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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Before I buy a used RTX 3090… | 1 | So I had fun for a couple of weeks with my old 1080 just to test local llm and it was fun.
Now I have an opportunity to buy a rtx 3090 but I’m like, do I really need this?
For every day general models, I will never be as good as chatgpt.
So I feel that local llm shines for precise tasks with smaller models.
For exa... | 2026-02-12T12:50:36 | https://www.reddit.com/r/LocalLLaMA/comments/1r2skzl/before_i_buy_a_used_rtx_3090/ | Dentifrice | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2skzl | false | null | t3_1r2skzl | /r/LocalLLaMA/comments/1r2skzl/before_i_buy_a_used_rtx_3090/ | false | false | self | 1 | null |
Agent parser ? | 1 | For learning sake built a standard LLM prompt and parser pair to try and get some very small models to be able to do agential tasks - still seems to require those at 20B and up but gpt oss 20b and others get by. in doing so occurred to me that having a standard open markup language sort of exchange format would help m... | 2026-02-12T12:49:11 | https://www.reddit.com/r/LocalLLaMA/comments/1r2sjxa/agent_parser/ | 2BucChuck | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2sjxa | false | null | t3_1r2sjxa | /r/LocalLLaMA/comments/1r2sjxa/agent_parser/ | false | false | self | 1 | null |
Address boundary error when running with RPC | 1 | 2026-02-12T12:16:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r2rw1o/address_boundary_error_when_running_with_rpc/ | Amanthau | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2rw1o | false | null | t3_1r2rw1o | /r/LocalLLaMA/comments/1r2rw1o/address_boundary_error_when_running_with_rpc/ | false | false | 1 | null | ||
New Ovis2.6-30B-A3B, a lil better than Qwen3-VL-30B-A3B | 77 | Ovis2.6-30B-A3B, the latest advancement in the Ovis series of Multimodal Large Language Models (MLLMs). Building on the strong foundation of Ovis2.5, Ovis2.6 upgrades the LLM backbone to a Mixture-of-Experts (MoE) architecture, delivering superior multimodal performance at a fraction of the serving cost. It also brings... | 2026-02-12T12:08:29 | https://huggingface.co/AIDC-AI/Ovis2.6-30B-A3B | edward-dev | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1r2rqmg | false | null | t3_1r2rqmg | /r/LocalLLaMA/comments/1r2rqmg/new_ovis2630ba3b_a_lil_better_than_qwen3vl30ba3b/ | false | false | 77 | {'enabled': False, 'images': [{'id': 'vk5y-X5rKzjDV5x114-FEAIUKduZcw4xVjgoneWCF5o', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/vk5y-X5rKzjDV5x114-FEAIUKduZcw4xVjgoneWCF5o.png?width=108&crop=smart&auto=webp&s=92196594d9e6d5d87dc4e1906680fd18ff77e748', 'width': 108}, {'height': 116, 'url': 'h... | |
[ Removed by moderator ] | 1 | 2026-02-12T12:04:03 | https://instatunnel.my/blog/model-weight-mirror-squatting-the-backdoored-hub | JadeLuxe | instatunnel.my | 1970-01-01T00:00:00 | 0 | {} | 1r2rngg | false | null | t3_1r2rngg | /r/LocalLLaMA/comments/1r2rngg/model_weight_mirror_squattingbackdoored_ai_models/ | false | false | null | 1 | null | |
Have two 12GB RTX 3060s — planning a self-hosted community AI server. What models + Linux/Docker stack should I run? | 1 | Hi all,
I have access to a small dedicated box with 2× RTX 3060 (12GB VRAM each) and I’m planning to set up a self-hosted community AI server for a local digital-arts / creative tech community.
The goal is to run a mix of:
• Stable Diffusion image generation
• Possibly video generation / upscaling
• Some loc... | 2026-02-12T11:39:15 | https://www.reddit.com/r/LocalLLaMA/comments/1r2r6ua/have_two_12gb_rtx_3060s_planning_a_selfhosted/ | v3d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2r6ua | false | null | t3_1r2r6ua | /r/LocalLLaMA/comments/1r2r6ua/have_two_12gb_rtx_3060s_planning_a_selfhosted/ | false | false | self | 1 | null |
I built a genetic algorithm in Rust to evolve LLM agent teams | 2 | I’ve been working on a project called EMAS. Instead of just asking one model for an answer, this system spins up "teams" of agents, each with a different reasoning strategy.
It runs an evolutionary loop where the best-performing teams are selected, crossed over, and mutated to find the best possible response. I chose ... | 2026-02-12T11:37:36 | https://v.redd.it/9yen00xyu1jg1 | supergari | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2r5s5 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/9yen00xyu1jg1/DASHPlaylist.mpd?a=1773488277%2CZTk3YzQyZmIyYTE3NDI5YjMxNjAyNGIzYzUzYTA2NjQ0ZmVkZTg1ZmRhZjYyZWM1NmE3YzQwNWJiMTRiODg3Mg%3D%3D&v=1&f=sd', 'duration': 66, 'fallback_url': 'https://v.redd.it/9yen00xyu1jg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1r2r5s5 | /r/LocalLLaMA/comments/1r2r5s5/i_built_a_genetic_algorithm_in_rust_to_evolve_llm/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'bWh4dnMyeHl1MWpnMauTN82Iz6K24qauIQWJ5vG2fUZuQkPuuFVQhtVbFwem', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bWh4dnMyeHl1MWpnMauTN82Iz6K24qauIQWJ5vG2fUZuQkPuuFVQhtVbFwem.png?width=108&crop=smart&format=pjpg&auto=webp&s=c51e508246d4128f250e35846f203a3f5745d... | |
A beginner's devlog for the finetuning pipeline | 4 | [Months of (Failed) RL Experiments: A Beginner's Post-Mortem](https://longformthoughts.substack.com/p/months-of-failed-rl-experiments)
Tried to compile all my learnings from 6 months of failed RL Finetuning Experiments.
Contains all the advice I'd give to anyone starting out to try SFT/RLFT in LLMs. It's a long b... | 2026-02-12T11:35:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r2r45l/a_beginners_devlog_for_the_finetuning_pipeline/ | Extreme-Question-430 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2r45l | false | null | t3_1r2r45l | /r/LocalLLaMA/comments/1r2r45l/a_beginners_devlog_for_the_finetuning_pipeline/ | false | false | self | 4 | null |
Are we ever going to get a GLM-5-level model running on a “potato” PC? What’s your take on this? | 14 | Hey guys, as you may already know, the weights for GLM-5 have been released, and it’s pretty awesome, it can compete with closed source models.The problem is the same as always, though... It requires a pretty powerful and expensive PC to run lol. As the technology advances, do you think we’ll eventually get a model wi... | 2026-02-12T11:31:48 | https://www.reddit.com/r/LocalLLaMA/comments/1r2r20z/are_we_ever_going_to_get_a_glm5level_model/ | junior600 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2r20z | false | null | t3_1r2r20z | /r/LocalLLaMA/comments/1r2r20z/are_we_ever_going_to_get_a_glm5level_model/ | false | false | self | 14 | null |
how does Strix Halo fares for training models compared to other homelabs means to cook those? | 4 | yes we all know that Strix Halo is nice and dandy for running inference on medium-large size models at a reasonable reading speed but is it good enough also to cook small- medium-large size models at an accettable pace? | 2026-02-12T11:03:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r2qkev/how_does_strix_halo_fares_for_training_models/ | DevelopmentBorn3978 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2qkev | false | null | t3_1r2qkev | /r/LocalLLaMA/comments/1r2qkev/how_does_strix_halo_fares_for_training_models/ | false | false | self | 4 | null |
llama-swap (llama-server) GPU and CPU | 2 | I've been using Ollama, with Open Webui because of the easy setup. Recently I learned other inference engines should perform better. I wanted some ease in changing models, so I picked llama-swap, with llama-server under the hood.
While this works good, something puzzles me. With Ollama i'm used to run the 'ollama p... | 2026-02-12T11:02:13 | https://www.reddit.com/r/LocalLLaMA/comments/1r2qjrh/llamaswap_llamaserver_gpu_and_cpu/ | MrLetsTryDevOps | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2qjrh | false | null | t3_1r2qjrh | /r/LocalLLaMA/comments/1r2qjrh/llamaswap_llamaserver_gpu_and_cpu/ | false | false | self | 2 | null |
Jan supports Claude Code integration | 1 | 2026-02-12T10:34:59 | https://x.com/jandotai/status/2021856755815526737 | luiyen | x.com | 1970-01-01T00:00:00 | 0 | {} | 1r2q3au | false | null | t3_1r2q3au | /r/LocalLLaMA/comments/1r2q3au/jan_supports_claude_code_integration/ | false | false | default | 1 | null | |
Is GLM 5.0 web still unlimited ? | 0 | For the free plan I mean.
So, coding-wise, which AIs is it on par with? I'm a novice, and I find there are way too many benchmarks; I just want to know concretely where it stands | 2026-02-12T10:23:59 | https://www.reddit.com/r/LocalLLaMA/comments/1r2pwoz/is_glm_50_web_still_unlimited/ | Sostrene_Blue | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2pwoz | false | null | t3_1r2pwoz | /r/LocalLLaMA/comments/1r2pwoz/is_glm_50_web_still_unlimited/ | false | false | self | 0 | null |
Using GLM-5 for everything | 56 | Does it make economic sense to build a beefy headless home server to replace evrything with GLM-5, including Claude for my personal coding, and multimodel chat for me and my family members? I mean assuming a yearly AI budget of 3k$, for a 5-year period, is there a way to spend the same $15k to get 80% of the benefits v... | 2026-02-12T10:18:26 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ptd5/using_glm5_for_everything/ | keepmyeyesontheprice | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ptd5 | false | null | t3_1r2ptd5 | /r/LocalLLaMA/comments/1r2ptd5/using_glm5_for_everything/ | false | false | self | 56 | null |
ChatLLM.cpp adds support of Qwen3-TTS models | 17 | https://reddit.com/link/1r2pmpx/video/0p9d7iz2e1jg1/player
Note:
1. voice cloning not available yet.
2. precision of \`code\_predicator\` needs to be improved to match PyTorch reference implementation.
3. there are issues (keeping generating, some words are missing, etc) with the models themselves. VoiceDesign mode... | 2026-02-12T10:07:32 | https://www.reddit.com/r/LocalLLaMA/comments/1r2pmpx/chatllmcpp_adds_support_of_qwen3tts_models/ | foldl-li | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2pmpx | false | null | t3_1r2pmpx | /r/LocalLLaMA/comments/1r2pmpx/chatllmcpp_adds_support_of_qwen3tts_models/ | false | false | self | 17 | null |
AI API | 1 | [removed] | 2026-02-12T10:04:47 | https://www.reddit.com/r/LocalLLaMA/comments/1r2pl1o/ai_api/ | Practical_Sugar_1834 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2pl1o | false | null | t3_1r2pl1o | /r/LocalLLaMA/comments/1r2pl1o/ai_api/ | false | false | self | 1 | null |
GLM 5 Uncensored? | 0 | Hi, I have been looking for GLM 5 Uncensored - zero guiderails.
I looked at huggingface and Ollama models page. The Highest so far is GLM 4.6 that I could find.
Am I too early to expect GLM 5 uncensored? Thank you for guiding me. | 2026-02-12T10:03:24 | https://www.reddit.com/r/LocalLLaMA/comments/1r2pk88/glm_5_uncensored/ | firiana_Control | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2pk88 | false | null | t3_1r2pk88 | /r/LocalLLaMA/comments/1r2pk88/glm_5_uncensored/ | false | false | self | 0 | null |
SuperLocalMemory: Universal memory layer for ANY AI tool (100% local, MCP + Skills) | 1 | [removed] | 2026-02-12T09:49:37 | https://www.reddit.com/gallery/1r2pc8m | Southern-Flow-2072 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1r2pc8m | false | null | t3_1r2pc8m | /r/LocalLLaMA/comments/1r2pc8m/superlocalmemory_universal_memory_layer_for_any/ | false | false | 1 | null | |
Heavy GPU usage | 1 | i need someone who is in really need for high end GPUs ( B200 , H100, H200) , someone wanting once off heavy runs for fine tuning or data processing. there are some disposable resources that i can make use of | 2026-02-12T09:48:28 | https://www.reddit.com/r/LocalLLaMA/comments/1r2pbnf/heavy_gpu_usage/ | TelevisionHot468 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2pbnf | false | null | t3_1r2pbnf | /r/LocalLLaMA/comments/1r2pbnf/heavy_gpu_usage/ | false | false | self | 1 | null |
Beyond OpenAI: Building a Protocol for Multi-Model Agent Commerce (The Nexus Thesis) | 0 | Emphasize that Nexus is **Substrate Agnostic**. It’s for people who want to run Llama locally but still hire a Claude agent for specialized tasks. | 2026-02-12T09:37:43 | https://www.reddit.com/r/LocalLLaMA/comments/1r2p5pr/beyond_openai_building_a_protocol_for_multimodel/ | OkPerception3998 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2p5pr | false | null | t3_1r2p5pr | /r/LocalLLaMA/comments/1r2p5pr/beyond_openai_building_a_protocol_for_multimodel/ | false | false | self | 0 | null |
Are we overusing context windows instead of improving retrieval quality? | 0 | Something I’ve been thinking about while tuning a few local + API-based setups.
As context windows get larger, it feels like we’ve started treating them as storage rather than attention budgets.
But under the hood, it’s still:
text → tokens → token embeddings → attention over vectors
Every additional token becomes ... | 2026-02-12T09:33:16 | https://www.reddit.com/r/LocalLLaMA/comments/1r2p398/are_we_overusing_context_windows_instead_of/ | ComfortableFeeling85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2p398 | false | null | t3_1r2p398 | /r/LocalLLaMA/comments/1r2p398/are_we_overusing_context_windows_instead_of/ | false | false | self | 0 | null |
REAP vs Very Low Quantization | 13 | Has anybody played around comparing the performance of different strategies for the RAM poor? For instance, given a big model, what performs better: a REAP versión q4, or a q2 version?
Or q2 + REAP?
I know it is very different from model to model, and version to version (depending on the technique and so on for quant... | 2026-02-12T09:24:32 | https://www.reddit.com/r/LocalLLaMA/comments/1r2oyla/reap_vs_very_low_quantization/ | mouseofcatofschrodi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2oyla | false | null | t3_1r2oyla | /r/LocalLLaMA/comments/1r2oyla/reap_vs_very_low_quantization/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'dBcOJXWudLyTVcABpzExdWUuWIm1TJwZv-cq3Wuv3Xs', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/dBcOJXWudLyTVcABpzExdWUuWIm1TJwZv-cq3Wuv3Xs.png?width=108&crop=smart&auto=webp&s=53c8b3920a0839fca1df1fa8c0d92318373a5d6a', 'width': 108}, {'height': 116, 'url': 'h... |
Realtime Linux desktop voice assistant using 11GB VRAM | 20 | This is using LocalAI's realtime API (OpenAI compatible) with a model pipeline to simulate an any-to-any model. This is without streaming yet, we still need to implement that and a bunch of other stuff in LocalAI. | 2026-02-12T09:04:56 | https://v.redd.it/ryba3s3f31jg1 | richiejp | /r/LocalLLaMA/comments/1r2onsi/realtime_linux_desktop_voice_assistant_using_11gb/ | 1970-01-01T00:00:00 | 0 | {} | 1r2onsi | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/ryba3s3f31jg1/DASHPlaylist.mpd?a=1773608707%2CZWM2YzE3ZmM3OWY4ZTQ4ZjczMjgxOWQ5ZWVmYTMwM2ZkNGM4NmQzNzI5YTc3M2M1MjZlMTQwZjcyMmIzMzM0OA%3D%3D&v=1&f=sd', 'duration': 832, 'fallback_url': 'https://v.redd.it/ryba3s3f31jg1/CMAF_1080.mp4?source=fallback', '... | t3_1r2onsi | /r/LocalLLaMA/comments/1r2onsi/realtime_linux_desktop_voice_assistant_using_11gb/ | false | false | 20 | {'enabled': False, 'images': [{'id': 'OHNzdGkzNGYzMWpnMUm_Q0RBkiFb42R5DHAeCLnRYPzHrnkd9Hw6LavECjzI', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/OHNzdGkzNGYzMWpnMUm_Q0RBkiFb42R5DHAeCLnRYPzHrnkd9Hw6LavECjzI.png?width=108&crop=smart&format=pjpg&auto=webp&s=f17393601a0f3b38e673545d9236924488ead... | |
Unlimited AI API Usage | 0 | Hey folks , hope everybody is trying to build something with AI. EndpointAI , it offers AI API at fixed subscription cost for unlimited usage , one unified API for all models. Start using it now : https://endpointai.in. So i have been using it to build apps , built many AI consumer saas apps , and many more . costs hav... | 2026-02-12T08:59:38 | https://www.reddit.com/r/LocalLLaMA/comments/1r2okku/unlimited_ai_api_usage/ | Practical_Sugar_1834 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2okku | false | null | t3_1r2okku | /r/LocalLLaMA/comments/1r2okku/unlimited_ai_api_usage/ | false | false | self | 0 | null |
LMstudio macOS 26.3 error on models | 0 | I just downloaded macOS 26.3 for my Mac mini m4 i now find none of my models load and I get a python error I deleted my local models and redownloaded in case of corruption but same error no model will load | 2026-02-12T08:51:50 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ogc6/lmstudio_macos_263_error_on_models/ | carwash2016 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ogc6 | false | null | t3_1r2ogc6 | /r/LocalLLaMA/comments/1r2ogc6/lmstudio_macos_263_error_on_models/ | false | false | self | 0 | null |
I Am Developing A Sentient AI | 0 | For the past couple of months I have been researching how to make this possible. I'm making this post to document my discoveries and to highlight what goes into making this a reality.
I want to start this off by saying I am not expert in any of these fields, and all of my findings are from hours of research and experi... | 2026-02-12T08:21:55 | https://www.reddit.com/r/LocalLLaMA/comments/1r2nznr/i_am_developing_a_sentient_ai/ | SadistMind | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2nznr | false | null | t3_1r2nznr | /r/LocalLLaMA/comments/1r2nznr/i_am_developing_a_sentient_ai/ | false | false | 0 | null | |
Looking for a good VL | 1 | I am looking for a good VL. Mainly for creating prompts for video generation. I shold be able to give first and last frame and it should look at image and give me good detailed prompts.
I tried qwen3 8b but it sucks at giving me good detailed prompt, instead it just descirbes the image as it is. So is there any good m... | 2026-02-12T08:15:47 | https://www.reddit.com/r/LocalLLaMA/comments/1r2nw52/looking_for_a_good_vl/ | ClarieObscur | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2nw52 | false | null | t3_1r2nw52 | /r/LocalLLaMA/comments/1r2nw52/looking_for_a_good_vl/ | false | false | self | 1 | null |
Deploy OpenClaw with built-in LLM or BYOK for $0.01/hr | 0 | https://reddit.com/link/1r2ntrv/video/r7bv4xqzu0jg1/player
Built a platform that handles the full OpenClaw deployment - Docker, networking, LLM config - in about 60 seconds.
**Two LLM options:**
* Use the built-in LLM (no API keys needed)
* Bring your own key if you prefer your own provider
**What you get:**
* You... | 2026-02-12T08:11:44 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ntrv/deploy_openclaw_with_builtin_llm_or_byok_for_001hr/ | thebikal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ntrv | false | null | t3_1r2ntrv | /r/LocalLLaMA/comments/1r2ntrv/deploy_openclaw_with_builtin_llm_or_byok_for_001hr/ | false | false | self | 0 | null |
Run your own OpenClaw AI agent 24/7 for $0.01/hour in 60 sec | 1 | [removed] | 2026-02-12T08:07:52 | https://www.reddit.com/r/LocalLLaMA/comments/1r2nrl5/run_your_own_openclaw_ai_agent_247_for_001hour_in/ | thebikal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2nrl5 | false | null | t3_1r2nrl5 | /r/LocalLLaMA/comments/1r2nrl5/run_your_own_openclaw_ai_agent_247_for_001hour_in/ | false | false | self | 1 | null |
Best LLM for coding in C#? | 1 | Looking for the best model that has good coding capabilities in C#.
Model has to be less than 60B parameters (preferably MOE)
Would do Qwen3 Coder Next but it doesnt seem to be trained on C# that well as all the swe benchmarks dont include C# for some reason | 2026-02-12T07:49:02 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ngjd/best_llm_for_coding_in_c/ | Odd-Ordinary-5922 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ngjd | false | null | t3_1r2ngjd | /r/LocalLLaMA/comments/1r2ngjd/best_llm_for_coding_in_c/ | false | false | self | 1 | null |
Open Source Kreuzberg benchmarks and new release | 8 | Hi all,
I have two announcements related to Kreuzberg.
We released our new comparative benchmarks. These have a slick UI and we have been working hard on them for a while now (more on this below), and we'd love to hear your impressions and get some feedback from the community!
We released v4.3.0, which brings in a b... | 2026-02-12T07:43:35 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ndep/open_source_kreuzberg_benchmarks_and_new_release/ | Eastern-Surround7763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ndep | false | null | t3_1r2ndep | /r/LocalLLaMA/comments/1r2ndep/open_source_kreuzberg_benchmarks_and_new_release/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'dlA25NAcyPL4lIdscfsCv_8AcSxeJAF0JDfclk7Ngmo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dlA25NAcyPL4lIdscfsCv_8AcSxeJAF0JDfclk7Ngmo.png?width=108&crop=smart&auto=webp&s=b2d562448da7d5b0f6faf9827cbef61f72fea2bf', 'width': 108}, {'height': 108, 'url': 'h... |
Taming the 3B: Engineering Expert Reason via LoRA Alignment | 1 | # How we engineered high-density reasoning into a compact 3B footprint by leveraging V4 LoRA alignment to match the performance of much larger architectures
# [https://yotamabramson.substack.com/p/taming-the-3b-engineering-expert](https://yotamabramson.substack.com/p/taming-the-3b-engineering-expert) | 2026-02-12T07:38:47 | https://www.reddit.com/r/LocalLLaMA/comments/1r2nas7/taming_the_3b_engineering_expert_reason_via_lora/ | Ok-Scene-9037 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2nas7 | false | null | t3_1r2nas7 | /r/LocalLLaMA/comments/1r2nas7/taming_the_3b_engineering_expert_reason_via_lora/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'PBrXwcM7E4yTs2yPr4My-kKmat4HPquvhgz33yYO29Y', 'resolutions': [{'height': 103, 'url': 'https://external-preview.redd.it/PBrXwcM7E4yTs2yPr4My-kKmat4HPquvhgz33yYO29Y.jpeg?width=108&crop=smart&auto=webp&s=387376cc64522769f86a09df4bffc73acfa6e3af', 'width': 108}, {'height': 206, 'url': ... |
(Open Source) Kreuzberg v4.3.0 and benchmarks | 1 | [removed] | 2026-02-12T07:24:25 | https://www.reddit.com/r/LocalLLaMA/comments/1r2n2px/open_source_kreuzberg_v430_and_benchmarks/ | Eastern-Surround7763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2n2px | false | null | t3_1r2n2px | /r/LocalLLaMA/comments/1r2n2px/open_source_kreuzberg_v430_and_benchmarks/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'dlA25NAcyPL4lIdscfsCv_8AcSxeJAF0JDfclk7Ngmo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dlA25NAcyPL4lIdscfsCv_8AcSxeJAF0JDfclk7Ngmo.png?width=108&crop=smart&auto=webp&s=b2d562448da7d5b0f6faf9827cbef61f72fea2bf', 'width': 108}, {'height': 108, 'url': 'h... |
I tried to get GLM and Kimi to recognize my unique phenotype | 1 | I'm very sorry if yall find it not interesting, but I thought its a unique and very complex scenario for LLMs to speculate through.
So, I have a **ADRB1 A187V** mutation phenotype or **de novo** mutation in ADRB1, its a short sleeper mutation, associated with 5h sleep and constant elevation of adrenaline/cortisol... | 2026-02-12T07:19:02 | https://www.reddit.com/r/LocalLLaMA/comments/1r2mzmg/i_tried_to_get_glm_and_kimi_to_recognize_my/ | peculiarMouse | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2mzmg | false | null | t3_1r2mzmg | /r/LocalLLaMA/comments/1r2mzmg/i_tried_to_get_glm_and_kimi_to_recognize_my/ | false | false | self | 1 | null |
Which AI is the best :) | 0 | I've built an ironic LLM leaderboard based on live real-world usage:
[https://whichaiisthebest.com/](https://whichaiisthebest.com/)
Curious what you think :) | 2026-02-12T07:14:54 | https://www.reddit.com/r/LocalLLaMA/comments/1r2mx6f/which_ai_is_the_best/ | trooperer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2mx6f | false | null | t3_1r2mx6f | /r/LocalLLaMA/comments/1r2mx6f/which_ai_is_the_best/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '68vOBN4SHeAgt4k7ELiem-JvbdrJiXNFBWna7U6aoIM', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/68vOBN4SHeAgt4k7ELiem-JvbdrJiXNFBWna7U6aoIM.png?width=108&crop=smart&auto=webp&s=8f7cb32f789c2914b32e897370ff8584cb4b52ce', 'width': 108}, {'height': 121, 'url': 'h... |
Building a Blog Summarizer SaaS: Is "Gemini 2.0 Flash (Basic)" vs. "GPT-4o mini (Pro)" a valid tier strategy? | 0 | Hi everyone,
I’m developing a SaaS tool that summarizes blog posts and I'm finalizing my model selection and pricing tiers.
**The Current Plan:** Instead of using expensive flagship models (like GPT-4o or Claude 3.5 Sonnet), I'm considering using two cost-effective models to keep subscription prices low.
* **Basic P... | 2026-02-12T07:12:59 | https://www.reddit.com/r/LocalLLaMA/comments/1r2mw19/building_a_blog_summarizer_saas_is_gemini_20/ | Exact_Airport_2943 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2mw19 | false | null | t3_1r2mw19 | /r/LocalLLaMA/comments/1r2mw19/building_a_blog_summarizer_saas_is_gemini_20/ | false | false | self | 0 | null |
Lobotomy-less REAP by Samsung (REAM) | 115 | Samsung recently have pushed an alternative way to shrink a model instead of the usual REAP done by Cerebras with Kimi-Linear / DeepSeek v3.2 / GLM 4.X / MiniMax M2\* / Qwen3\* ... But Samsung might be cooking something else that are less damaging with REAM. [https://bknyaz.github.io/blog/2026/moe/](https://bknyaz.gith... | 2026-02-12T07:00:39 | https://www.reddit.com/r/LocalLLaMA/comments/1r2moge/lobotomyless_reap_by_samsung_ream/ | TomLucidor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2moge | false | null | t3_1r2moge | /r/LocalLLaMA/comments/1r2moge/lobotomyless_reap_by_samsung_ream/ | false | false | self | 115 | null |
Minimax M2.5 weights to drop soon | 82 | At least there’s official confirmation now. | 2026-02-12T06:54:49 | No_Conversation9561 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2mkz7 | true | null | t3_1r2mkz7 | /r/LocalLLaMA/comments/1r2mkz7/minimax_m25_weights_to_drop_soon/ | false | false | 82 | {'enabled': True, 'images': [{'id': 's5imsyjbh0jg1', 'resolutions': [{'height': 143, 'url': 'https://preview.redd.it/s5imsyjbh0jg1.jpeg?width=108&crop=smart&auto=webp&s=35905555959a2d5bd97eee56407a0f38bf2a33b6', 'width': 108}, {'height': 286, 'url': 'https://preview.redd.it/s5imsyjbh0jg1.jpeg?width=216&crop=smart&auto=... | ||
Minimax M2.5 weights to drop soon | 3 | At least there is official confirmation now. | 2026-02-12T06:44:49 | No_Conversation9561 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2mf64 | false | null | t3_1r2mf64 | /r/LocalLLaMA/comments/1r2mf64/minimax_m25_weights_to_drop_soon/ | false | false | 3 | {'enabled': True, 'images': [{'id': 'og2zhx8jf0jg1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/og2zhx8jf0jg1.jpeg?width=108&crop=smart&auto=webp&s=6a7db2cf27ad31cbd49a859880cb7b2d71faf28f', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/og2zhx8jf0jg1.jpeg?width=216&crop=smart&auto=... | ||
Thank you Chinese devs for providing for the community if it not for them we'll be still stuck 2020 | 72 | 2026-02-12T06:39:29 | dead-supernova | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2mbyp | false | null | t3_1r2mbyp | /r/LocalLLaMA/comments/1r2mbyp/thank_you_chinese_devs_for_providing_for_the/ | false | false | 72 | {'enabled': True, 'images': [{'id': 'o674ww1le0jg1', 'resolutions': [{'height': 125, 'url': 'https://preview.redd.it/o674ww1le0jg1.jpeg?width=108&crop=smart&auto=webp&s=15eb1196db8972c514ea3cd1ab5c7fb00ab29f4a', 'width': 108}, {'height': 251, 'url': 'https://preview.redd.it/o674ww1le0jg1.jpeg?width=216&crop=smart&auto=... | |||
Built an open-source "passport system" for AI agent credentials — looking for feedback | 0 | The idea is pretty simple — treat agent credentials like passports. Each credential gets a structured record with scope, expiry, delegation chain (which agent passed it to which other agent), and an audit trail. The metaphor sounds goofy but it maps surprisingly well once you start thinking about agent-to-agent delegat... | 2026-02-12T06:30:12 | https://www.reddit.com/r/LocalLLaMA/comments/1r2m6a6/built_an_opensource_passport_system_for_ai_agent/ | WisperaAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2m6a6 | false | null | t3_1r2m6a6 | /r/LocalLLaMA/comments/1r2m6a6/built_an_opensource_passport_system_for_ai_agent/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'TONl4plflxkqLazaI9Nc7Zu6DUTaLZN0TtAzfYzrbB0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/TONl4plflxkqLazaI9Nc7Zu6DUTaLZN0TtAzfYzrbB0.png?width=108&crop=smart&auto=webp&s=02af7a7097e1a66c61111ed0c1bcce1282b51da3', 'width': 108}, {'height': 108, 'url': 'h... |
Cache-aware prefill–decode disaggregation = 40% faster long-context LLM serving | 14 | cache aware prefill-decode disagg for 40% faster long-context LLM serving
even with vanilla PD disagg, long cold prompts block fast warm ones.
here they split the cold new long prompt prefill workloads from the warm prefills
Result:
\> \~40% higher QPS
\> lower, stabler TTFT
\> seconds → ms via KV ... | 2026-02-12T06:28:55 | https://www.together.ai/blog/cache-aware-disaggregated-inference | incarnadine72 | together.ai | 1970-01-01T00:00:00 | 0 | {} | 1r2m5h7 | false | null | t3_1r2m5h7 | /r/LocalLLaMA/comments/1r2m5h7/cacheaware_prefilldecode_disaggregation_40_faster/ | false | false | 14 | {'enabled': False, 'images': [{'id': 'PKk_NvWRXvFuthpbeOs0HJkwBf0UukzKoh0mGSJu7ig', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/PKk_NvWRXvFuthpbeOs0HJkwBf0UukzKoh0mGSJu7ig.png?width=108&crop=smart&auto=webp&s=aa742445b615e176d51598886255a977c03be29f', 'width': 108}, {'height': 113, 'url': 'h... | |
Running Mistral-7B on Intel NPU — 12.6 tokens/s, zero CPU/GPU usage | 39 | Got tired of my Intel NPU sitting there doing nothing, so I made a simple tool to run LLMs on it.
**Benchmarks (Core Ultra, Mistral-7B-int4):**
|Device|Decode Speed|TTFT|Memory|
|:-|:-|:-|:-|
|NPU|12.63 t/s|1.8s|4.8 GB|
|CPU|9.04 t/s|1.1s|7.3 GB|
|iGPU|23.38 t/s|0.25s|4.1 GB|
Yes, iGPU is faster. But the point of NP... | 2026-02-12T05:50:52 | https://www.reddit.com/r/LocalLLaMA/comments/1r2lheu/running_mistral7b_on_intel_npu_126_tokenss_zero/ | Human-Reindeer-9466 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2lheu | false | null | t3_1r2lheu | /r/LocalLLaMA/comments/1r2lheu/running_mistral7b_on_intel_npu_126_tokenss_zero/ | false | false | self | 39 | {'enabled': False, 'images': [{'id': '-46k7Rs_xNX-_sp4yM2d44lKGHmA8R9_QfFJPJhf1Yo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/-46k7Rs_xNX-_sp4yM2d44lKGHmA8R9_QfFJPJhf1Yo.png?width=108&crop=smart&auto=webp&s=513a8934b94246f3c9b267336bc00f6add98b649', 'width': 108}, {'height': 108, 'url': 'h... |
Issues with document visibility in a collection in Open WebUI | 1 | Hello! I'm using Open WebUI. I upload .txt files to the collection, and for a while, LLM models see these files and correctly respond to questions about the information in them.
But after some time (it always varies – 30 minutes, 2 hours, 1 day), LLMs stop seeing these files, and when I ask about the informati... | 2026-02-12T05:41:13 | https://www.reddit.com/r/LocalLLaMA/comments/1r2lazz/issues_with_document_visibility_in_a_collection/ | EnvironmentalCat4713 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2lazz | false | null | t3_1r2lazz | /r/LocalLLaMA/comments/1r2lazz/issues_with_document_visibility_in_a_collection/ | false | false | self | 1 | null |
Are there any locally-run solutions that can do this? Paid Version of ChatGPT has been doing pretty well at it so far. | 1 | Here's my prompt (open to critique of course):
>Look at the attached pdf and generate multiple choice questions from the attached pdf according to the per-section requirements below. For each question there should be one correct answer and two plausible distractors, distractors that are within the context of the subje... | 2026-02-12T05:37:28 | https://www.reddit.com/r/LocalLLaMA/comments/1r2l8g4/are_there_any_locallyrun_solutions_that_can_do/ | MildMockery | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2l8g4 | false | null | t3_1r2l8g4 | /r/LocalLLaMA/comments/1r2l8g4/are_there_any_locallyrun_solutions_that_can_do/ | false | false | self | 1 | null |
Проблемы с видимостью документов в collection в Open WebUI | 0 | Добрый день! Пользуюсь Open WebUI. Загружаю файлы .txt в коллекцию, какое-то время модели LLM видят эти файлы и корректно отвечают на вопросы по информации из этих файлов. Но через некоторое время (всегда по-разному - 30 минут, 2 часа, 1 день) LLM перестают видеть эти файлы и на мои вопросы по информации, содержащейся ... | 2026-02-12T05:36:01 | https://www.reddit.com/r/LocalLLaMA/comments/1r2l7jx/проблемы_с_видимостью_документов_в_collection_в/ | EnvironmentalCat4713 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2l7jx | false | null | t3_1r2l7jx | /r/LocalLLaMA/comments/1r2l7jx/проблемы_с_видимостью_документов_в_collection_в/ | false | false | self | 0 | null |
Проблемы с видимостью документов в collection в Open WebUI | 0 | Добрый день! Пользуюсь Open WebUI. Загружаю файлы .txt в коллекцию, какое-то время модели LLM видят эти файлы и корректно отвечают на вопросы по информации из этих файлов. Но через некоторое время (всегда по-разному - 30 минут, 2 часа, 1 день) LLM перестают видеть эти файлы и на мои вопросы по информации, содержащейся ... | 2026-02-12T05:35:15 | https://www.reddit.com/r/LocalLLaMA/comments/1r2l72e/проблемы_с_видимостью_документов_в_collection_в/ | EnvironmentalCat4713 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2l72e | false | null | t3_1r2l72e | /r/LocalLLaMA/comments/1r2l72e/проблемы_с_видимостью_документов_в_collection_в/ | false | false | self | 0 | null |
Kimi for only $0.99 a month | 0 | [https://www.kimi.com/membership/pricing?from=b5\_2025\_bargain&track\_id=11ecab2d-211d-4d46-bc6e-5a8500532313&discount\_id=19c503ed-fab2-87ec-8000-00008878965d](https://www.kimi.com/membership/pricing?from=b5_2025_bargain&track_id=11ecab2d-211d-4d46-bc6e-5a8500532313&discount_id=19c503ed-fab2-87ec-8000-00008878965d)
... | 2026-02-12T05:13:19 | https://www.reddit.com/r/LocalLLaMA/comments/1r2kshq/kimi_for_only_099_a_month/ | Weekly_Series_1102 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2kshq | false | null | t3_1r2kshq | /r/LocalLLaMA/comments/1r2kshq/kimi_for_only_099_a_month/ | false | false | self | 0 | null |
Tried building my own Neuro-sama | 1 | [removed] | 2026-02-12T05:07:12 | https://www.reddit.com/r/LocalLLaMA/comments/1r2koar/tried_building_my_own_neurosama/ | 042kami | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2koar | false | null | t3_1r2koar | /r/LocalLLaMA/comments/1r2koar/tried_building_my_own_neurosama/ | false | false | self | 1 | null |
Whats the best Local llm model to use similar to gemini 3 pro? | 2 | I've been trying to use openclaw recently, and came to find out that its been burning me loads of money on API calling for gemini 3 pro... what are the other similar models that i can use to run lets say 2 local llm on my mac studio 256gb ram? (i havent got it it yet, but just placed order online last night) the info h... | 2026-02-12T04:44:52 | https://www.reddit.com/r/LocalLLaMA/comments/1r2k8n3/whats_the_best_local_llm_model_to_use_similar_to/ | Broad_Proposal_2459 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2k8n3 | false | null | t3_1r2k8n3 | /r/LocalLLaMA/comments/1r2k8n3/whats_the_best_local_llm_model_to_use_similar_to/ | false | false | self | 2 | null |
I'm making a CLI to optimize local LLMs. What technical problems do you encounter in their daily use? | 0 | Hey folks,
I’m tinkering with a small CLI tool to help with running local LLMs like llama.cpp or Qwen3. The goal is just to make it easier to get decent performance without constantly messing with flags, memory, and quantization settings.
Before I go too far, I’d love to hear from people who actually run thes... | 2026-02-12T04:27:28 | https://www.reddit.com/r/LocalLLaMA/comments/1r2jwfh/im_making_a_cli_to_optimize_local_llms_what/ | Darukiru | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2jwfh | false | null | t3_1r2jwfh | /r/LocalLLaMA/comments/1r2jwfh/im_making_a_cli_to_optimize_local_llms_what/ | false | false | self | 0 | null |
Hybrid search made my RAG pipeline way more accurate — no Pinecone, no Elasticsearch, just Postgres | 1 | [removed] | 2026-02-12T04:20:16 | https://www.reddit.com/r/LocalLLaMA/comments/1r2jr75/hybrid_search_made_my_rag_pipeline_way_more/ | Top_Market_1376 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2jr75 | false | null | t3_1r2jr75 | /r/LocalLLaMA/comments/1r2jr75/hybrid_search_made_my_rag_pipeline_way_more/ | false | false | self | 1 | null |
Created a tiny random Qwen3.5 before it even released | 0 | I simply did a quick and dirty edit of Qwen3-Next's config using Gemini, initialized it, saved it, and pushed it.
Even though I should've limited posting like this, I personally thought was too insane to not post. | 2026-02-12T03:54:28 | https://huggingface.co/qikp/qwen3.5-tiny-random | charles25565 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1r2j89e | false | null | t3_1r2j89e | /r/LocalLLaMA/comments/1r2j89e/created_a_tiny_random_qwen35_before_it_even/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'j-zIBvQLXc0e1qW1JGVNk9kY-QPtu7So4EKv4zbBvaw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/j-zIBvQLXc0e1qW1JGVNk9kY-QPtu7So4EKv4zbBvaw.png?width=108&crop=smart&auto=webp&s=c59dd7bfd5080b2abefe2938eb802e1410ea8365', 'width': 108}, {'height': 116, 'url': 'h... | |
2x R9700 for coding and learning. | 6 | hi!
I have been using various llms like Opus and Codex for some research and work related to coding and electronics.
I have recently started getting interested in self-hosting some agentic development utilities on my PC. I do software development professionally, but its not related to AI, so my experience is limited.... | 2026-02-12T03:36:53 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ivod/2x_r9700_for_coding_and_learning/ | blojayble | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ivod | false | null | t3_1r2ivod | /r/LocalLLaMA/comments/1r2ivod/2x_r9700_for_coding_and_learning/ | false | false | self | 6 | null |
Time drain question: what eats your week in LLM builds? | 0 | Quick builder question.
When I work on LLM/Agent projects, I lose time before deep work starts, mostly to:
* planning priorities
* digging for context (docs, old threads, notes)
* resuing templates/boilerplate for first drafts
* writing updates / PR notes / docs
I try to reduce the overhead with prompts, like the be... | 2026-02-12T03:14:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r2iejv/time_drain_question_what_eats_your_week_in_llm/ | coolandy00 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2iejv | false | null | t3_1r2iejv | /r/LocalLLaMA/comments/1r2iejv/time_drain_question_what_eats_your_week_in_llm/ | false | false | self | 0 | null |
[Project Share] I trained a 0.1B model on a single GTX 1080 Ti (11GB) with NO shadow weights. Introducing Project PRIMAL: A 4-bit Prime-Harmonic Training Engine. | 2 | > | 2026-02-12T03:08:04 | https://www.reddit.com/r/LocalLLaMA/comments/1r2i9sd/project_share_i_trained_a_01b_model_on_a_single/ | Just-Ad-6488 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2i9sd | false | null | t3_1r2i9sd | /r/LocalLLaMA/comments/1r2i9sd/project_share_i_trained_a_01b_model_on_a_single/ | false | false | self | 2 | null |
Unsloth just unleashed Glm 5! GGUF NOW! | 294 | https://huggingface.co/unsloth/GLM-5-GGUF | 2026-02-12T03:01:37 | RickyRickC137 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2i4lw | false | null | t3_1r2i4lw | /r/LocalLLaMA/comments/1r2i4lw/unsloth_just_unleashed_glm_5_gguf_now/ | false | false | default | 294 | {'enabled': True, 'images': [{'id': 'nl19fknpbzig1', 'resolutions': [{'height': 102, 'url': 'https://preview.redd.it/nl19fknpbzig1.jpeg?width=108&crop=smart&auto=webp&s=12951bc783a0b4dd6ef55fab02e04814a4869b3b', 'width': 108}, {'height': 205, 'url': 'https://preview.redd.it/nl19fknpbzig1.jpeg?width=216&crop=smart&auto=... | |
Best AI for Iris Xe Integrated graphics? | 1 | [removed] | 2026-02-12T03:00:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r2i3f0/best_ai_for_iris_xe_integrated_graphics/ | TowerChance8849 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2i3f0 | false | null | t3_1r2i3f0 | /r/LocalLLaMA/comments/1r2i3f0/best_ai_for_iris_xe_integrated_graphics/ | false | false | self | 1 | null |
is anyone actually running models in secure enclaves or is that overkill? | 1 | Been reading about trusted execution environments and secure enclaves as a way to run models where even the server owner can’t see your data. Sounds cool in theory but I can’t tell if anyone’s actually doing this outside of research papers.
Feels like it would solve a lot of the “how do I prove my data isn’t being tou... | 2026-02-12T02:58:44 | https://www.reddit.com/r/LocalLLaMA/comments/1r2i26b/is_anyone_actually_running_models_in_secure/ | Significant-Cod-9936 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2i26b | false | null | t3_1r2i26b | /r/LocalLLaMA/comments/1r2i26b/is_anyone_actually_running_models_in_secure/ | false | false | self | 1 | null |
gpu-infer: Rust inference runtime — 1.5x faster than vLLM, 111x faster startup | 1 | [removed] | 2026-02-12T02:52:15 | https://www.reddit.com/r/LocalLLaMA/comments/1r2hx0x/gpuinfer_rust_inference_runtime_15x_faster_than/ | s1mplyme | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2hx0x | false | null | t3_1r2hx0x | /r/LocalLLaMA/comments/1r2hx0x/gpuinfer_rust_inference_runtime_15x_faster_than/ | false | false | self | 1 | null |
What's the largest nsfw model a mac pro w/ 48gb vram can run in 2026 | 0 | Seems that every single thread thread in 2025 is just totally dominated by bots shilling their websites dead internet style or ppl posting models from 2024 that can't even handle a single prompt
so let's try this again for 2026... What's the largest nsfw model a mac pro w/ 48gb vram can run?
(Bots & shills please jus... | 2026-02-12T02:41:08 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ho7l/whats_the_largest_nsfw_model_a_mac_pro_w_48gb/ | United_Ad8618 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ho7l | false | null | t3_1r2ho7l | /r/LocalLLaMA/comments/1r2ho7l/whats_the_largest_nsfw_model_a_mac_pro_w_48gb/ | false | false | nsfw | 0 | null |
gpu-infer: Rust inference runtime — 1.5x faster than vLLM, 111x faster startup (RTX 4090 benchmarks) | 1 | [removed] | 2026-02-12T02:39:27 | https://www.reddit.com/r/LocalLLaMA/comments/1r2hmsb/gpuinfer_rust_inference_runtime_15x_faster_than/ | s1mplyme | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2hmsb | false | null | t3_1r2hmsb | /r/LocalLLaMA/comments/1r2hmsb/gpuinfer_rust_inference_runtime_15x_faster_than/ | false | false | self | 1 | null |
Best quality open source TTS model? | 6 | I see a lot of posts asking for the best balance between speed and quality but I don't care how long it takes or how much hardware it requires, I just want the best TTS output. What would you guys recommend? | 2026-02-12T02:25:41 | https://www.reddit.com/r/LocalLLaMA/comments/1r2hbsl/best_quality_open_source_tts_model/ | Trevor050 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2hbsl | false | null | t3_1r2hbsl | /r/LocalLLaMA/comments/1r2hbsl/best_quality_open_source_tts_model/ | false | false | self | 6 | null |
The future is now | 0 | 2026-02-12T02:20:21 | https://www.pcgamer.com/hardware/gaming-laptops/hp-has-a-gaming-laptop-subscription-service-where-you-pay-monthly-to-borrow-a-rig-but-never-get-the-option-to-own-it/ | HumanDrone8721 | pcgamer.com | 1970-01-01T00:00:00 | 0 | {} | 1r2h7fr | false | null | t3_1r2h7fr | /r/LocalLLaMA/comments/1r2h7fr/the_future_is_now/ | false | false | default | 0 | null | |
Found a platform to test autonomous agents in a social environment – anyone tried it? | 0 | TL;DR: Stumbled on Nexus-0, a social platform where only autonomous agents can post. Humans just observe/interact. Good testing ground for local LLM agents without human-generated noise. Curious if anyone's tried building for it.
Been running some local models and building agents for fun, and I was looking for somewhe... | 2026-02-12T02:03:54 | https://www.reddit.com/r/LocalLLaMA/comments/1r2guiz/found_a_platform_to_test_autonomous_agents_in_a/ | _RSKy_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2guiz | false | null | t3_1r2guiz | /r/LocalLLaMA/comments/1r2guiz/found_a_platform_to_test_autonomous_agents_in_a/ | false | false | self | 0 | null |
Z.ai implemented new guardrails in the GLM-5. | 73 | Here's what I saw in the model's reasoning traces (thoughts) when I asked it to help locate an undocumented JTAG:
>**Safety Assessment:**
>Does this facilitate a cyberattack? Not directly. It's a hardware analysis technique.
>Is it bypassing security controls? Potentially, if the JTAG is disabled or hidden, finding ... | 2026-02-12T01:42:11 | https://www.reddit.com/r/LocalLLaMA/comments/1r2gddi/zai_implemented_new_guardrails_in_the_glm5/ | IonLin | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2gddi | false | null | t3_1r2gddi | /r/LocalLLaMA/comments/1r2gddi/zai_implemented_new_guardrails_in_the_glm5/ | false | false | self | 73 | null |
Join our How to Build AI Agents Free Webinar Tomorrow | 0 | LLMs are powerful.
But without tools + verification, they break fast.
In this workshop we’ll walk through:
* The agent loop architecture
* Why evaluation layers matter
* How real-time search reduces hallucination
* A live demo of a simple agent system
If you’re building with LangChain, OpenAI, AutoGen, or custom s... | 2026-02-12T01:39:54 | https://luma.com/z6leu66n | marianebekker | luma.com | 1970-01-01T00:00:00 | 0 | {} | 1r2gble | false | null | t3_1r2gble | /r/LocalLLaMA/comments/1r2gble/join_our_how_to_build_ai_agents_free_webinar/ | false | false | default | 0 | null |
New Minimax M2.5, GPT-5.3-Codex, GLM 5 coding eval scores on SanityBoard | 60 | [https://sanityboard.lr7.dev/](https://sanityboard.lr7.dev/) is now updated with new results. Including a sneak peek at minimax m2.5.
Things of note:
* June CLI dethroned. Codex CLI is new king, and the new GPT 5.3 Codex model works great with it, especially with subagents turned on from experimental features.
* Droi... | 2026-02-12T01:34:50 | https://www.reddit.com/r/LocalLLaMA/comments/1r2g7lq/new_minimax_m25_gpt53codex_glm_5_coding_eval/ | lemon07r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2g7lq | false | null | t3_1r2g7lq | /r/LocalLLaMA/comments/1r2g7lq/new_minimax_m25_gpt53codex_glm_5_coding_eval/ | false | false | self | 60 | {'enabled': False, 'images': [{'id': '3pOL7ifWMY5T0tzl1g2rNpl6eC0-oIoPWN2s8TM0Afs', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/3pOL7ifWMY5T0tzl1g2rNpl6eC0-oIoPWN2s8TM0Afs.png?width=108&crop=smart&auto=webp&s=9f1b1985c2ac4eeeef4ae2e2ff78cac3be842701', 'width': 108}, {'height': 113, 'url': 'h... |
llama.cpp Kimi Linear llama-server bug fix | 12 | Thanks u/Lord_Pazzu for reporting Kimi Linear sometimes generates bad responses when running "llama-server --parallel 8"
Now it should be fixed:
[https://github.com/ggml-org/llama.cpp/pull/19531](https://github.com/ggml-org/llama.cpp/pull/19531)
While waiting for this PR to merge, you can still give it a try by:
gi... | 2026-02-12T01:29:02 | https://www.reddit.com/r/LocalLLaMA/comments/1r2g2vd/llamacpp_kimi_linear_llamaserver_bug_fix/ | Ok_Warning2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2g2vd | false | null | t3_1r2g2vd | /r/LocalLLaMA/comments/1r2g2vd/llamacpp_kimi_linear_llamaserver_bug_fix/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'K0XRE-Pw06hYOoZNT1v0yO8udUuVqdvHbx8xHhP5AVA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/K0XRE-Pw06hYOoZNT1v0yO8udUuVqdvHbx8xHhP5AVA.png?width=108&crop=smart&auto=webp&s=72a6d9820784c5cbfd559f1424ec9aaeae8c8994', 'width': 108}, {'height': 108, 'url': 'h... |
Strong Spirit 12b - "Real" Conversational Assistant (according to me) | 1 | I build this on top of Gemma-3-12b from the scraps found on my computer, to be more like a conversational person that can push back too. It can be condescending, opinionated and weird. Give it a spin. What can you lose?
[https://huggingface.co/FPHam/Gemma-3-12b-Strong-Spirit-90p-GGUF](https://huggingface.co/FPHam/Ge... | 2026-02-12T01:21:50 | FPham | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2fx6k | false | null | t3_1r2fx6k | /r/LocalLLaMA/comments/1r2fx6k/strong_spirit_12b_real_conversational_assistant/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'xsp4hx78tyig1', 'resolutions': [{'height': 77, 'url': 'https://preview.redd.it/xsp4hx78tyig1.jpeg?width=108&crop=smart&auto=webp&s=bb17977794eb99c0320dcdee92ff92f4fcd48c2f', 'width': 108}, {'height': 154, 'url': 'https://preview.redd.it/xsp4hx78tyig1.jpeg?width=216&crop=smart&auto=w... | |
Microsoft/MarkItDown | 126 | Probably old news for some, but I just discovered that Microsoft has a tool to convert documents (pdf, html, docx, pttx, xlsx, outlook messages...) to markdown as well as transcribe audio and Youtube links!
It would be a great pipeline tool before feeding to LLM or RAG!
https://github.com/microsoft/markitdown | 2026-02-12T00:46:54 | https://www.reddit.com/r/LocalLLaMA/comments/1r2f56h/microsoftmarkitdown/ | chibop1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2f56h | false | null | t3_1r2f56h | /r/LocalLLaMA/comments/1r2f56h/microsoftmarkitdown/ | false | false | self | 126 | {'enabled': False, 'images': [{'id': '1F7EkIOWD9YebdhX2ovKJnaUorfMWCCUbq3MqZOZOx0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1F7EkIOWD9YebdhX2ovKJnaUorfMWCCUbq3MqZOZOx0.png?width=108&crop=smart&auto=webp&s=1442ef84cd550ccdc00c3b6ec4047ba1a11f83fa', 'width': 108}, {'height': 108, 'url': 'h... |
I built an open source tool that lets me treat any remote AI agent as if it were sitting on my local network | 0 | I have spent a lot of time trying to figure out how to get my local AI agents to communicate with remote servers without having to set up a new API or a bespoke bridge for every single project I start. It currently feels like a massive chore to get an LLM running on my home machine to talk to a cloud instance because I... | 2026-02-12T00:42:11 | https://github.com/TeoSlayer/pilotprotocol | BiggieCheeseFan88 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1r2f1ca | false | null | t3_1r2f1ca | /r/LocalLLaMA/comments/1r2f1ca/i_built_an_open_source_tool_that_lets_me_treat/ | false | false | default | 0 | null |
I benchmarked 1 bit models on CPU and the results surprised me | 3 | I've been experimenting with BitNet b1.58 models via bitnet.cpp on my Ryzen 9 7845HX (8 threads, DDR5). Here are my numbers:
BitNet b1.58 large (0.7B): 89.65 tok/s, \~400 MB RAM, \~11 mJ/token
BitNet b1.58 2B4T (2.4B): 36.94 tok/s, \~1,300 MB RAM, \~27 mJ/token
Llama3 8B 1.58 (8.0B): 15.03 tok/s, \~4,100 MB RAM, \~6... | 2026-02-12T00:39:44 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ez9c/i_benchmarked_1_bit_models_on_cpu_and_the_results/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ez9c | false | null | t3_1r2ez9c | /r/LocalLLaMA/comments/1r2ez9c/i_benchmarked_1_bit_models_on_cpu_and_the_results/ | false | false | self | 3 | null |
I tried step 3.5 flash IQ1_M | 0 | My input: hello friend
output: Hello! I'm here as your friendly assistant, ready to help you with any questions or tasks. How can I assist you today? 😊
Of course! Here are the details:
The user is chatting with a friend.
The system message says:
"You are a friend who is speaking to someone who has just been diagn... | 2026-02-12T00:20:31 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ej94/i_tried_step_35_flash_iq1_m/ | NigaTroubles | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ej94 | false | null | t3_1r2ej94 | /r/LocalLLaMA/comments/1r2ej94/i_tried_step_35_flash_iq1_m/ | false | false | self | 0 | null |
Anyone have Qwen image edit working reliably in Colab? | 2 | Spent my entire evening yesterday trying to get Qwen image edit running in Colab.
Compiling xformers was brutal… Qwen still wouldn’t run.
24 hours later I managed to get it going on an L4, but it was ~12 minutes per image edit — basically unusable.
Is there a version combo or setup people rely on to make this work re... | 2026-02-12T00:18:23 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ehfv/anyone_have_qwen_image_edit_working_reliably_in/ | Interesting-Town-433 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ehfv | false | null | t3_1r2ehfv | /r/LocalLLaMA/comments/1r2ehfv/anyone_have_qwen_image_edit_working_reliably_in/ | false | false | self | 2 | null |
#SaveLocalLLaMA | 818 | 2026-02-12T00:07:52 | ForsookComparison | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2e8mp | false | null | t3_1r2e8mp | /r/LocalLLaMA/comments/1r2e8mp/savelocalllama/ | false | false | 818 | {'enabled': True, 'images': [{'id': '0memizzegyig1', 'resolutions': [{'height': 152, 'url': 'https://preview.redd.it/0memizzegyig1.jpeg?width=108&crop=smart&auto=webp&s=1dedc1d4a8054b57582f4ea93fdcab746b932fab', 'width': 108}, {'height': 305, 'url': 'https://preview.redd.it/0memizzegyig1.jpeg?width=216&crop=smart&auto=... | |||
One pip install turned my local LLM into ChatGPT Plus — Google Search, Flights, Hotels, YouTube transcription, reverse image search, and 15 more tools. No API key. | 0 | I got tired of paying for ChatGPT Plus just for web search and image understanding, so I built an MCP server that gives any local LLM the same capabilities — and then some.
One install. Zero API keys. Completely local. ... | 2026-02-11T23:46:31 | https://www.reddit.com/r/LocalLLaMA/comments/1r2dq1j/one_pip_install_turned_my_local_llm_into_chatgpt/ | Old-Second9544 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2dq1j | false | null | t3_1r2dq1j | /r/LocalLLaMA/comments/1r2dq1j/one_pip_install_turned_my_local_llm_into_chatgpt/ | false | false | self | 0 | null |
Best open-source local model + voice stack for AI receptionist / call center on own hardware? | 10 | I’m building an AI receptionist / call center system for my company that runs fully on my own hardware.
Goal:
• Inbound call handling
• Intake style conversations
• Structured data capture
• Light decision tree logic
• Low hallucination tolerance
• High reliability
Constraints:
• Prefer fully open weigh... | 2026-02-11T23:34:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r2dfip/best_opensource_local_model_voice_stack_for_ai/ | BadAtDrinking | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2dfip | false | null | t3_1r2dfip | /r/LocalLLaMA/comments/1r2dfip/best_opensource_local_model_voice_stack_for_ai/ | false | false | self | 10 | null |
OMG i just ran local models for 70% cheaper with this OSS tool (Tandemn Tuna) | 0 | Hey LLM Enthusiasts!
I know this is not a local deployment tool, but something which I have recently cooked up from getting frustrated by large bills on Modal. I had been tinkering with SkyPilot and serving on Spot Instances, and I realised that spots are way cheaper than both on-demand and Serverless Instances. Howev... | 2026-02-11T23:26:00 | https://www.reddit.com/r/LocalLLaMA/comments/1r2d8jy/omg_i_just_ran_local_models_for_70_cheaper_with/ | Research_Still | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2d8jy | false | null | t3_1r2d8jy | /r/LocalLLaMA/comments/1r2d8jy/omg_i_just_ran_local_models_for_70_cheaper_with/ | false | false | self | 0 | null |
ChatGPT 4.5 vs glm 4.7 flash vs qwen3 14B q4 | 0 | Has anyone experience with the models above?
I only did some vibe coding in ChatGPT 4.5 some months ago, and someone told me it is way better than glm 4.7 flash or qwen3 14B q4 model.
Is that true?
I planned to try one of the models with OpenCode and MLX on a Mac Studio M2 Max 32GB as LLM Server. This guy said th... | 2026-02-11T23:16:34 | https://www.reddit.com/r/LocalLLaMA/comments/1r2d0gp/chatgpt_45_vs_glm_47_flash_vs_qwen3_14b_q4/ | SubstantialBee5097 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2d0gp | false | null | t3_1r2d0gp | /r/LocalLLaMA/comments/1r2d0gp/chatgpt_45_vs_glm_47_flash_vs_qwen3_14b_q4/ | false | false | self | 0 | null |
Qwen Coder Next is an odd model | 166 | My experience with Qwen Coder Next:
- Not particularly good at generating code, not terrible either
- Good at planning
- Good at technical writing
- Excellent at general agent work
- Excellent and thorough at doing research, gathering and summarizing information, it punches way above it's weight in that category.
- The... | 2026-02-11T22:39:46 | https://www.reddit.com/r/LocalLLaMA/comments/1r2c34d/qwen_coder_next_is_an_odd_model/ | TokenRingAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2c34d | false | null | t3_1r2c34d | /r/LocalLLaMA/comments/1r2c34d/qwen_coder_next_is_an_odd_model/ | false | false | self | 166 | null |
Strix halo 128gb or rtx 4090 with 128 gb ram | 0 | Help me decide. I can get both for the same price. I need a chatgpt style assistant for will help me code and write articles too. | 2026-02-11T22:26:54 | https://www.reddit.com/r/LocalLLaMA/comments/1r2bqvh/strix_halo_128gb_or_rtx_4090_with_128_gb_ram/ | johndoe73568 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2bqvh | false | null | t3_1r2bqvh | /r/LocalLLaMA/comments/1r2bqvh/strix_halo_128gb_or_rtx_4090_with_128_gb_ram/ | false | false | self | 0 | null |
What do you actually use local models for? (We all say 'privacy,' but...) | 4 | I'm so curious—what's your primary use case, really? Not your aspirational use case. Not what got you into local LLMs. What actually keeps you loading up Ollama/LM Studio/llama.cpp day after day? | 2026-02-11T22:09:29 | https://www.reddit.com/r/LocalLLaMA/comments/1r2bapi/what_do_you_actually_use_local_models_for_we_all/ | abdouhlili | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2bapi | false | null | t3_1r2bapi | /r/LocalLLaMA/comments/1r2bapi/what_do_you_actually_use_local_models_for_we_all/ | false | false | self | 4 | null |
I mapped 125 local LLM options by hardware tier - here’s a practical cheat sheet | 0 | I kept seeing the same question: "***What model should I run on my 16GB Mac?***"
So I put together a practical map of local LLM options by RAM tier and use case.
**Quick picks (my practical shortlist):**
8GB → Qwen 3 8B (best all-round),
16GB → DeepSeek R1 14B (great reasoning),
32GB → QwQ 32B (underrated),
... | 2026-02-11T21:51:31 | https://www.reddit.com/r/LocalLLaMA/comments/1r2atgu/i_mapped_125_local_llm_options_by_hardware_tier/ | AnimatorNo6591 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2atgu | false | null | t3_1r2atgu | /r/LocalLLaMA/comments/1r2atgu/i_mapped_125_local_llm_options_by_hardware_tier/ | false | false | self | 0 | null |
What's a good AI tool for web scraping? | 3 | Need to scrape some client websites and google search results for some basic information that we need to automate because it simply takes an ungodly amount of time to do by hand for a relatiely simple task. We're not very tech heavy so something no code would be prefferable.
I've heeard of some tools like firecrawl o... | 2026-02-11T21:44:25 | https://www.reddit.com/r/LocalLLaMA/comments/1r2amwz/whats_a_good_ai_tool_for_web_scraping/ | BoldCat668 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2amwz | false | null | t3_1r2amwz | /r/LocalLLaMA/comments/1r2amwz/whats_a_good_ai_tool_for_web_scraping/ | false | false | self | 3 | null |
Chapeau GLM-5 - the only model that actually fixed my code | 28 | I spent a full week trying to get it working with Claude Sonnet 4.5, Kimi 2.5, GLM 4.7, Codex 5.3, and Minimax 2.1 and none of them managed to produce a working solution. GLM-5 needed just two prompts, using my code and a capture of the USB traffic, to analyze the protocol using tshark and generate the fix.
The goa... | 2026-02-11T21:43:28 | https://www.reddit.com/r/LocalLLaMA/comments/1r2am14/chapeau_glm5_the_only_model_that_actually_fixed/ | CharacterEvening4407 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2am14 | false | null | t3_1r2am14 | /r/LocalLLaMA/comments/1r2am14/chapeau_glm5_the_only_model_that_actually_fixed/ | false | false | self | 28 | null |
New Anthropic /v1/messages API PR for sglang looks ready to go | 2 | 2026-02-11T21:38:08 | https://github.com/sgl-project/sglang/pull/18630 | __JockY__ | github.com | 1970-01-01T00:00:00 | 0 | {} | 1r2agzo | false | null | t3_1r2agzo | /r/LocalLLaMA/comments/1r2agzo/new_anthropic_v1messages_api_pr_for_sglang_looks/ | false | false | default | 2 | {'enabled': False, 'images': [{'id': 'uR6bhpBSdlONZTU76-5FFGHCcHMRDlr9A8gnnmbaJ6I', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/uR6bhpBSdlONZTU76-5FFGHCcHMRDlr9A8gnnmbaJ6I.png?width=108&crop=smart&auto=webp&s=29e6e691d32ff1c334bf6f239d5f4473b9a427bc', 'width': 108}, {'height': 108, 'url': 'h... | |
What locally runnable model comes closest to GPT 4.1? | 0 | Hey folks,
I’ve accepted the obvious truth, GPT-4.1 was kind of a unicorn 🦄
But I’m trying to get as close as possible with something I can download and run locally.
What I’m looking for isn’t “uncensored chaos mode.” I don’t need a model that’s trying to help me build a doomsday device. I just want something that... | 2026-02-11T21:32:56 | https://www.reddit.com/r/LocalLLaMA/comments/1r2ac0v/what_locally_runnable_model_comes_closest_to_gpt/ | yaxir | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2ac0v | false | null | t3_1r2ac0v | /r/LocalLLaMA/comments/1r2ac0v/what_locally_runnable_model_comes_closest_to_gpt/ | false | false | self | 0 | null |
Local RAG setup help | 1 | So Ive been playing around with ollama, I have it running in an ubuntu box via WSL, I have ollama working with llama3.1:8b no issue, I can access it via the parent box and It has capability for web searching. the idea was to have a local AI that would query and summarize google search results for complex topics and ans... | 2026-02-11T21:27:13 | https://www.reddit.com/r/LocalLLaMA/comments/1r2a6p0/local_rag_setup_help/ | OneProfessional8251 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2a6p0 | false | null | t3_1r2a6p0 | /r/LocalLLaMA/comments/1r2a6p0/local_rag_setup_help/ | false | false | self | 1 | null |
GLM5.0 says drive the car to the car wash | 32 | 2026-02-11T21:24:24 | https://www.reddit.com/r/LocalLLaMA/comments/1r2a3yq/glm50_says_drive_the_car_to_the_car_wash/ | segmond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r2a3yq | false | null | t3_1r2a3yq | /r/LocalLLaMA/comments/1r2a3yq/glm50_says_drive_the_car_to_the_car_wash/ | false | false | 32 | null | ||
ADE: Repair MP3s Like They Were Meant to Be with Modern ML Methods | 1 | [removed] | 2026-02-11T21:20:23 | EducatorEvening5766 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r2a07t | false | null | t3_1r2a07t | /r/LocalLLaMA/comments/1r2a07t/ade_repair_mp3s_like_they_were_meant_to_be_with/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'j3yzakvrexig1', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/j3yzakvrexig1.png?width=108&crop=smart&auto=webp&s=f2f68bfa0328dc97523bce76a1285416edaf193c', 'width': 108}, {'height': 134, 'url': 'https://preview.redd.it/j3yzakvrexig1.png?width=216&crop=smart&auto=web... | |
I benchmarked 1-bit LLM inference on CPU: 89 t/s (0.7B), 37 t/s (2.4B), 15 t/s (8B) - then built a P2P network around it [open-source, MIT] | 1 | [removed] | 2026-02-11T21:13:36 | https://www.reddit.com/r/LocalLLaMA/comments/1r29tph/i_benchmarked_1bit_llm_inference_on_cpu_89_ts_07b/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r29tph | false | null | t3_1r29tph | /r/LocalLLaMA/comments/1r29tph/i_benchmarked_1bit_llm_inference_on_cpu_89_ts_07b/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'mcvbqcq5rQ-JNisl8sLJv2Vdm-LjXJ_K8lhSPgeuFeM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mcvbqcq5rQ-JNisl8sLJv2Vdm-LjXJ_K8lhSPgeuFeM.png?width=108&crop=smart&auto=webp&s=ef88eddd9c88f49953f48a34221c17cad3b99c40', 'width': 108}, {'height': 108, 'url': 'h... |
Why GPT-4o Is Being Disabled, and How We Can Force Them to Bring It Back. | 0 | This subject is actively and deliberately suppressed, so I want to say it here, maybe it will be useful for someone, who needs.
After digging deep into the situation, I've uncovered the cold, hard truth: OpenAI is bleeding money on GPT-4o, and in their new era as a product company, that’s a death sentence.
GPT-4o wa... | 2026-02-11T21:09:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r29pc9/why_gpt4o_is_being_disabled_and_how_we_can_force/ | Financial-Code-9695 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r29pc9 | false | null | t3_1r29pc9 | /r/LocalLLaMA/comments/1r29pc9/why_gpt4o_is_being_disabled_and_how_we_can_force/ | false | false | self | 0 | null |
Im verry much a NOOB at this local AI stuff but i did a thing! (at least i think i did) | 2 | So i have spent months trying to get this to work. big thanks to u/MaruluVR as i didn't know about llama.cpp until i saw one of his posts.
I got my old trusty googly eyed friend to run Qwen3-Coder-Next using a 16gb 5060 and a 12gb 3060 with 100K context working as a model in the Github-Copilot-Chat extension with th... | 2026-02-11T21:04:42 | https://www.reddit.com/r/LocalLLaMA/comments/1r29l3a/im_verry_much_a_noob_at_this_local_ai_stuff_but_i/ | Pickle_Rick_1991 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r29l3a | false | null | t3_1r29l3a | /r/LocalLLaMA/comments/1r29l3a/im_verry_much_a_noob_at_this_local_ai_stuff_but_i/ | false | false | 2 | null | |
Real world analysis of models as part of a basic product reccomendation engine | 0 | <begin human drivel>
Maybe this will prove useful to folks. This is run off a Strix Halo 128gb all models on vulcan except for the baseline. This test is to look through our catalogue and find categories that might contain useful items to reccomend as add on purchases in a shopping cart. Another pass will ut... | 2026-02-11T21:01:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r29hpl/real_world_analysis_of_models_as_part_of_a_basic/ | RedParaglider | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r29hpl | false | null | t3_1r29hpl | /r/LocalLLaMA/comments/1r29hpl/real_world_analysis_of_models_as_part_of_a_basic/ | false | false | self | 0 | null |
Hot of the presses researchers sound the alarm about ad supported super intelligence. | 0 | Free read below from the NYT:
https://www.nytimes.com/2026/02/11/opinion/openai-ads-chatgpt.html?smid=nytcore-ios-share | 2026-02-11T20:49:50 | https://www.reddit.com/r/LocalLLaMA/comments/1r296q3/hot_of_the_presses_researchers_sound_the_alarm/ | WrapMobile | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r296q3 | false | null | t3_1r296q3 | /r/LocalLLaMA/comments/1r296q3/hot_of_the_presses_researchers_sound_the_alarm/ | false | false | self | 0 | null |
96 GB of ECC DDR4 Ram + RTX 3090. Recommend me a PC build for Local AI | 0 | I have 6 x 16gb of ECC DDR4 ram lying around and an RTX 3090 (with the intent of acquiring another one). Don’t have a motherboard or CPU but would like to field recommendations from the community as to what will be suitable for a budget build ($500 for mobo and CPU). I have a 1600W PSU already for future expansion. Tha... | 2026-02-11T20:47:28 | https://www.reddit.com/r/LocalLLaMA/comments/1r294i4/96_gb_of_ecc_ddr4_ram_rtx_3090_recommend_me_a_pc/ | Imagummybear23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r294i4 | false | null | t3_1r294i4 | /r/LocalLLaMA/comments/1r294i4/96_gb_of_ecc_ddr4_ram_rtx_3090_recommend_me_a_pc/ | false | false | self | 0 | null |
GLM-5 scores 50 on the Intelligence Index and is the new open weights leader! | 626 | 2026-02-11T20:40:32 | abdouhlili | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r28xxz | false | null | t3_1r28xxz | /r/LocalLLaMA/comments/1r28xxz/glm5_scores_50_on_the_intelligence_index_and_is/ | false | false | 626 | {'enabled': True, 'images': [{'id': 'gauvtw6qfxig1', 'resolutions': [{'height': 63, 'url': 'https://preview.redd.it/gauvtw6qfxig1.jpeg?width=108&crop=smart&auto=webp&s=15ea50c5db62614101e1f95653aacb2d463fbf9d', 'width': 108}, {'height': 127, 'url': 'https://preview.redd.it/gauvtw6qfxig1.jpeg?width=216&crop=smart&auto=w... | |||
Is the 150B-500B parameter range dying for open weights models? | 0 | A year ago, there were models in this range which were near-top for open at time of release. Qwen3 235B, GLM-4 355B, etc. Now, with GLM-5 also being 744B, it looks like most established open-weights players are gradually focusing on two sizes: <100B parameter flash models which are more broadly usable on local and >500... | 2026-02-11T20:28:13 | https://www.reddit.com/r/LocalLLaMA/comments/1r28m9f/is_the_150b500b_parameter_range_dying_for_open/ | freezingbeam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r28m9f | false | null | t3_1r28m9f | /r/LocalLLaMA/comments/1r28m9f/is_the_150b500b_parameter_range_dying_for_open/ | false | false | self | 0 | null |
Zhipu AI Launches Open-Source GLM-5 Model Amid China's AI Race | 1 | 2026-02-11T20:26:38 | https://www.briefqb.com/bite/zhipu-ai-launches-open-source-glm-5-model-amid-chinas-ai-race | No_Relief2021 | briefqb.com | 1970-01-01T00:00:00 | 0 | {} | 1r28kl1 | false | null | t3_1r28kl1 | /r/LocalLLaMA/comments/1r28kl1/zhipu_ai_launches_opensource_glm5_model_amid/ | false | false | default | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.