7 | /r/LocalLLaMA/comments/1oqy1k7/ama_announcement_moonshot_ai_the_opensource/ | false | true | default | 353 | {'enabled': True, 'images': [{'id': '8v2luf5owuzf1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/8v2luf5owuzf1.jpeg?width=108&crop=smart&auto=webp&s=fabb883ff715a8b3e78dae2bcac5041a45236d86', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/8v2luf5owuzf1.jpeg?width=216&crop=smart&auto=... | ||
Vulnerability Inception: How AI Code Assistants Replicate and Amplify Security Flaws | 5 | Hi all, I'm sharing an article about prompt injection in Large Language Models (LLMs), specifically regarding coding and coding agents. The research shows that it's easy to manipulate LLMs into injecting backdoors and vulnerabilities into code, simply by embedding instructions in a comment, as the LLM will follow any i... | 2025-11-07T15:48:49 | https://github.com/ortegaalfredo/aiweaknesses/blob/main/ai_vulnerabilities_article.pdf | ortegaalfredo | github.com | 1970-01-01T00:00:00 | 0 | {} | 1oqxx8w | false | null | t3_1oqxx8w | /r/LocalLLaMA/comments/1oqxx8w/vulnerability_inception_how_ai_code_assistants/ | false | false | default | 5 | {'enabled': False, 'images': [{'id': '5sm3GRNGqkHPJJHTtLe5heJ60MTx9qDDMNLNZZnboms', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5sm3GRNGqkHPJJHTtLe5heJ60MTx9qDDMNLNZZnboms.png?width=108&crop=smart&auto=webp&s=79d328204fadc6291591bc5aecfecf80b29cc568', 'width': 108}, {'height': 108, 'url': 'h... |
From your experience for text only, how is Qwen3VL compared to Qwen3, does having a Visual module penalize the text-only capacities ? | 26 | Title.
Let's say `Qwen3-30B-A3B-Instruct-2507` excels at text only and long context.
What about `Qwen3-VL-30B-A3B-Instruct` if you use it as a text only model ? have you seen any quality loss ?
We're wondering if it make sense to have in one gpu Qwen3 VL and on another gpu Qwen3. | 2025-11-07T15:46:05 | https://www.reddit.com/r/LocalLLaMA/comments/1oqxuqs/from_your_experience_for_text_only_how_is_qwen3vl/ | LinkSea8324 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqxuqs | false | null | t3_1oqxuqs | /r/LocalLLaMA/comments/1oqxuqs/from_your_experience_for_text_only_how_is_qwen3vl/ | false | false | self | 26 | null |
AI observability: how i actually keep agents reliable in prod | 3 | AI observability isn’t about slapping a dashboard on your logs and calling it a day. here’s what i do, straight up, to actually know what my agents are doing (and not doing) in production:
* every agent run is traced, start to finish. i want to see every prompt, every tool call, every context change. if something goes... | 2025-11-07T15:38:45 | https://www.reddit.com/r/LocalLLaMA/comments/1oqxnw5/ai_observability_how_i_actually_keep_agents/ | Otherwise_Flan7339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqxnw5 | false | null | t3_1oqxnw5 | /r/LocalLLaMA/comments/1oqxnw5/ai_observability_how_i_actually_keep_agents/ | false | false | self | 3 | null |
AI service I can have a conversation with? Preferably with a face? | 1 | Hey y’all.
Sorry if this is the wrong place to ask. I’m conceptualising a board game and a key component of it would be an interactive agent that’s promotable and can have a convo in real time. I’m just unsure what service to use for this?
I can build something if needed if there are any SDKs to plug into
Thanks! | 2025-11-07T15:19:52 | https://www.reddit.com/r/LocalLLaMA/comments/1oqx60m/ai_service_i_can_have_a_conversation_with/ | Turbulent-Pattern653 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqx60m | false | null | t3_1oqx60m | /r/LocalLLaMA/comments/1oqx60m/ai_service_i_can_have_a_conversation_with/ | false | false | self | 1 | null |
Emergent Occam's Razor: Teaching qwen2.5:7b to learn through journaling (51%→78%) [Full code + paper] | 17 | I just finished an experiment where a 7B model learns through reflection and self-critique - no weight updates, no training data, just journaling about mistakes.
\*\*The surprising part: the model discovered Occam's Razor on its own.\*\*
\## The Setup
\- Model: qwen2.5:7b (local, via Ollama)
\- Task: Meeting ... | 2025-11-07T15:18:06 | https://www.reddit.com/r/LocalLLaMA/comments/1oqx4dj/emergent_occams_razor_teaching_qwen257b_to_learn/ | Next_Bid_8339 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqx4dj | false | null | t3_1oqx4dj | /r/LocalLLaMA/comments/1oqx4dj/emergent_occams_razor_teaching_qwen257b_to_learn/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'KC8jJJ4Xxr9hckVscbwLy5_BaBVS2HApQ7pvt_n18gU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KC8jJJ4Xxr9hckVscbwLy5_BaBVS2HApQ7pvt_n18gU.png?width=108&crop=smart&auto=webp&s=68f7078006489bb19388fc7ddc3472d620c40af3', 'width': 108}, {'height': 108, 'url': 'h... |
A Unique way to Run Your ai models On Mobile Devices | 0 | I know I know the video is little bit long
links :
- https://github.com/Siddhesh2377/ToolNeuron
- https://discord.com/invite/mVPwHDhrAP
- https://tool-neuron.vercel.app/ | 2025-11-07T15:04:37 | https://v.redd.it/5omrtxewnuzf1 | DarkEngine774 | /r/LocalLLaMA/comments/1oqwri1/a_unique_way_to_run_your_ai_models_on_mobile/ | 1970-01-01T00:00:00 | 0 | {} | 1oqwri1 | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/5omrtxewnuzf1/DASHPlaylist.mpd?a=1765249488%2COWQwMWE4YmE4ODAzZmU2MzFlYmE5YWYzY2YwYjQ2MWZiNGE1MmFkZDZiM2RjOWNlNjZkODJlNGFlODgyYzM1Mg%3D%3D&v=1&f=sd', 'duration': 594, 'fallback_url': 'https://v.redd.it/5omrtxewnuzf1/CMAF_720.mp4?source=fallback', 'h... | t3_1oqwri1 | /r/LocalLLaMA/comments/1oqwri1/a_unique_way_to_run_your_ai_models_on_mobile/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'YTBzaW51ZXdudXpmMTf_kA8xQOJkpqdZnrlblRxtOIoeOadMlvCYE39NluMF', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/YTBzaW51ZXdudXpmMTf_kA8xQOJkpqdZnrlblRxtOIoeOadMlvCYE39NluMF.png?width=108&crop=smart&format=pjpg&auto=webp&s=5ba65bd932640205990ceecca251803881af... | |
Using Ray, Unsloth, Axolotl or GPUStack? We are looking for beta testers | 2 | We are looking for beta testers to help us put the [Kalavai platform](https://github.com/kalavai-net/kalavai-client) through its paces.
If you are using **Ray** for distributed workloads, **Unsloth/Axolotl** for fine tuning models or **GPUStack** to manage your GPU cluster, we need you!
Sign up [here](https://kalava... | 2025-11-07T14:58:42 | https://www.reddit.com/r/LocalLLaMA/comments/1oqwloa/using_ray_unsloth_axolotl_or_gpustack_we_are/ | Good-Coconut3907 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqwloa | false | null | t3_1oqwloa | /r/LocalLLaMA/comments/1oqwloa/using_ray_unsloth_axolotl_or_gpustack_we_are/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '684qZO77d9-w1WgoMbVmRAClGDvTYPSXGqMzRZWkqBA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/684qZO77d9-w1WgoMbVmRAClGDvTYPSXGqMzRZWkqBA.png?width=108&crop=smart&auto=webp&s=4b9a7df5069327927423f687ac2f9078907265ba', 'width': 108}, {'height': 108, 'url': 'h... |
What we learned while building evaluation and observability workflows for multimodal AI agents | 1 | I’m one of the builders at Maxim AI, and over the past few months we’ve been working deeply on how to make evaluation and observability workflows more aligned with how real engineering and product teams actually build and scale AI systems.
When we started, we looked closely at the strengths of existing platforms; Fidd... | 2025-11-07T14:51:27 | https://www.reddit.com/r/LocalLLaMA/comments/1oqwfak/what_we_learned_while_building_evaluation_and/ | dinkinflika0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqwfak | false | null | t3_1oqwfak | /r/LocalLLaMA/comments/1oqwfak/what_we_learned_while_building_evaluation_and/ | false | false | self | 1 | null |
A Small Demo Of My Project, Not looking for promotion, Just need Honest Feedback | 1 | I know I know the video is little bit long | 2025-11-07T14:26:42 | https://v.redd.it/fbwb53oghuzf1 | DarkEngine774 | /r/LocalLLaMA/comments/1oqvtch/a_small_demo_of_my_project_not_looking_for/ | 1970-01-01T00:00:00 | 0 | {} | 1oqvtch | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/fbwb53oghuzf1/DASHPlaylist.mpd?a=1765247207%2CM2VlODIzNzcwOTI3NjdhOWU1N2E2Yzk4ZDEwMmVlYjQwN2JmODYwOWUwZWE5ZTI4YjNiNDMwMzgzZGVjYzNmYQ%3D%3D&v=1&f=sd', 'duration': 594, 'fallback_url': 'https://v.redd.it/fbwb53oghuzf1/CMAF_720.mp4?source=fallback', 'h... | t3_1oqvtch | /r/LocalLLaMA/comments/1oqvtch/a_small_demo_of_my_project_not_looking_for/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'dWt1cDFxd29ndXpmMR4Qs7uCZ54HCqhyA4O-tE5gQvXEQJntW-_rPzK3Qbo6', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/dWt1cDFxd29ndXpmMR4Qs7uCZ54HCqhyA4O-tE5gQvXEQJntW-_rPzK3Qbo6.png?width=108&crop=smart&format=pjpg&auto=webp&s=c3068ca5e0929e99eb2468f81e34a56909cf... | |
Errors installing Ryzen-AI 1.6.1 on a Windows 11 AMD AI Max 395 system | 1 | Has anyone managed to successfully install Ryzen-AI-1.6.1 on this system or any similar system? I have installed all the prerequisites and configured paths to python etc. That all seems to be fine. But I'm getting the following error late on in the installation:
CondaHTTPError: HTTP 000 CONNECTION FAILED for url <htt... | 2025-11-07T14:01:36 | https://www.reddit.com/r/LocalLLaMA/comments/1oqv6s9/errors_installing_ryzenai_161_on_a_windows_11_amd/ | exoplanetman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqv6s9 | false | null | t3_1oqv6s9 | /r/LocalLLaMA/comments/1oqv6s9/errors_installing_ryzenai_161_on_a_windows_11_amd/ | false | false | self | 1 | null |
Kimi K2 Thinking with sglang and mixed GPU / ktransformers CPU inference @ 31 tokens/sec | 118 | Just got Kimi K2 Thinking running locally and I'm blown away how fast it runs in simple chat tests: approximately ~ 30 tokens/sec with 4000 tokens in the context. Obviously a lot more testing to be done, but wow... a trillion parameter model running at 30 tokens/sec.
I'll whip up some tests around batching and availa... | 2025-11-07T13:28:44 | https://www.reddit.com/r/LocalLLaMA/comments/1oquezp/kimi_k2_thinking_with_sglang_and_mixed_gpu/ | __JockY__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oquezp | false | null | t3_1oquezp | /r/LocalLLaMA/comments/1oquezp/kimi_k2_thinking_with_sglang_and_mixed_gpu/ | false | false | self | 118 | {'enabled': False, 'images': [{'id': '4HhDpVKxqcLmnxFz3Pa7jEqUmnKin0qj8sxjj2Y7Tqk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/4HhDpVKxqcLmnxFz3Pa7jEqUmnKin0qj8sxjj2Y7Tqk.png?width=108&crop=smart&auto=webp&s=62a5ab4169def4e757d6f5a94343e4ecef10bb0d', 'width': 108}, {'height': 108, 'url': 'h... |
Help running Seed OSS with thinking budget | 2 | I can't seem to get seed oss to use it's thinking budget. I'm running it on llama cpp server like this:
llama-server --model Seed-OSS-36B-Instruct-UD-Q4\_K\_XL.gguf --no-mmap -fa on -c 10000 -ngl 80 --port 5899
I'm using a python client like this:
import openai
client = openai.OpenAI(
base\_url="http://localhost:5... | 2025-11-07T13:24:30 | https://www.reddit.com/r/LocalLLaMA/comments/1oqubgg/help_running_seed_oss_with_thinking_budget/ | Otherwise-Alfalfa495 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqubgg | false | null | t3_1oqubgg | /r/LocalLLaMA/comments/1oqubgg/help_running_seed_oss_with_thinking_budget/ | false | false | self | 2 | null |
Building a Multi-Turn Agentic AI Evaluation Platform – Looking for Validation | 2 | Hey everyone,
I've been noticing that building AI agents is getting easier and easier, thanks to no-code tools and "vibe coding" (the latest being LangGraph's agent builder). The goal seems to be making agent development accessible even to non-technical folks, at least for prototypes.
But evaluating multi-turn agents... | 2025-11-07T13:19:50 | https://www.reddit.com/r/LocalLLaMA/comments/1oqu7od/building_a_multiturn_agentic_ai_evaluation/ | shivmohith8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqu7od | false | null | t3_1oqu7od | /r/LocalLLaMA/comments/1oqu7od/building_a_multiturn_agentic_ai_evaluation/ | false | false | self | 2 | null |
Intel Arc Pro B50 GPU Review: An Affordable, Low-Power Workstation GPU | 22 | 2025-11-07T13:16:02 | https://www.storagereview.com/review/intel-arc-pro-b50-gpu-review-an-affordable-low-power-workstation-gpu | brand_momentum | storagereview.com | 1970-01-01T00:00:00 | 0 | {} | 1oqu4i3 | false | null | t3_1oqu4i3 | /r/LocalLLaMA/comments/1oqu4i3/intel_arc_pro_b50_gpu_review_an_affordable/ | false | false | default | 22 | {'enabled': False, 'images': [{'id': '3Egk-w2HASlmi68QUUwWJyPFPlaRWFVtyMPx2j34DHg', 'resolutions': [{'height': 74, 'url': 'https://external-preview.redd.it/3Egk-w2HASlmi68QUUwWJyPFPlaRWFVtyMPx2j34DHg.jpeg?width=108&crop=smart&auto=webp&s=ca6b5c08bec53a58aed595fb8a7a06763e32a3d8', 'width': 108}, {'height': 148, 'url': '... | |
Hardware recommendations | 1 | Hi guys, I’m planning to suggest to my company that we build a machine to run local LLMs. The goal is to be able to run something around \~70B models with decent tokens/sec, or maybe use quantized versions of larger ones. I want to export an OpenAI-compatible API using tools like llama.cpp or vLLM, and connect it to ou... | 2025-11-07T13:04:54 | https://www.reddit.com/r/LocalLLaMA/comments/1oqtv8l/hardware_recommendations/ | Pyrotheus | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqtv8l | false | null | t3_1oqtv8l | /r/LocalLLaMA/comments/1oqtv8l/hardware_recommendations/ | false | false | self | 1 | null |
Can someone explain what a Mixture-of-Experts model really is? | 209 | Hello, I've been aware of MoE since Deepseek dropped in the beginning of the year but I never really delved deep into what it is and how it helps in things like local AI inferencing. This sub's been very helpful with my local AI related questions so I wanted to learn from the people here.
Here are some more questions:... | 2025-11-07T13:02:36 | https://www.reddit.com/r/LocalLLaMA/comments/1oqttg0/can_someone_explain_what_a_mixtureofexperts_model/ | Weebviir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqttg0 | false | null | t3_1oqttg0 | /r/LocalLLaMA/comments/1oqttg0/can_someone_explain_what_a_mixtureofexperts_model/ | false | false | self | 209 | null |
Why does Elon Musk say OpenAl's open-source models are broke? (GPT OSS) | 0 | Hey, I'm really interested in what Elon Musk meant in the recent interview when he said that OpenAl's open-source models are 'broke' and non working. He is probably referring to GPT-OSS. For anyone who already deployed one of the OSS models, what is you’re experience? | 2025-11-07T12:59:05 | https://v.redd.it/rn6o7ffv1uzf1 | ZeroKelvinMood | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oqtqg1 | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/rn6o7ffv1uzf1/DASHPlaylist.mpd?a=1765112359%2CZmE4NTM4Njk4NWRhNzYyNmZhZmUxMDg1MWU5NzhiYjJiYTg5NDkzYjhmNDU4MWI3YTVjYjQ2OGE4OGViZTdmNw%3D%3D&v=1&f=sd', 'duration': 13, 'fallback_url': 'https://v.redd.it/rn6o7ffv1uzf1/CMAF_720.mp4?source=fallback', 'ha... | t3_1oqtqg1 | /r/LocalLLaMA/comments/1oqtqg1/why_does_elon_musk_say_openals_opensource_models/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'dGswZXZoYXYxdXpmMWTUkKZeTz_DNkmsKolPcUKoA9SUOA9XrDt2aNywaF5l', 'resolutions': [{'height': 167, 'url': 'https://external-preview.redd.it/dGswZXZoYXYxdXpmMWTUkKZeTz_DNkmsKolPcUKoA9SUOA9XrDt2aNywaF5l.png?width=108&crop=smart&format=pjpg&auto=webp&s=e6a0b848c0dead1d213ad146b1d919faa74f... | |
Sparse Attention MoE - a test repo for a novel swappable attention mechanism | 15 | I saw someone talking about using a MoE for Attention a few weeks back. At the time, it seemed like nonsense, but something about the post made me fiddle around with it a bit, and I was surprised to find it... worked? Crazier still... it seems to beat regular attention while radically reducing the amount of time and co... | 2025-11-07T12:56:53 | https://github.com/Deveraux-Parker/Adaptive_Sparse_Attention_MoE/tree/main | teachersecret | github.com | 1970-01-01T00:00:00 | 0 | {} | 1oqtose | false | null | t3_1oqtose | /r/LocalLLaMA/comments/1oqtose/sparse_attention_moe_a_test_repo_for_a_novel/ | false | false | default | 15 | null |
Hermes4 14b, 2 months later. Thoughts? Opinions? | 1 | I love Hermes3 8B. I was looking forward to Hermes4 for so long. But they don't seem to be releasing an 8B or 4B this time so I would barely be able to run it. On top of that, I just can't seem to get it running on my computer for some reason. Probably just something needs to be updated, idk. But I would only be able ... | 2025-11-07T12:35:38 | https://www.reddit.com/r/LocalLLaMA/comments/1oqt8fn/hermes4_14b_2_months_later_thoughts_opinions/ | Low_Poetry5287 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqt8fn | false | null | t3_1oqt8fn | /r/LocalLLaMA/comments/1oqt8fn/hermes4_14b_2_months_later_thoughts_opinions/ | false | false | self | 1 | null |
Has anyone used Generative UI tools to make complex content easier to understand? | 1 | So, I was working on this blog about Zendesk alternatives, right? Pulled a ton of info from G2 reviews and ended up with what felt like a mini e-book. Seriously, it was a wall of text and I figured… nobody’s going to read all this.
But then I stumbled on this random AI tool that just turned all that giant content into... | 2025-11-07T12:27:36 | https://www.reddit.com/r/LocalLLaMA/comments/1oqt2f5/has_anyone_used_generative_ui_tools_to_make/ | venkatweetz | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqt2f5 | false | null | t3_1oqt2f5 | /r/LocalLLaMA/comments/1oqt2f5/has_anyone_used_generative_ui_tools_to_make/ | false | false | 1 | null | |
Kimi K2 Thinking outperforms Claude Opus 4 while being ~30x cheaper | 0 | ERROR: type should be string, got "https://preview.redd.it/7e64vl7mutzf1.png?width=3568&format=png&auto=webp&s=48a5f3c5b0cf392294f2aec8a6131bcdfc572241\n\nKimi-k2-thinking achieves the highest combinatorics score on GDM’s IMO-AnswerBench (65.5% overall)\n\nhttps://preview.redd.it/e31uduq2vtzf1.png?width=4096&format=png&auto=webp&s=4f2c06070a714268a33ac6f5c750c0adfc977556\n\n" | 2025-11-07T12:23:48 | https://www.reddit.com/r/LocalLLaMA/comments/1oqszjs/kimi_k2_thinking_outperforms_claude_opus_4_while/ | InternationalAsk1490 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqszjs | false | null | t3_1oqszjs | /r/LocalLLaMA/comments/1oqszjs/kimi_k2_thinking_outperforms_claude_opus_4_while/ | false | false | 0 | null | |
How do you evaluate the quality of your knowledge base? | 9 | Typically, we measure metrics related to the retrieval pipeline — such as retriever performance, reranker accuracy, and generation quality.
However, I believe it’s equally important to have metrics that assess the quality of the underlying knowledge base itself. For example:
Are there contradictory or outdated docume... | 2025-11-07T11:54:59 | https://www.reddit.com/r/LocalLLaMA/comments/1oqsf0j/how_do_you_evaluate_the_quality_of_your_knowledge/ | CapitalShake3085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqsf0j | false | null | t3_1oqsf0j | /r/LocalLLaMA/comments/1oqsf0j/how_do_you_evaluate_the_quality_of_your_knowledge/ | false | false | self | 9 | null |
gpt-oss-20b in vscode | 1 | I'm trying to use gpt-oss-20b in Vscode.
Has anyone managed to get it working with a OpenSource/Free coding agent plugin?
I tried RooCode and [Continue.dev](http://Continue.dev), in both cases it failed in the tool calls.
| 2025-11-07T11:45:42 | https://www.reddit.com/r/LocalLLaMA/comments/1oqs8yr/gptoss20b_in_vscode/ | stable_monk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqs8yr | false | null | t3_1oqs8yr | /r/LocalLLaMA/comments/1oqs8yr/gptoss20b_in_vscode/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '7FTmwKM4TuCvaIMSlask76mRn8liFawdPuHJFSqPl9U', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/7FTmwKM4TuCvaIMSlask76mRn8liFawdPuHJFSqPl9U.png?width=108&crop=smart&auto=webp&s=efe307f51ff2874b18960bc89ca5a18a1b551442', 'width': 108}, {'height': 113, 'url': 'h... |
Hello guys im new in this community i have qestions | 0 | So I wil be geting acer nitro 16 rtx 5070 and ryzen 7 270 what model can I run , please can someone specify what can I run, wil the 5070ti wil be improvement | 2025-11-07T11:15:10 | https://www.reddit.com/r/LocalLLaMA/comments/1oqrp3z/hello_guys_im_new_in_this_community_i_have/ | Former_Location_5543 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqrp3z | false | null | t3_1oqrp3z | /r/LocalLLaMA/comments/1oqrp3z/hello_guys_im_new_in_this_community_i_have/ | false | false | self | 0 | null |
How do large companies securely integrate LLMs without exposing confidential data? | 2 | I'm exploring ways to use LLMs as autonomous agents to interact with our internal systems (ERP, chat, etc.). The major roadblock is data confidentiality.
I understand that services like Amazon Bedrock, Anthropic, and OpenAI offer robust security features and Data Processing Addendums (DPAs). However, by their nature, ... | 2025-11-07T11:12:00 | https://www.reddit.com/r/LocalLLaMA/comments/1oqrn1f/how_do_large_companies_securely_integrate_llms/ | Straight_Pin_8618 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqrn1f | false | null | t3_1oqrn1f | /r/LocalLLaMA/comments/1oqrn1f/how_do_large_companies_securely_integrate_llms/ | false | false | self | 2 | {'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... |
The real difference between Pipecat and LiveKit? | 1 | I know both Pipecat and LiveKit are open source Python frameworks used for building AI phone assistants, but I’m having a hard time understanding the real practical differences between them.
From a development and production standpoint, when should i choose pipecat vs LiveKit and is one more developed then the other? ... | 2025-11-07T11:10:27 | https://www.reddit.com/r/LocalLLaMA/comments/1oqrm0r/the_real_difference_between_pipecat_and_livekit/ | ZeroKelvinMood | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqrm0r | false | null | t3_1oqrm0r | /r/LocalLLaMA/comments/1oqrm0r/the_real_difference_between_pipecat_and_livekit/ | false | false | self | 1 | null |
Why can't a local model (Qwen 3 14b) call correctly a local agent ? | 0 | Using Qwen 3 14B as an orchestrator for a Claude 4.5 review agent. Despite clear routing logic, Qwen calls the agent without passing the code snippets. When the agent requests the code again, Qwen ignores it and starts doing the review itself, even though Claude should handle that part.
System: Ryzen 5 3600, 32 GB RAM... | 2025-11-07T10:22:53 | Toulalaho | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oqqt97 | false | null | t3_1oqqt97 | /r/LocalLLaMA/comments/1oqqt97/why_cant_a_local_model_qwen_3_14b_call_correctly/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'ovvkqres9tzf1', 'resolutions': [{'height': 104, 'url': 'https://preview.redd.it/ovvkqres9tzf1.png?width=108&crop=smart&auto=webp&s=c78fd7dc2e0df2e8935acb191d526378d2a0493d', 'width': 108}, {'height': 208, 'url': 'https://preview.redd.it/ovvkqres9tzf1.png?width=216&crop=smart&auto=we... | |
Kimi-K2 thinking self host help needed | 1 | We plan to host Kimi-K2 for our multiple clients preferably with full context length.
How can it handle around 20-40 requests at once with good context length?
We can get 6xh200s or similar specs systems.
But we want to know, What’s the cheapest way to go about it? | 2025-11-07T10:08:20 | https://www.reddit.com/r/LocalLLaMA/comments/1oqqkpu/kimik2_thinking_self_host_help_needed/ | work_urek03 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqqkpu | false | null | t3_1oqqkpu | /r/LocalLLaMA/comments/1oqqkpu/kimik2_thinking_self_host_help_needed/ | false | false | self | 1 | null |
Release: VellumK2 Fantasy Datasets — 5 Complete DPO Datasets totalling 17k response pairs | 6 | Wanted share my series of writing datasets I've created using Kimi K2 0905 and Phi 4 Mini Instruct (which I thought would be a good negative signal since it inherently has a lot of slop and was purely trained on synthetic data).
* **VellumK2-Fantasy-DPO-Tiny-01**: 126 rows - Testing and validation
* **VellumK2-Fanta... | 2025-11-07T09:24:57 | https://www.reddit.com/r/LocalLLaMA/comments/1oqpvyr/release_vellumk2_fantasy_datasets_5_complete_dpo/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqpvyr | false | null | t3_1oqpvyr | /r/LocalLLaMA/comments/1oqpvyr/release_vellumk2_fantasy_datasets_5_complete_dpo/ | false | false | 6 | null | |
Built a local AI Benchmark Tool - just something I made for my own testing | 1 | [removed] | 2025-11-07T09:23:37 | https://www.reddit.com/gallery/1oqpv6t | PKC83 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1oqpv6t | false | null | t3_1oqpv6t | /r/LocalLLaMA/comments/1oqpv6t/built_a_local_ai_benchmark_tool_just_something_i/ | false | false | 1 | null | |
Best way to handle foreign language documents | 1 | I’ve been working on a **receipt extraction pipeline** involving a lot of **Hebrew-language receipts** (right-to-left text, mixed fonts, etc.).
I’ve tested **Qwen3-VL-7B** and **Qwen3-VL-30B-A3B**, but both struggle with extracting **raw Hebrew text** directly from images — the layout is fine, but the actual text is ... | 2025-11-07T09:21:33 | https://www.reddit.com/r/LocalLLaMA/comments/1oqpu0v/best_way_to_handle_foreign_language_documents/ | Ok_Television_9000 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqpu0v | false | null | t3_1oqpu0v | /r/LocalLLaMA/comments/1oqpu0v/best_way_to_handle_foreign_language_documents/ | false | false | self | 1 | null |
Minimax will launch a coding package on November 14th | 24 | 2025-11-07T09:20:02 | https://www.reddit.com/gallery/1oqpt4w | Fun-Doctor6855 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1oqpt4w | false | null | t3_1oqpt4w | /r/LocalLLaMA/comments/1oqpt4w/minimax_will_launch_a_coding_package_on_november/ | false | false | 24 | null | ||
Idea idk | 0 | So what if you trained a trillion tokens worth of weights of large language models of different purposes, sizes, functions, and then ran all of that through a similar transformer architecture training to output a model and then have an interface that can communicate with that? | 2025-11-07T08:44:02 | https://www.reddit.com/r/LocalLLaMA/comments/1oqp8rv/idea_idk/ | mr_happy_nice | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqp8rv | false | null | t3_1oqp8rv | /r/LocalLLaMA/comments/1oqp8rv/idea_idk/ | false | false | self | 0 | null |
Kimi K2 Thinking Fast Provider Waiting Room | 0 | Please update us if you find a faster inference Provider for Kimi K2 Thinking. The Provider mustn't distill it! | 2025-11-07T08:24:28 | marvijo-software | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1oqoy4m | false | null | t3_1oqoy4m | /r/LocalLLaMA/comments/1oqoy4m/kimi_k2_thinking_fast_provider_waiting_room/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'g6uzazbwoszf1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/g6uzazbwoszf1.png?width=108&crop=smart&auto=webp&s=6039419b70a4da84942ae091a7dadb39cf718470', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/g6uzazbwoszf1.png?width=216&crop=smart&auto=we... | |
LLM Running On Multi GPU With PCIe 1x | 0 | Noob here sorry for the amateur question, currently I have RTX 4070 as my GPU, I plan on getting new GPU to run LLM but my motherboard only has 1x PCie 3.0 slot left. Can I run single large model on a setup like that ? | 2025-11-07T08:08:54 | https://www.reddit.com/r/LocalLLaMA/comments/1oqopjv/llm_running_on_multi_gpu_with_pcie_1x/ | Emergency_exit_now | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1oqopjv | false | null | t3_1oqopjv | /r/LocalLLaMA/comments/1oqopjv/llm_running_on_multi_gpu_with_pcie_1x/ | false | false | self | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.