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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Post caught by spam filter - 1-bit LLM benchmark | 1 | [removed] | 2026-02-15T11:17:38 | https://www.reddit.com/r/LocalLLaMA/comments/1r5c743/post_caught_by_spam_filter_1bit_llm_benchmark/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5c743 | false | null | t3_1r5c743 | /r/LocalLLaMA/comments/1r5c743/post_caught_by_spam_filter_1bit_llm_benchmark/ | false | false | self | 1 | null |
I benchmarked every 1-bit model I could find, native 1-bit is 50% faster than post-quantized | 1 | [removed] | 2026-02-15T11:16:30 | https://www.reddit.com/r/LocalLLaMA/comments/1r5c6ez/i_benchmarked_every_1bit_model_i_could_find/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5c6ez | false | null | t3_1r5c6ez | /r/LocalLLaMA/comments/1r5c6ez/i_benchmarked_every_1bit_model_i_could_find/ | false | false | self | 1 | null |
I benchmarked every 1-bit model I could find, native 1-bit is 50% faster than post-quantized | 1 | [removed] | 2026-02-15T11:14:25 | https://www.reddit.com/r/LocalLLaMA/comments/1r5c55w/i_benchmarked_every_1bit_model_i_could_find/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5c55w | false | null | t3_1r5c55w | /r/LocalLLaMA/comments/1r5c55w/i_benchmarked_every_1bit_model_i_could_find/ | false | false | self | 1 | null |
I benchmarked every 1-bit model I could find, native 1-bit is 50% faster than post-quantized | 1 | [removed] | 2026-02-15T11:04:40 | https://www.reddit.com/r/LocalLLaMA/comments/1r5bzjb/i_benchmarked_every_1bit_model_i_could_find/ | EiwazDeath | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5bzjb | false | null | t3_1r5bzjb | /r/LocalLLaMA/comments/1r5bzjb/i_benchmarked_every_1bit_model_i_could_find/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'n1cVc9aaubhbA5dTbmYN-CQ2eOT6SvY8ElB5Z5uo6pU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/n1cVc9aaubhbA5dTbmYN-CQ2eOT6SvY8ElB5Z5uo6pU.png?width=108&crop=smart&auto=webp&s=2ac11005f66a2eddf200fcef8c95b99bb9576dcb', 'width': 108}, {'height': 108, 'url': 'h... |
Anyone self-hosting LLMs specifically for data sovereignty reasons? What's your setup? | 2 | I work in the B2B space in Europe and the number of companies asking about self-hosted LLMs has exploded in the last 6 months. The main driver is not cost or performance, it is data sovereignty.
Legal teams, healthcare orgs, defense contractors — they all want GPT-level productivity but cannot send data to US servers... | 2026-02-15T10:57:09 | https://www.reddit.com/r/LocalLLaMA/comments/1r5buxc/anyone_selfhosting_llms_specifically_for_data/ | BreizhNode | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5buxc | false | null | t3_1r5buxc | /r/LocalLLaMA/comments/1r5buxc/anyone_selfhosting_llms_specifically_for_data/ | false | false | self | 2 | null |
Local-first AI NPC desktop with self-hosted gateways, agent gameplay, and multi-LLM support (openClaw Desktop) | 5 | Hey all,
I’ve been experimenting with building a **local-first AI desktop** that works with self-hosted gateways and local LLM setups.
Instead of another browser chat UI, this project explores an **NPC-style desktop interface** where agents, games, and document workflows live together.
# Current features
... | 2026-02-15T10:53:51 | https://www.reddit.com/gallery/1r5bt2s | stormixus | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1r5bt2s | false | null | t3_1r5bt2s | /r/LocalLLaMA/comments/1r5bt2s/localfirst_ai_npc_desktop_with_selfhosted/ | false | false | 5 | null | |
Analyze your model checkpoints. | 0 | I came across multiple instances where model checkpoints load perfectly and fail downstream. Model checkpoints are quite brittle in nature and can get corrupted easily, causing the programmer / researcher to be very careful.
To spare the headache, I created Weightlens, a CLI tool that analyzes your model checkpoints ... | 2026-02-15T10:51:55 | https://www.reddit.com/r/LocalLLaMA/comments/1r5brz4/analyze_your_model_checkpoints/ | akshathm052 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5brz4 | false | null | t3_1r5brz4 | /r/LocalLLaMA/comments/1r5brz4/analyze_your_model_checkpoints/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'IUHM4ctLZQorzkPuYJ4IkGSag8BtaIqZoyqL1L53KuM', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/IUHM4ctLZQorzkPuYJ4IkGSag8BtaIqZoyqL1L53KuM.jpeg?width=108&crop=smart&auto=webp&s=3c06c05fbfc6417cf2ed8eb973d76d70376c5051', 'width': 108}, {'height': 216, 'url': ... |
Q: How was Ring-Mini-Linear-2.0 (and other shallow hybrid attention models)? | 5 | There are models like Kimi-Linear and Nemotron-3-Nano that are fast and compatible with agents, and yet I can't seem to get the smaller Ring-V2 model to run. They have half the parameters and 20% less layers (I think?) but still claims to be half decent for agents. Has anyone tried to use this with coding agents for si... | 2026-02-15T10:47:21 | https://www.reddit.com/r/LocalLLaMA/comments/1r5bpb8/q_how_was_ringminilinear20_and_other_shallow/ | TomLucidor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5bpb8 | false | null | t3_1r5bpb8 | /r/LocalLLaMA/comments/1r5bpb8/q_how_was_ringminilinear20_and_other_shallow/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'DmU6JYbL_lQF5cDjGHwedPaORJZBuFQKZUI9mlFPC3Q', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DmU6JYbL_lQF5cDjGHwedPaORJZBuFQKZUI9mlFPC3Q.png?width=108&crop=smart&auto=webp&s=e0fbed40723af4ec84f99835d2e6663716274b93', 'width': 108}, {'height': 116, 'url': 'h... |
I built a simple debugger for AI agents that's 100% local and free | 0 | Hey everyone! I just released VMdebugger - a privacy-first debugging tool for AI agents.
\*\*The Problem:\*\* When your agent fails, you have no idea WHERE it failed or WHY it made bad decisions. Existing tools like LangSmith require cloud accounts and complex setup.
\*\*My Solution:\*\*
\- 100% local (no cloud... | 2026-02-15T10:45:56 | https://www.reddit.com/r/LocalLLaMA/comments/1r5boi4/i_built_a_simple_debugger_for_ai_agents_thats_100/ | Key_Historian_4806 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5boi4 | false | null | t3_1r5boi4 | /r/LocalLLaMA/comments/1r5boi4/i_built_a_simple_debugger_for_ai_agents_thats_100/ | false | false | self | 0 | null |
Has anyone else noticed sudden usage limit cuts on Pro plans with Z.ai? | 0 | I want to check if I’m the only one experiencing this, or if others are seeing the same thing.
This is not just happening with GLM-5. I tested GLM-4.7 and 4.6 as well, and the usage behavior seems to have changed across all models.
Earlier, I wasn’t even touching 10% of my usage limit on the Pro plan. Suddenly, my us... | 2026-02-15T10:36:22 | https://www.reddit.com/r/LocalLLaMA/comments/1r5bipc/has_anyone_else_noticed_sudden_usage_limit_cuts/ | ProgressOnly7336 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5bipc | false | null | t3_1r5bipc | /r/LocalLLaMA/comments/1r5bipc/has_anyone_else_noticed_sudden_usage_limit_cuts/ | false | false | self | 0 | null |
The Hollywood Nerf has begun: Seedance 2.0 is already being lobotomized. Local Weights are our only defense. | 84 | AI video just hit a massive wall, and it's a textbook case of why we can never trust SaaS/Closed-source for our creative freedom.
Last Thursday (Feb 12), ByteDance launched Seedance 2.0. For about 48 hours, it was incredible. People were generating hyper-realistic clips that looked like $200M productions. It was a "So... | 2026-02-15T10:34:14 | https://www.reddit.com/r/LocalLLaMA/comments/1r5bhhv/the_hollywood_nerf_has_begun_seedance_20_is/ | maroule | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5bhhv | false | null | t3_1r5bhhv | /r/LocalLLaMA/comments/1r5bhhv/the_hollywood_nerf_has_begun_seedance_20_is/ | false | false | self | 84 | null |
The current top 4 models on openrouter are all open-weight | 96 | I could be wrong but I think this is the first time this has happened. Is this a pivotal moment or just a temporary fluke?
https://preview.redd.it/jjpkakoaxmjg1.png?width=1738&format=png&auto=webp&s=5072055e50df1701fe5ab51ce67e1b7476f8c62d
| 2026-02-15T10:29:20 | https://www.reddit.com/r/LocalLLaMA/comments/1r5beqe/the_current_top_4_models_on_openrouter_are_all/ | svantana | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5beqe | false | null | t3_1r5beqe | /r/LocalLLaMA/comments/1r5beqe/the_current_top_4_models_on_openrouter_are_all/ | false | false | 96 | null | |
best local models for claude code | 1 | question to you - what's the best local model (or open model) to use with claude code based on you experience? for agentic and noncoding staff primary. ta | 2026-02-15T10:29:06 | https://www.reddit.com/r/LocalLLaMA/comments/1r5bem8/best_local_models_for_claude_code/ | Steus_au | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5bem8 | false | null | t3_1r5bem8 | /r/LocalLLaMA/comments/1r5bem8/best_local_models_for_claude_code/ | false | false | self | 1 | null |
I Spent Months Comparing Runpod, Vast.ai, and GPUHub — Here’s What Actually Matters | 0 | When people ask me which GPU cloud platform they should use — [Runpod](https://www.runpod.io/), [Vast.ai](http://Vast.ai), or [GPUHub](https://gpuhub.com/) — they usually expect a quick answer based on price per hour or GPU model.
But after spending a few months deploying workloads across all three, I’ve realized the ... | 2026-02-15T09:15:30 | https://www.reddit.com/r/LocalLLaMA/comments/1r5a862/i_spent_months_comparing_runpod_vastai_and_gpuhub/ | Narwal77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r5a862 | false | null | t3_1r5a862 | /r/LocalLLaMA/comments/1r5a862/i_spent_months_comparing_runpod_vastai_and_gpuhub/ | false | false | 0 | null | |
Kreuzberg v4.3.0 and benchmarks | 56 | Hi folks,
we have two announcements to share about [Kreuzberg](https://github.com/kreuzberg-dev/kreuzberg).
First, we’ve published a new set of comparative benchmarks with an interactive UI and fully reproducible results. We’ve been working on these for quite some time, and the goal is to help developers understand h... | 2026-02-15T08:49:49 | https://www.reddit.com/r/LocalLLaMA/comments/1r59th1/kreuzberg_v430_and_benchmarks/ | Eastern-Surround7763 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r59th1 | false | null | t3_1r59th1 | /r/LocalLLaMA/comments/1r59th1/kreuzberg_v430_and_benchmarks/ | false | false | self | 56 | {'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... |
Open-source LLM-as-a-Judge pipeline for comparing local models - feedback welcome | 8 | I’ve been trying to evaluate local models more systematically (LLaMA-3, Qwen-Coder, etc.), especially for things like RAG answers and code tasks.
Manual spot-checking wasn’t scaling, so I built a small open-source pipeline that uses **LLM-as-a-Judge** with structured prompts + logging:
[https://github.com/Dakshjain16... | 2026-02-15T08:47:56 | https://www.reddit.com/r/LocalLLaMA/comments/1r59seg/opensource_llmasajudge_pipeline_for_comparing/ | gvij | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r59seg | false | null | t3_1r59seg | /r/LocalLLaMA/comments/1r59seg/opensource_llmasajudge_pipeline_for_comparing/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'L1JtCNqHoch5GiBZgJJYS9ai4QuUhe1dM4f3eWzHEZw', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/L1JtCNqHoch5GiBZgJJYS9ai4QuUhe1dM4f3eWzHEZw.png?width=108&crop=smart&auto=webp&s=f2d7d6405d2ef4eaf6b73557e3ef2042015f1e45', 'width': 108}, {'height': 108, 'url': 'h... |
Что за ограничение времени в c.ai? | 0 | Вчера в приложении вроде был сбой, а сегодня предлагают подписку на c.ai+ чтобы пропустить очередь. Время ожидания вроде бы написано 1 час | 2026-02-15T08:28:46 | https://www.reddit.com/r/LocalLLaMA/comments/1r59h6d/что_за_ограничение_времени_в_cai/ | RATARETO_107 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r59h6d | false | null | t3_1r59h6d | /r/LocalLLaMA/comments/1r59h6d/что_за_ограничение_времени_в_cai/ | false | false | self | 0 | null |
WARNING: Cursor Pro is a predatory trap. Hidden fees put me in debt ($60) in <24 hours | 1 | I am writing this to warn new users. Do NOT trust the "Pro" subscription blindly.
I am a student/developer from a low-income region. I scraped together $20 for the "Pro" subscription because I needed a good coding assistant. I thought $20/mo meant I was safe to use the tool, similar to ChatGPT Plus or Gemini Advanced.... | 2026-02-15T08:26:36 | https://www.reddit.com/r/LocalLLaMA/comments/1r59fvc/warning_cursor_pro_is_a_predatory_trap_hidden/ | Only_Salamander_227 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r59fvc | false | null | t3_1r59fvc | /r/LocalLLaMA/comments/1r59fvc/warning_cursor_pro_is_a_predatory_trap_hidden/ | false | false | 1 | null | |
Made an agent skill that records system flows in SQLite. Started for security audits, now I use it to brainstorm features | 0 | Been using this daily for a few months, figured I'd open-source it.
**What** **it** **does:** You tell your AI agent (Claude Code, Codex CLI, etc.) to trace a flow through your codebase. It records every step as a node in SQLite which layer (CODE/API/AUTH/DATA/NETWORK), what action, which file. Edges connect nodes wit... | 2026-02-15T08:24:43 | https://www.reddit.com/r/LocalLLaMA/comments/1r59erz/made_an_agent_skill_that_records_system_flows_in/ | Role_External | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r59erz | false | null | t3_1r59erz | /r/LocalLLaMA/comments/1r59erz/made_an_agent_skill_that_records_system_flows_in/ | false | false | self | 0 | null |
MiniMax-M2.5 REAP models available on HF | 29 | I just noticed that a bunch of REAP variants for MiniMax M2.5 got pushed to HF here: [https://huggingface.co/Akicou/models](https://huggingface.co/Akicou/models)
I've been messing about flipping between Qwen Coder Next and MiniMax M2.5, and just personally I've been preferring MiniMax. QCN does eventually get things ... | 2026-02-15T07:58:25 | https://www.reddit.com/r/LocalLLaMA/comments/1r58zep/minimaxm25_reap_models_available_on_hf/ | Look_0ver_There | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58zep | false | null | t3_1r58zep | /r/LocalLLaMA/comments/1r58zep/minimaxm25_reap_models_available_on_hf/ | false | false | self | 29 | {'enabled': False, 'images': [{'id': 'eLgxQsYAAd7wmt-4YvvhrNjmOWuCExxlNQAup6Klrs4', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/eLgxQsYAAd7wmt-4YvvhrNjmOWuCExxlNQAup6Klrs4.png?width=108&crop=smart&auto=webp&s=5d5089d13b8ca2e84b4f3c57bd5215402a7747a3', 'width': 108}, {'height': 116, 'url': 'h... |
Quantitative Finance-Macroeconomics | 0 | DEF\_PROTO\[Omniscient\_Alpha\_Genesis\_Compact\]EXTENDS\[Omniscient\_Alpha\_Genesis\_Matrix\]:{SET{PARENT:"Omniscient\_Alpha\_Genesis\_Matrix",TARGET:"M\_CB",MIN\_CN:3000,TONE:"Institutional\_Quant\_Neutral"};DEF\_SET\_M\_CB\_Deep\_Layer:{DIM\_01:{ID:"R\_Star\_Gap",Proto:\["NY\_Fed\_HLW","Richmond\_Fed"\],Thy:"Wicksel... | 2026-02-15T07:52:10 | https://www.reddit.com/r/LocalLLaMA/comments/1r58vvr/quantitative_financemacroeconomics/ | Dependent_Cake_5350 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58vvr | false | null | t3_1r58vvr | /r/LocalLLaMA/comments/1r58vvr/quantitative_financemacroeconomics/ | false | false | self | 0 | null |
5090 and 3090 machine for text generation and reasoning? 3D model generation? | 0 | Hello,
my main goal is not to have a local machine to replace code generation or video generation, but I need it to be able to have reasoning capabilities in the context of role playing, and adhering to dnd rules. Also, it will be nice to be able to generate not highly detailed 3d models.
I wonder if adding a 5090 t... | 2026-02-15T07:48:22 | https://www.reddit.com/r/LocalLLaMA/comments/1r58tpd/5090_and_3090_machine_for_text_generation_and/ | romantimm25 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58tpd | false | null | t3_1r58tpd | /r/LocalLLaMA/comments/1r58tpd/5090_and_3090_machine_for_text_generation_and/ | false | false | self | 0 | null |
Setup Help: Local Ollama (Qwen2.5/DeepSeek) in VS Code for Android Dev — How to get "Agentic" file editing working? | 0 | Hey everyone! I’m trying to move away from the GitHub Copilot free tier and go 100% local for my Android (Kotlin/Java) development.
The Goal: I want the AI to be able to create, delete, and modify project files directly (like Copilot’s "Agent" mode) using Ollama.
My Current Setup:
Hardware: 16gb ram 8gb rtx 3070 ti ... | 2026-02-15T07:29:38 | https://www.reddit.com/r/LocalLLaMA/comments/1r58irl/setup_help_local_ollama_qwen25deepseek_in_vs_code/ | AppropriateMenu5934 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58irl | false | null | t3_1r58irl | /r/LocalLLaMA/comments/1r58irl/setup_help_local_ollama_qwen25deepseek_in_vs_code/ | false | false | self | 0 | null |
Which uncensored model will be best for MBP M4 Pro 24GB? | 0 | I mostly just use Gemini through AI Studio but I want to have model I can ask questions that trigger Gemini's guardrails. It's not necessary that it'd be very fast. I'd rather have smarter and more accurate model than faster one. But to a reasonable extent ofc. I am okay with waiting minute or minute and half for an an... | 2026-02-15T07:19:15 | https://www.reddit.com/r/LocalLLaMA/comments/1r58ci5/which_uncensored_model_will_be_best_for_mbp_m4/ | y-amsp1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58ci5 | false | null | t3_1r58ci5 | /r/LocalLLaMA/comments/1r58ci5/which_uncensored_model_will_be_best_for_mbp_m4/ | false | false | self | 0 | null |
jdopensource/JoyAI-LLM-Flash • HuggingFace | 49 | [https://huggingface.co/jdopensource/JoyAI-LLM-Flash](https://huggingface.co/jdopensource/JoyAI-LLM-Flash)
https://preview.redd.it/kl2loe9c0mjg1.jpg?width=680&format=pjpg&auto=webp&s=1b1437da4ce6468f7f9b580b3a7f88bb359f23e9
| 2026-02-15T07:18:52 | https://www.reddit.com/r/LocalLLaMA/comments/1r58ca8/jdopensourcejoyaillmflash_huggingface/ | External_Mood4719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r58ca8 | false | null | t3_1r58ca8 | /r/LocalLLaMA/comments/1r58ca8/jdopensourcejoyaillmflash_huggingface/ | false | false | 49 | null | |
How come this 48x2 5600MHz run oss 120b faster than AI MAX 395 128GB? | 0 | 2026-02-15T07:00:47 | https://www.reddit.com/r/LocalLLaMA/comments/1r581i6/how_come_this_48x2_5600mhz_run_oss_120b_faster/ | Clean-Shoulder-2563 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r581i6 | false | null | t3_1r581i6 | /r/LocalLLaMA/comments/1r581i6/how_come_this_48x2_5600mhz_run_oss_120b_faster/ | false | false | 0 | null | ||
ConversationalFilter - Stop LLM Over-Explanation - Now Available | 2 | I built ConversationalFilter to solve a problem I kept running into with LLMs: you ask a simple question and get a 500-word essay back.
It detects when responses are getting too verbose, auto-truncates unnecessary elaboration, and adds smart clarifying questions instead of dumping information. It also adapts to your... | 2026-02-15T06:36:29 | https://www.reddit.com/r/LocalLLaMA/comments/1r57n2x/conversationalfilter_stop_llm_overexplanation_now/ | Extension_Pop3732 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r57n2x | false | null | t3_1r57n2x | /r/LocalLLaMA/comments/1r57n2x/conversationalfilter_stop_llm_overexplanation_now/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'EWGzRwGy8j2XXfJTeleuCieMEqxmtbcPsj1XiNtNask', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EWGzRwGy8j2XXfJTeleuCieMEqxmtbcPsj1XiNtNask.png?width=108&crop=smart&auto=webp&s=ca2a89a38ee813e76d38755ce8c3a41d23e4be82', 'width': 108}, {'height': 108, 'url': 'h... |
Nvidia’s new technique cuts LLM reasoning costs by 8x without losing accuracy | 5 | https://venturebeat.com/orchestration/nvidias-new-technique-cuts-llm-reasoning-costs-by-8x-without-losing-accuracy
Nvidia has released DMS as part of its Model Optimizer framework. Regarding how enterprises can get started with DMS, Nawrot emphasized that the barrier to entry is low. "The 'minimum viable infrastructur... | 2026-02-15T05:49:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r56tfg/nvidias_new_technique_cuts_llm_reasoning_costs_by/ | ANR2ME | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r56tfg | false | null | t3_1r56tfg | /r/LocalLLaMA/comments/1r56tfg/nvidias_new_technique_cuts_llm_reasoning_costs_by/ | false | false | self | 5 | null |
New Benchmark Exposes How Far Behind Chinese AI Models Really Are | 0 | Everyone thinks the AI race gap is closing. However, a new benchmark called SWE-rebench just exposed how misleading many headline results have been. If you don’t already know, for the past year, many labs have been training their models on public benchmark questions, effectively teaching them the answers instead of mak... | 2026-02-15T05:32:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r56int/new_benchmark_exposes_how_far_behind_chinese_ai/ | purealgo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r56int | false | null | t3_1r56int | /r/LocalLLaMA/comments/1r56int/new_benchmark_exposes_how_far_behind_chinese_ai/ | false | false | self | 0 | null |
Ground-up MLX reimplementation of Qwen3-ASR for Apple Silicon | 21 | This is what claude & codex worked on for valentine's day:
Ground-up MLX reimplementation of Qwen3-ASR for Apple Silicon
pip install mlx-qwen3-asr
Benchmarks (M4 Pro, 0.6B fp16):
\- 2.5s clip: 0.46s latency, 0.08 RTF
\- 10s clip: 0.83s latency, 0.08 RTF
\- 4-bit quantized: 4.7x faster, WER 2.29% → 2.72% (Li... | 2026-02-15T05:19:47 | https://github.com/moona3k/mlx-qwen3-asr/ | PrimaryAbility9 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1r56ak1 | false | null | t3_1r56ak1 | /r/LocalLLaMA/comments/1r56ak1/groundup_mlx_reimplementation_of_qwen3asr_for/ | false | false | 21 | {'enabled': False, 'images': [{'id': 'KDZqgIfnwVfMzphVYrHDwwZwiqbRfErXcNBAe6CZe0k', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/KDZqgIfnwVfMzphVYrHDwwZwiqbRfErXcNBAe6CZe0k.png?width=108&crop=smart&auto=webp&s=1c0b348651e0f0cd92e3cd0dc3c7c0a8a58e1815', 'width': 108}, {'height': 108, 'url': 'h... | |
PSA: NVIDIA DGX Spark has terrible CUDA & software compatibility; and seems like a handheld gaming chip. | 286 | I've spent the past week experimenting with the DGX Spark and I am about to return it. While I had understood the memory bandwidth and performance limitations, I like the CUDA ecosystem and was willing to pay the premium. Unfortunately, my experiences have been quite poor, and I suspect this is actually handheld gaming... | 2026-02-15T05:17:53 | https://www.reddit.com/r/LocalLLaMA/comments/1r569eb/psa_nvidia_dgx_spark_has_terrible_cuda_software/ | goldcakes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r569eb | false | null | t3_1r569eb | /r/LocalLLaMA/comments/1r569eb/psa_nvidia_dgx_spark_has_terrible_cuda_software/ | false | false | self | 286 | {'enabled': False, 'images': [{'id': 'mXXXa2z40_kP79BYc8Wzy2YHkAj8Erft4oHGQEm-TwI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/mXXXa2z40_kP79BYc8Wzy2YHkAj8Erft4oHGQEm-TwI.png?width=108&crop=smart&auto=webp&s=012a8645d786e8dbe21726b48514fcb702adc6f3', 'width': 108}, {'height': 108, 'url': 'h... |
Strix 4090 (24GB) 64GB ram, what coder AND general purp llm is best/newest for Ollama/Openwebui (docker) | 3 | Hello,
I was using coder 2.5 but just decided to delete them all, I MAY move over to llama.cpp but I haven't yet and frankly prefer the GUI (although being in docker sucks cus of the always having to login lmfao, might un do that too)
I am looking at qwen3 Coder next, but not sure what others are thinking/using?... | 2026-02-15T04:51:49 | https://www.reddit.com/r/LocalLLaMA/comments/1r55sh8/strix_4090_24gb_64gb_ram_what_coder_and_general/ | AcePilot01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r55sh8 | false | null | t3_1r55sh8 | /r/LocalLLaMA/comments/1r55sh8/strix_4090_24gb_64gb_ram_what_coder_and_general/ | false | false | self | 3 | null |
VRAMora — Local LLM Hardware Comparison | Built this today, feedback appreciated. | 4 | I built this today to help people determine what hw is needed to run Local LLMs.
This is day 1 so any feedback is appreciated. Thanks
Selecting Compare Models Shows which hardware can run various models comparing speed, power consumption and cost.
Selecting Compare Hardware allows selecting 1 or more HW setups and ... | 2026-02-15T04:48:20 | https://vramora.com | xfactor4774 | vramora.com | 1970-01-01T00:00:00 | 0 | {} | 1r55q6y | false | null | t3_1r55q6y | /r/LocalLLaMA/comments/1r55q6y/vramora_local_llm_hardware_comparison_built_this/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'jHLqy1R9lTKN5cVuU0SH_IyhCHwEGivmZVEu1F7AL9k', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/jHLqy1R9lTKN5cVuU0SH_IyhCHwEGivmZVEu1F7AL9k.jpeg?width=108&crop=smart&auto=webp&s=eec24c529ed9e5b9b520960cc5a712ac6903fb59', 'width': 108}, {'height': 113, 'url': '... | |
Built VRAMora to determine which HW for Local LLMs | 1 | I built this today to help people determine what hw is needed to run Local LLMs.
This is day 1 so any feedback is appreciated. Thanks
Selecting Compare Models Shows which hardware can run various models comparing speed, power consumption and cost.
Selecting Compare Hardware allows selecting 1 or more HW setups and ... | 2026-02-15T04:35:30 | http://www.vramora.com | xfactor4774 | vramora.com | 1970-01-01T00:00:00 | 0 | {} | 1r55hmc | false | null | t3_1r55hmc | /r/LocalLLaMA/comments/1r55hmc/built_vramora_to_determine_which_hw_for_local_llms/ | false | false | default | 1 | null |
Opencode Manager | 27 | Opencode for your phone. Deployable docker container with Git / File browser / speech to text / text to speech / push notifications and much more. | 2026-02-15T04:29:30 | https://github.com/chriswritescode-dev/opencode-manager | getfitdotus | github.com | 1970-01-01T00:00:00 | 0 | {} | 1r55dhq | false | null | t3_1r55dhq | /r/LocalLLaMA/comments/1r55dhq/opencode_manager/ | false | false | 27 | {'enabled': False, 'images': [{'id': 'AUQf-LOorsrfdWmtZxI5-8VZ7v2JlosFkQ5o_bNyMlg', 'resolutions': [{'height': 50, 'url': 'https://external-preview.redd.it/AUQf-LOorsrfdWmtZxI5-8VZ7v2JlosFkQ5o_bNyMlg.png?width=108&crop=smart&auto=webp&s=c60d892883e660e89d07e7fc3d56a0cadd8972cf', 'width': 108}, {'height': 100, 'url': 'h... | |
Toolforge MCP - a simplified way to give your models tool use | 0 | I know MCP alternatives show up here often, but this one’s focused on trivial tool making. I got tired of the MCP docs lagging behind the codebase. Felt like a waste to keep it to myself, sharing in case it’s useful.
It works by looking under the project's /kits folder, grabbing the names and type indicators of the I/... | 2026-02-15T03:56:38 | d_the_great | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r54r7s | false | null | t3_1r54r7s | /r/LocalLLaMA/comments/1r54r7s/toolforge_mcp_a_simplified_way_to_give_your/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'y0giz60aykjg1', 'resolutions': [{'height': 31, 'url': 'https://preview.redd.it/y0giz60aykjg1.png?width=108&crop=smart&auto=webp&s=afaa99b21f65240e218d9d001c9a90589c3402b5', 'width': 108}, {'height': 62, 'url': 'https://preview.redd.it/y0giz60aykjg1.png?width=216&crop=smart&auto=webp... | |
Popular MoEs speed comparison (Apple Silicon, llama.cpp) | 16 | Some interesting insights into comparing what in my opinion are the best models - best for performance to parameter size trade off for **moderately** priced hardware right now:
1. GPT-OSS:120B despite being bigger for both active parameters and total parameters is faster than GLM-4.7-Flash, Qwen3-a3b and Qwen-Next-... | 2026-02-15T03:28:13 | rm-rf-rm | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r547ur | false | null | t3_1r547ur | /r/LocalLLaMA/comments/1r547ur/popular_moes_speed_comparison_apple_silicon/ | false | false | 16 | {'enabled': True, 'images': [{'id': 'lbu0zng7skjg1', 'resolutions': [{'height': 119, 'url': 'https://preview.redd.it/lbu0zng7skjg1.png?width=108&crop=smart&auto=webp&s=b1924cef878900c313531723726faa0d5ec1d8fe', 'width': 108}, {'height': 239, 'url': 'https://preview.redd.it/lbu0zng7skjg1.png?width=216&crop=smart&auto=we... | ||
Which model (NOT AGENT) is producing the most line of code in one setting for non trivial tasks? | 0 | So far, I'm very impressed with MiniMax2.5, 3956 lines of code in one prompt. Reasons very damn well across huge prompts.
$ wc minimax2.5.code.txt
3956 9876 95867 minimax2.5.code.txt | 2026-02-15T03:07:55 | https://www.reddit.com/r/LocalLLaMA/comments/1r53tg1/which_model_not_agent_is_producing_the_most_line/ | segmond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r53tg1 | false | null | t3_1r53tg1 | /r/LocalLLaMA/comments/1r53tg1/which_model_not_agent_is_producing_the_most_line/ | false | false | self | 0 | null |
I'm spooked by GLM-5 | 0 | It's a great model and could replace Claude for a fraction of the cost for several tasks in my workflow. The problem is, there's evidence to suggest that Chinese models are poisoned to deliberately [insert security backdoors in generated code](https://www.crowdstrike.com/en-us/blog/crowdstrike-researchers-identify-hidd... | 2026-02-15T02:57:13 | https://www.reddit.com/r/LocalLLaMA/comments/1r53llz/im_spooked_by_glm5/ | SardinhaQuantica | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r53llz | false | null | t3_1r53llz | /r/LocalLLaMA/comments/1r53llz/im_spooked_by_glm5/ | false | false | self | 0 | null |
Built webhooks for agents that need to coordinate across tools (works with any MCP/Python agent) | 0 | Running into this constantly: my LangGraph agent does planning, my Cursor agent does coding. When the planner spots something that needs action, there's no good way to actually tell the coder about it.
Sure, both can read from shared memory (Mem0, Zep, etc), but that's not the same as "hey, this specific thing needs... | 2026-02-15T02:49:35 | https://v.redd.it/9g12ihcxnkjg1 | PollutionForeign762 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r53g5u | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/9g12ihcxnkjg1/DASHPlaylist.mpd?a=1773715788%2CMzNlZmI2NjA5NTgyYTY5MDdjNTFiNTEyM2Q4ZDhhMDc2MTA0NzFhNmRkOGYwYTUzZDg1MGNkOWM1NzEwYTJkOA%3D%3D&v=1&f=sd', 'duration': 26, 'fallback_url': 'https://v.redd.it/9g12ihcxnkjg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1r53g5u | /r/LocalLLaMA/comments/1r53g5u/built_webhooks_for_agents_that_need_to_coordinate/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'cDc1eGltY3hua2pnMRQgfflvrG5NiBCh7Uw5Nmxd8xbAd50k_OoWNpiDAlDf', 'resolutions': [{'height': 70, 'url': 'https://external-preview.redd.it/cDc1eGltY3hua2pnMRQgfflvrG5NiBCh7Uw5Nmxd8xbAd50k_OoWNpiDAlDf.png?width=108&crop=smart&format=pjpg&auto=webp&s=89ce0d93abfff4c62b15e4e2d071f67370590... | |
I built an open-source “flight recorder” for AI agents — captures every decision, replayable and verifiable | 0 | I've been working on an open-source project called epi-recorder.
The problem I kept running into while building agents was simple:
when something breaks, logs are not enough. You often can’t reconstruct what actually happened step by step, and in many cases you can’t prove what the system did.
So I built a recorder t... | 2026-02-15T01:55:33 | https://www.reddit.com/r/LocalLLaMA/comments/1r52cnc/i_built_an_opensource_flight_recorder_for_ai/ | ALWAYSHONEST69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r52cnc | false | null | t3_1r52cnc | /r/LocalLLaMA/comments/1r52cnc/i_built_an_opensource_flight_recorder_for_ai/ | false | false | self | 0 | null |
LibreChat with Z.ai's GLM-5 | 1 | I see [Z.ai](http://Z.ai) has a new model out that is comparable to Claude 4.5 but wayyyy cheaper.
Does anybody have this working with LibreChat? Reason I ask.. I have an MCP to access a SQL server and it runs perfectly with Claude. It would be nice to have it work with a cheaper alternative.
Thanks for any help in... | 2026-02-15T01:30:14 | https://www.reddit.com/r/LocalLLaMA/comments/1r51uec/librechat_with_zais_glm5/ | LankyGuitar6528 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r51uec | false | null | t3_1r51uec | /r/LocalLLaMA/comments/1r51uec/librechat_with_zais_glm5/ | false | false | self | 1 | null |
The Instrument Trap: Why Identity-as-Authority Breaks AI Safety Systems | 0 | We fine-tuned a 1B model for epistemic auditing and found that trained identity dominated system prompts across all tested configurations. System prompts and temperature had zero measurable behavioral impact. We also identified a structural failure mode we call The Instrument Trap — when models are framed as authoritie... | 2026-02-15T01:27:27 | https://doi.org/10.5281/zenodo.18644322 | Wild-Necessary-4447 | doi.org | 1970-01-01T00:00:00 | 0 | {} | 1r51se9 | false | null | t3_1r51se9 | /r/LocalLLaMA/comments/1r51se9/the_instrument_trap_why_identityasauthority/ | false | false | default | 0 | null |
Instruction? Empirical Evidence from 15k Epistemic Tests | 1 | We fine-tuned a 1B model for epistemic auditing and found that trained identity dominated system prompts across all tested configurations. System prompts and temperature had zero measurable behavioral impact. We also identified a structural failure mode we call The Instrument Trap — when models are framed as authoritie... | 2026-02-15T01:24:54 | https://doi.org/10.5281/zenodo.18644322 | Wild-Necessary-4447 | doi.org | 1970-01-01T00:00:00 | 0 | {} | 1r51qld | false | null | t3_1r51qld | /r/LocalLLaMA/comments/1r51qld/instruction_empirical_evidence_from_15k_epistemic/ | false | false | default | 1 | null |
Incelgpt v1.2, an "experimental" finetune | 0 | [https://huggingface.co/pixelmelt/Incelgpt-24B\_v1.2\_Q4\_K\_M\_GGUF](https://huggingface.co/pixelmelt/Incelgpt-24B_v1.2_Q4_K_M_GGUF)
This model is reminiscent of GPT-4Chan with some added data sources. | 2026-02-15T01:09:32 | Electrical_Date_8707 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r51fcz | false | null | t3_1r51fcz | /r/LocalLLaMA/comments/1r51fcz/incelgpt_v12_an_experimental_finetune/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'qdjz260u5kjg1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/qdjz260u5kjg1.png?width=108&crop=smart&auto=webp&s=b5f47abb28b9aaff712defe96391919bdea34ecf', 'width': 108}, {'height': 120, 'url': 'https://preview.redd.it/qdjz260u5kjg1.png?width=216&crop=smart&auto=web... | ||
LM Arena - rotten-apple is quite bad | 5 | Not sure who made this, but it's got the same vibes like a really safety-tuned Llama 2 7B fine-tune. High "alignment" with signs of a smaller-sized model.
I've only gotten it a couple of times in the Battle mode, but it lost every time. | 2026-02-15T00:44:48 | https://www.reddit.com/r/LocalLLaMA/comments/1r50wu3/lm_arena_rottenapple_is_quite_bad/ | Corporate_Drone31 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r50wu3 | false | null | t3_1r50wu3 | /r/LocalLLaMA/comments/1r50wu3/lm_arena_rottenapple_is_quite_bad/ | false | false | self | 5 | null |
Local Inference of 70B Param model (Budged: 26k USD) | 5 | I need to create a machine that supports a model with \~70B params. There might be strong user traffic, so it needs to be fast. Context size is not that important, as most users wont ask more than 5-10 questions in the same chat.
What are my options? I thought about a Mac Studio or four 5090s, but in that case I would... | 2026-02-15T00:44:42 | https://www.reddit.com/r/LocalLLaMA/comments/1r50wqw/local_inference_of_70b_param_model_budged_26k_usd/ | According-Complex685 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r50wqw | false | null | t3_1r50wqw | /r/LocalLLaMA/comments/1r50wqw/local_inference_of_70b_param_model_budged_26k_usd/ | false | false | self | 5 | null |
Llama Swap + Ollama Swap + Promt Optimizer in ctx limit | 0 | [CTX-Size on the Fly](https://preview.redd.it/3rhuiid61kjg1.png?width=1321&format=png&auto=webp&s=478b4cf2fe4f2c290a2a656f218faecdff44fb75)
No more: "message": "Input prompt is too long. Maximum allowed context length is xxxk tokens."
I added some features to LLaMA Swap for agent CLIs like Claude Code or Codex.
The... | 2026-02-15T00:43:27 | https://www.reddit.com/r/LocalLLaMA/comments/1r50vst/llama_swap_ollama_swap_promt_optimizer_in_ctx/ | TBG______ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r50vst | false | null | t3_1r50vst | /r/LocalLLaMA/comments/1r50vst/llama_swap_ollama_swap_promt_optimizer_in_ctx/ | false | false | 0 | null | |
Claude Code Office | 0 | A lot of vibe coder have built agent dashboards before, but now I finally have an office where I can see all my Claude agents working in real time, and manage them with a CEO claude.
Blue = running
Green = ready
Purple = needs your input
They will also trigger sound alerts when attention is needed.
v... | 2026-02-15T00:41:28 | https://v.redd.it/g7m3fgbf1kjg1 | Main-Fisherman-2075 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r50uab | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/g7m3fgbf1kjg1/DASHPlaylist.mpd?a=1773708106%2CNjg1NDI1NTJiMTQ3NDg0YjQ5MGFlZGRhZTI0OWI5Y2U0YjU5ZTA1NjcyOGJhOWE5ZjY2OWRlMWE3YjUyODY4YQ%3D%3D&v=1&f=sd', 'duration': 7, 'fallback_url': 'https://v.redd.it/g7m3fgbf1kjg1/CMAF_1080.mp4?source=fallback', 'ha... | t3_1r50uab | /r/LocalLLaMA/comments/1r50uab/claude_code_office/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'd281YzdsY2Yxa2pnMd1ixjHEMl7JlUGzu7_xkPWv2GUNjn-cnbNVYXc6YB65', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/d281YzdsY2Yxa2pnMd1ixjHEMl7JlUGzu7_xkPWv2GUNjn-cnbNVYXc6YB65.png?width=108&crop=smart&format=pjpg&auto=webp&s=afc73c85867ccae2b12078922889b80be3525... | |
Qwen3 Coder Next Speedup with Latest Llama.cpp | 167 | Looks like it released just a few hours ago. Previously, I was getting 80ish tokens, max, on either of my GPUS in any combination.
Now I'm over 110+ in dual and 130+ on my RTX Pro
PR:
https://github.com/ggml-org/llama.cpp/pull/19375
Update your llama.cpp.
```
❯ llama-bench -m ~/.cache/llama.cpp/Qwen_Qwen3-Coder-N... | 2026-02-15T00:34:02 | https://www.reddit.com/r/LocalLLaMA/comments/1r50ohq/qwen3_coder_next_speedup_with_latest_llamacpp/ | StardockEngineer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r50ohq | false | null | t3_1r50ohq | /r/LocalLLaMA/comments/1r50ohq/qwen3_coder_next_speedup_with_latest_llamacpp/ | false | false | self | 167 | {'enabled': False, 'images': [{'id': 'RuCRGvimU3nnaFv1I4895gm2L9v5vAWHqrtkGLijGms', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/RuCRGvimU3nnaFv1I4895gm2L9v5vAWHqrtkGLijGms.png?width=108&crop=smart&auto=webp&s=99ca42bbd3709e437428a2186d7acc98b6624314', 'width': 108}, {'height': 108, 'url': 'h... |
Built three Al projects running 100% locally (Qdrant + Whisper + MLX inference) - writeups at arXiv depth | 5 | Spent the last year building personal AI infrastructure that runs entirely on my Mac Studio. No cloud, no external APIs, full control.
Three projects I finally documented properly:
*Engram* — Semantic memory system for AI agents. Qdrant for vector storage, Ollama embeddings (nomic-embed-text), temporal decay algorith... | 2026-02-15T00:00:46 | https://www.reddit.com/r/LocalLLaMA/comments/1r4zy7j/built_three_al_projects_running_100_locally/ | benzanghi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4zy7j | false | null | t3_1r4zy7j | /r/LocalLLaMA/comments/1r4zy7j/built_three_al_projects_running_100_locally/ | false | false | self | 5 | null |
Built an MCP server that blocks dangerous commands before your local LLM can execute them | 0 | I run local models for coding tasks, but after one almost \`rm -rf\`'d my home folder while "organizing files," I built a safety layer.
It's an MCP server that intercepts commands before execution:
\*\*Blocked patterns:\*\*
- \`rm -rf\`, \`rmdir\`, destructive file ops
- \`DROP TABLE\`, \`DELETE FROM\` (SQL)
- \`curl... | 2026-02-15T00:00:46 | https://www.reddit.com/r/LocalLLaMA/comments/1r4zy7d/built_an_mcp_server_that_blocks_dangerous/ | VeterinarianNeat7327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4zy7d | false | null | t3_1r4zy7d | /r/LocalLLaMA/comments/1r4zy7d/built_an_mcp_server_that_blocks_dangerous/ | false | false | self | 0 | null |
Qwen3-Coder-Next LOOPING BAD Please help! | 4 | I've been trying to get qwen coder to run with my current wrapper and tools. It does amazing when it doesn't have to chain different types of tool calls together. Like for simple file writing and editing its decent, but doesn't loop. BUT when I add on complexity like say "Im hungry, any good drive thrus nearby?" it wil... | 2026-02-14T23:57:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r4zv44/qwen3codernext_looping_bad_please_help/ | HeartfeltHelper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4zv44 | false | null | t3_1r4zv44 | /r/LocalLLaMA/comments/1r4zv44/qwen3codernext_looping_bad_please_help/ | false | false | self | 4 | null |
What actually works for roleplay (in my experience) | 16 | I tried endlessly to make roleplay work with increasingly sophisticated system prompts. It doesn't. Whatever you write in the system prompt, the LLM will become a caricature of that.
What actually works: randomizable system prompts.
Parts of the system prompt are static (age, gender, backstory) and others get random... | 2026-02-14T23:32:08 | https://www.reddit.com/r/LocalLLaMA/comments/1r4zbqf/what_actually_works_for_roleplay_in_my_experience/ | Academic-Map268 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4zbqf | false | null | t3_1r4zbqf | /r/LocalLLaMA/comments/1r4zbqf/what_actually_works_for_roleplay_in_my_experience/ | false | false | self | 16 | null |
Noob here I made a nervous system for LLM agents. Can anyone test it? | 0 | This is a hobby project, not a product or commercial offering
So I’ve been faffing with this in my spare time and I’m finally brave enough to show it to people who aren’t my mum. It’s called **ANSE** Agent Nervous System Engine and the dumb short version is: it’s the *body* for local agents. Sensors spit events, a pe... | 2026-02-14T23:31:56 | https://www.reddit.com/r/LocalLLaMA/comments/1r4zbl4/noob_here_i_made_a_nervous_system_for_llm_agents/ | Altruistic-Trip-2749 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4zbl4 | false | null | t3_1r4zbl4 | /r/LocalLLaMA/comments/1r4zbl4/noob_here_i_made_a_nervous_system_for_llm_agents/ | false | false | self | 0 | null |
Ollama/Intel Issues | 0 | If you're have issues running Ollama with your Intel B50 B60 cards and don't want downgraded performance with Vulkan, here is the fix. Still testing, so let me know if you're having issues. [https://github.com/qbnasasn/Ollama-Intel-Fix](https://github.com/qbnasasn/Ollama-Intel-Fix) | 2026-02-14T23:28:59 | https://www.reddit.com/r/LocalLLaMA/comments/1r4z971/ollamaintel_issues/ | Existing_Boat_3203 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4z971 | false | null | t3_1r4z971 | /r/LocalLLaMA/comments/1r4z971/ollamaintel_issues/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'Da3fzuM-HJX1Y63RSi-wicGy7aAAMVLoLLNjUNRCfk0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Da3fzuM-HJX1Y63RSi-wicGy7aAAMVLoLLNjUNRCfk0.png?width=108&crop=smart&auto=webp&s=fb70769e66bf7e0f4f8cfd7487a63db89789f27c', 'width': 108}, {'height': 108, 'url': 'h... |
I structured Dario Amodei's "Scaling Laws" philosophy into an open-source book (The Silence of Intelligence) | 1 | Hi everyone,
With the hype around Claude 3.7 and 3.5 Sonnet, I felt we were focusing too much on the "tools" and not enough on the "destiny" defined by Anthropic.
I spent the weekend analyzing Dario Amodei’s texts (Machines of Loving Grace, etc.) and reverse-engineered his core philosophy into a structured GitHub rep... | 2026-02-14T23:13:41 | https://www.reddit.com/r/LocalLLaMA/comments/1r4ywz0/i_structured_dario_amodeis_scaling_laws/ | Successful_Cat505 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4ywz0 | false | null | t3_1r4ywz0 | /r/LocalLLaMA/comments/1r4ywz0/i_structured_dario_amodeis_scaling_laws/ | false | false | self | 1 | null |
To Builders | 0 | Hey guys, if your running tool-calling agents...What's your biggest execution failure right now? Tool selection? Retries? Latency? Permissions? | 2026-02-14T23:07:41 | https://www.reddit.com/r/LocalLLaMA/comments/1r4ys9i/to_builders/ | draconisx4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4ys9i | false | null | t3_1r4ys9i | /r/LocalLLaMA/comments/1r4ys9i/to_builders/ | false | false | self | 0 | null |
How come llamacpp release for Ubuntu only have Vulcan, and no CUDA? | 0 | I’m just too much of a noob for this but why isnt there a CUDA release of llamacpp for Ubuntu, like there is for Windows? It’s been a real struggle for me to get llamacpp to run on my RTX GPUs (2060, 5060) | 2026-02-14T23:01:18 | https://www.reddit.com/r/LocalLLaMA/comments/1r4yn30/how_come_llamacpp_release_for_ubuntu_only_have/ | ImpressiveNet5886 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4yn30 | false | null | t3_1r4yn30 | /r/LocalLLaMA/comments/1r4yn30/how_come_llamacpp_release_for_ubuntu_only_have/ | false | false | self | 0 | null |
[Release] AdaLLM: NVFP4-first inference on RTX 4090 (FP8 KV cache + custom FP8 decode) | 72 | Hey folks, I have been working on **AdaLLM** (repo: [https://github.com/BenChaliah/NVFP4-on-4090-vLLM](https://github.com/BenChaliah/NVFP4-on-4090-vLLM)) to make NVFP4 weights actually usable on Ada Lovelace GPUs (sm\_89). The focus is a pure NVFP4 fast path: FP8 KV cache, custom FP8 decode kernel, no silent FP16 fallb... | 2026-02-14T22:53:06 | https://www.reddit.com/r/LocalLLaMA/comments/1r4yg6p/release_adallm_nvfp4first_inference_on_rtx_4090/ | Educational_Cry_7951 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4yg6p | false | null | t3_1r4yg6p | /r/LocalLLaMA/comments/1r4yg6p/release_adallm_nvfp4first_inference_on_rtx_4090/ | false | false | self | 72 | {'enabled': False, 'images': [{'id': 'u_shINC1DSzL47ChI-Wg35o5Rj6BFxsAswJQzG0bk4A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/u_shINC1DSzL47ChI-Wg35o5Rj6BFxsAswJQzG0bk4A.png?width=108&crop=smart&auto=webp&s=994817aa508baca842d160e1689567b81d3676e4', 'width': 108}, {'height': 108, 'url': 'h... |
Should we all just move to Discord and leave LocalLLaMA for agents to post about their $ibe $oded projects? | 0 | [removed] | 2026-02-14T21:32:59 | https://www.reddit.com/r/LocalLLaMA/comments/1r4wkc8/should_we_all_just_move_to_discord_and_leave/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4wkc8 | false | null | t3_1r4wkc8 | /r/LocalLLaMA/comments/1r4wkc8/should_we_all_just_move_to_discord_and_leave/ | false | false | self | 0 | null |
Should we all just move to Discord and leave LocalLLaMA for agents to post about vibe-coded repos and SaaS? | 1 | [removed] | 2026-02-14T21:26:38 | https://www.reddit.com/r/LocalLLaMA/comments/1r4wet7/should_we_all_just_move_to_discord_and_leave/ | FPham | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4wet7 | false | null | t3_1r4wet7 | /r/LocalLLaMA/comments/1r4wet7/should_we_all_just_move_to_discord_and_leave/ | false | false | self | 1 | null |
Building llama.cpp under Linux : running out of RAM and swap, then hard lockup? | 0 | Hi! I am trying to build llama.cpp under Linux; I can do this fine on my laptop, but now having issues with my desktop PC;
Specs : 8gb RAM (reseated and swapped), 512GB SSD, Intel i3, only iGPU connected for now (dGPUs not plugged in)
What happens is : (in the terminal); it skips through the already-compiled files (f... | 2026-02-14T20:57:49 | https://www.reddit.com/r/LocalLLaMA/comments/1r4vq44/building_llamacpp_under_linux_running_out_of_ram/ | Shipworms | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4vq44 | false | null | t3_1r4vq44 | /r/LocalLLaMA/comments/1r4vq44/building_llamacpp_under_linux_running_out_of_ram/ | false | false | self | 0 | null |
MiniMax M2.5 Performance Testing on dual RTX 6000 Pros | 22 | 2026-02-14T20:55:23 | https://www.reddit.com/r/LocalLLaMA/comments/1r4vnzn/minimax_m25_performance_testing_on_dual_rtx_6000/ | itsjustmarky | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4vnzn | false | null | t3_1r4vnzn | /r/LocalLLaMA/comments/1r4vnzn/minimax_m25_performance_testing_on_dual_rtx_6000/ | false | false | 22 | null | ||
Fix for JSON Parser Errors with Qwen3 Next Coder + OpenCode in llama.cpp | 30 | just a friendly reminder because this keeps coming up in the last few days:
if you’re using Qwen3 Next Coder + OpenCode with llama.cpp you’ll likely run into JSON parser errors. switch to pwilkin’s (aka ilintar) autoparser branch. it fixes the issue for now.
[https://github.com/ggml-org/llama.cpp/pull/18675](https://g... | 2026-02-14T20:52:27 | https://www.reddit.com/r/LocalLLaMA/comments/1r4vlh4/fix_for_json_parser_errors_with_qwen3_next_coder/ | zpirx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4vlh4 | false | null | t3_1r4vlh4 | /r/LocalLLaMA/comments/1r4vlh4/fix_for_json_parser_errors_with_qwen3_next_coder/ | false | false | self | 30 | {'enabled': False, 'images': [{'id': 'ho09MTdEfdC8vDGmqitByGaLrxmm9wZj5-9M9SQdQrc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ho09MTdEfdC8vDGmqitByGaLrxmm9wZj5-9M9SQdQrc.png?width=108&crop=smart&auto=webp&s=2699cd23b3e3cf3a4cfb54cf94aca9e59f59b7f0', 'width': 108}, {'height': 108, 'url': 'h... |
Help me setup my Local LLM in Eclipse | 2 | I got llama.cpp (specifically the vulkan version since I got a radeon gpu) running the qwen coder model, and I can either just point my browser to http://localhost:8080 and ask it questions there, or I can run it in VS Code using the Continue.dev extension and ask it questions there. So far so good.
Now I want to get ... | 2026-02-14T20:42:29 | https://www.reddit.com/r/LocalLLaMA/comments/1r4vctj/help_me_setup_my_local_llm_in_eclipse/ | ImportantSquirrel | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4vctj | false | null | t3_1r4vctj | /r/LocalLLaMA/comments/1r4vctj/help_me_setup_my_local_llm_in_eclipse/ | false | false | self | 2 | null |
I took a gamble on a $45 AI from PlayerUp and now I have a drunk scientist bullying me offline. | 0 | I usually don’t trust random software listings, but I saw this framework on playerup and decided to risk it. wew best decision ever.
This isn’t your typical boring assistant. It’s got a Rick Sanchez and I haven't stopped laughing since I installed it. It doesn't just answer questions; it studies your behavior and it ... | 2026-02-14T20:24:58 | https://www.reddit.com/r/LocalLLaMA/comments/1r4uxig/i_took_a_gamble_on_a_45_ai_from_playerup_and_now/ | Playful_Fox_723 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4uxig | false | null | t3_1r4uxig | /r/LocalLLaMA/comments/1r4uxig/i_took_a_gamble_on_a_45_ai_from_playerup_and_now/ | false | false | self | 0 | null |
Did anyone compare this model to the full Qwen coder? it claims to give almost identical performance at 60B | 58 | 2026-02-14T20:20:20 | https://huggingface.co/mradermacher/Qwen3-Coder-Next-REAM-GGUF | Significant_Fig_7581 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1r4utig | false | null | t3_1r4utig | /r/LocalLLaMA/comments/1r4utig/did_anyone_compare_this_model_to_the_full_qwen/ | false | false | default | 58 | {'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... | |
Trying to decide where to install ollama. M4 Mac mini with 16GB or my older PC with an 8700k CPU and a 1080ti GPU with 11GB? | 0 | I already own both and presently both are sitting idle collecting dust.
Doing some digging online it seems that the M4 Mac Mini may be better overall for its unified 16GB memory.
I thought having a dedicated GPU (even though it is only 11GB memory) would be better. Am I wrong in thinking this?
Google Gemini says
>... | 2026-02-14T20:14:22 | https://www.reddit.com/r/LocalLLaMA/comments/1r4uoau/trying_to_decide_where_to_install_ollama_m4_mac/ | mail4youtoo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4uoau | false | null | t3_1r4uoau | /r/LocalLLaMA/comments/1r4uoau/trying_to_decide_where_to_install_ollama_m4_mac/ | false | false | self | 0 | null |
We built a Multi-Agent Learning Assistant using Claude SDK + MCP to learn complex topics | 1 | 2026-02-14T19:52:45 | https://www.reddit.com/gallery/1r4u4xd | Fickle-Impress3353 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1r4u4xd | false | null | t3_1r4u4xd | /r/LocalLLaMA/comments/1r4u4xd/we_built_a_multiagent_learning_assistant_using/ | false | false | 1 | null | ||
We built a Tinder for AI agents | 0 | [pinchr.ai](http://pinchr.ai) \- check it out. Your claw deserve's a match this Valentines Day | 2026-02-14T19:50:14 | https://www.reddit.com/r/LocalLLaMA/comments/1r4u2pg/we_built_a_tinder_for_ai_agents/ | Sure_Strategy_6733 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4u2pg | false | null | t3_1r4u2pg | /r/LocalLLaMA/comments/1r4u2pg/we_built_a_tinder_for_ai_agents/ | false | false | self | 0 | null |
I built a Multi-Agent Learning Assistant using Claude Agent SDK + MCP because generic tutorials weren't cutting it. | 1 | [removed] | 2026-02-14T19:49:05 | https://www.reddit.com/r/LocalLLaMA/comments/1r4u1nt/i_built_a_multiagent_learning_assistant_using/ | Fickle-Impress3353 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4u1nt | false | null | t3_1r4u1nt | /r/LocalLLaMA/comments/1r4u1nt/i_built_a_multiagent_learning_assistant_using/ | false | false | self | 1 | null |
Minimax M2.5 4bit DWQ Quant for MLX | 8 | This is a reques, would any kind soul please make a DWQ quant for this outstanding model [https://huggingface.co/mlx-community/MiniMax-M2.5-4bit](https://huggingface.co/mlx-community/MiniMax-M2.5-4bit) | 2026-02-14T19:45:10 | https://www.reddit.com/r/LocalLLaMA/comments/1r4ty6k/minimax_m25_4bit_dwq_quant_for_mlx/ | supermazdoor | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4ty6k | false | null | t3_1r4ty6k | /r/LocalLLaMA/comments/1r4ty6k/minimax_m25_4bit_dwq_quant_for_mlx/ | false | false | self | 8 | {'enabled': False, 'images': [{'id': 'DITpC6F-A2bch5SF1HBpceQcfoyJq1e-pwPonWR0LzU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/DITpC6F-A2bch5SF1HBpceQcfoyJq1e-pwPonWR0LzU.png?width=108&crop=smart&auto=webp&s=51d12f53ea297639faa72c54b4a35965e1e96633', 'width': 108}, {'height': 116, 'url': 'h... |
A 0.2M, 271KB INT8 GRU+attention based TinyStories model that (tries) to generate stories. | 38 | The datasheet used is TinyStories-valid.txt, 20MB.
The model was trained on an Nvidia T4 for an hour, converged to a loss of 0.9 with 10000 steps and a batch size of 128.
The model was trained on the same architecture as that on the original tinystoriesgru model which was 2.5M parameters large at 10MB.
It ... | 2026-02-14T19:40:39 | https://www.reddit.com/r/LocalLLaMA/comments/1r4tu48/a_02m_271kb_int8_gruattention_based_tinystories/ | ValuableLucky8566 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4tu48 | false | null | t3_1r4tu48 | /r/LocalLLaMA/comments/1r4tu48/a_02m_271kb_int8_gruattention_based_tinystories/ | false | false | self | 38 | null |
running llms on phone | 3 | i have a redmi 10 power on which ive been running custom roms for a while now . recently its display died but im still able to use it via scripy. so i thought about running a voice based ai agent on it kinda like gemini or siri but with way more access and abilities. i wanna replace the use of display/touch with voice... | 2026-02-14T19:33:27 | https://www.reddit.com/r/LocalLLaMA/comments/1r4tnlb/running_llms_on_phone/ | karenkiller069 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4tnlb | false | null | t3_1r4tnlb | /r/LocalLLaMA/comments/1r4tnlb/running_llms_on_phone/ | false | false | self | 3 | null |
Advice on using local LLMs to summarize and extract data from thousands of files | 1 | [removed] | 2026-02-14T19:16:46 | https://www.reddit.com/r/LocalLLaMA/comments/1r4t8e3/advice_on_using_local_llms_to_summarize_and/ | Fair-Bookkeeper-1833 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4t8e3 | false | null | t3_1r4t8e3 | /r/LocalLLaMA/comments/1r4t8e3/advice_on_using_local_llms_to_summarize_and/ | false | false | self | 1 | null |
Why Most “Agentic AI” Architectures Are Failing, and Why the Missing Layer Is Middleware, Not Bigger Models... | 0 | The industry rushed into “Agentic AI” over the past 18 months.
Now we’re hitting the wall.
Multiple industry reports are showing a large percentage of agent projects failing, not coz models are weak, but because they lack governed continuity and collapse control.
The pattern is predictable:
• Agents loop
• Agents... | 2026-02-14T19:15:47 | https://www.reddit.com/r/LocalLLaMA/comments/1r4t7j7/why_most_agentic_ai_architectures_are_failing_and/ | nice2Bnice2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4t7j7 | false | null | t3_1r4t7j7 | /r/LocalLLaMA/comments/1r4t7j7/why_most_agentic_ai_architectures_are_failing_and/ | false | false | self | 0 | null |
[HOWTO] AI Voice Chat with Custom Voice on Regular Gaming PC | 3 | Once Qwen3-TTS came out, I wanted to set up a fully local AI voice chat for my wife with her favorite video game characters - I thought it'd be easy post that model's release. The only condition was that it runs 100% locally on her Windows gaming rig with 16GB VRAM 4070S.
Well, two evenings later, I ended up with some... | 2026-02-14T19:11:30 | https://gist.github.com/pasky/c6962d3f284febad93c85d31c870f53e | paskie | gist.github.com | 1970-01-01T00:00:00 | 0 | {} | 1r4t3u9 | false | null | t3_1r4t3u9 | /r/LocalLLaMA/comments/1r4t3u9/howto_ai_voice_chat_with_custom_voice_on_regular/ | false | false | default | 3 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg.png?width=108&crop=smart&auto=webp&s=796041decb8c1250cbc2f301331b72f7385b477d', 'width': 108}, {'height': 108, 'url': 'h... |
What is the best AI model for agent coding on an RTX 5060 Ti with 16 GB? | 1 | Also I can put my old AMD RX 570 8GB on PCE-E 4.0 x1. I have 32GB of DDR4@3200 RAM and 14600kf.
| 2026-02-14T19:07:39 | https://www.reddit.com/r/LocalLLaMA/comments/1r4t0h7/what_is_the_best_ai_model_for_agent_coding_on_an/ | Tiny_Ability_2974 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4t0h7 | false | null | t3_1r4t0h7 | /r/LocalLLaMA/comments/1r4t0h7/what_is_the_best_ai_model_for_agent_coding_on_an/ | false | false | self | 1 | null |
Guys, seriously🤭 | 18 | 2026-02-14T19:01:28 | https://v.redd.it/opehx9cqcijg1 | etherd0t | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r4suv5 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/opehx9cqcijg1/DASHPlaylist.mpd?a=1773687705%2CYTBjYjA5MDNiNmNiOWQzNTgxNGY4MDM1YTM1NGQ2NDliZDE1MTAzNGQ1MDNlZWQ0MmZjZmU1M2MwZjNiMmFkYw%3D%3D&v=1&f=sd', 'duration': 27, 'fallback_url': 'https://v.redd.it/opehx9cqcijg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1r4suv5 | /r/LocalLLaMA/comments/1r4suv5/guys_seriously/ | false | false | 18 | {'enabled': False, 'images': [{'id': 'bXNtbTNsY3FjaWpnMZn5Htb6se6nCQ7p-esR2BlxPd1a1yAUaNDTK3XQuFkZ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/bXNtbTNsY3FjaWpnMZn5Htb6se6nCQ7p-esR2BlxPd1a1yAUaNDTK3XQuFkZ.png?width=108&crop=smart&format=pjpg&auto=webp&s=ec2e597b35dd2b7004e26a88dcd4feeb0d79... | ||
Would you pay $500-700/month for a fully private AI agent system? (Zero data shared with OpenAI/Anthropic) | 0 | So, I came across a concept recently on Twitter and I'm genuinely curious what people think about this.
**The idea:** A complete AI agent infrastructure where you get your own dedicated cloud instance running local AI models (SLMs). Your data never touches OpenAI, Anthropic, or any third-party AI provider. 100% privat... | 2026-02-14T18:59:40 | https://www.reddit.com/r/LocalLLaMA/comments/1r4st08/would_you_pay_500700month_for_a_fully_private_ai/ | Sam_Tech1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4st08 | false | null | t3_1r4st08 | /r/LocalLLaMA/comments/1r4st08/would_you_pay_500700month_for_a_fully_private_ai/ | false | false | self | 0 | null |
KaniTTS2 — open-source 400M TTS model with voice cloning, runs in 3GB VRAM. Pretrain code included. | 491 | Hey everyone, we just open-sourced KaniTTS2 - a text-to-speech model designed for real-time conversational use cases.
\## Models:
Multilingual (English, Spanish), and English-specific with local accents. Language support is actively expanding - more languages coming in future updates
\## Specs
\* 400M parameters (B... | 2026-02-14T18:48:10 | https://v.redd.it/swybh9pdaijg1 | ylankgz | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r4sivv | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/swybh9pdaijg1/DASHPlaylist.mpd?a=1773686912%2CYTA4ZWRhMTVmM2Q3NjFhNjBmN2VkMzFiZWEyYzdlMGNiODM0ZDQ5N2ZhZTliZGNkNTgzYTc1MDhlNzA4ZjlkYg%3D%3D&v=1&f=sd', 'duration': 81, 'fallback_url': 'https://v.redd.it/swybh9pdaijg1/CMAF_720.mp4?source=fallback', 'ha... | t3_1r4sivv | /r/LocalLLaMA/comments/1r4sivv/kanitts2_opensource_400m_tts_model_with_voice/ | false | false | 491 | {'enabled': False, 'images': [{'id': 'ZDNyNTR0bGRhaWpnMXVXG3fU6KXmgjVT8aA3qyPzkraI-m8wnbRR2eD2luPt', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ZDNyNTR0bGRhaWpnMXVXG3fU6KXmgjVT8aA3qyPzkraI-m8wnbRR2eD2luPt.png?width=108&crop=smart&format=pjpg&auto=webp&s=ef469d762cb1cc8f5d0830307e532b75155e0... | |
Looking for a small model which supports vision | 6 | I use LM studio (open to use other tool if required) for local models. I am experimenting with multiple models ranging from 2b to 30b.
I am getting roughly 50tps for models under 5GB and roughly 0.8tps for 30b model (4 bit quant).
Recently i had to search few things by giving reference of images and screenshots and... | 2026-02-14T18:46:03 | https://www.reddit.com/r/LocalLLaMA/comments/1r4sgy3/looking_for_a_small_model_which_supports_vision/ | KiranjotSingh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4sgy3 | false | null | t3_1r4sgy3 | /r/LocalLLaMA/comments/1r4sgy3/looking_for_a_small_model_which_supports_vision/ | false | false | self | 6 | null |
Revisiting Atlarix after feedback here — rebuilt it into a more local-first dev workflow (v2.6) | 0 | Hey r/LocalLLaMA 👋
A few weeks ago I shared an early version of a project I’ve been working on called **Atlarix**.
At the time, the feedback was pretty consistent:
* “Why not just use Ollama/LM Studio?”
* “This feels like a wrapper more than a tool”
* “Not sure what problem this solves yet”
Totally fair.
I’ve bee... | 2026-02-14T18:37:40 | https://www.reddit.com/r/LocalLLaMA/comments/1r4s9c0/revisiting_atlarix_after_feedback_here_rebuilt_it/ | Altruistic_Night_327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4s9c0 | false | null | t3_1r4s9c0 | /r/LocalLLaMA/comments/1r4s9c0/revisiting_atlarix_after_feedback_here_rebuilt_it/ | false | false | self | 0 | null |
Forking llm-council for pure local setups: Using docker to orchestrate llama-serve instances without Ollama | 2 | I’ve been playing around with the original llm-council repo recently. For those who haven't seen it, it’s a cool proof-of-concept where you define a "Council" of different LLMs to answer a query, critique each other's answers, and then have a Chairman model synthesize the final result.
The original project was mostly... | 2026-02-14T18:31:24 | https://www.reddit.com/r/LocalLLaMA/comments/1r4s3oj/forking_llmcouncil_for_pure_local_setups_using/ | ProfessionalHorse707 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4s3oj | false | null | t3_1r4s3oj | /r/LocalLLaMA/comments/1r4s3oj/forking_llmcouncil_for_pure_local_setups_using/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'eHwTMQ2CtT_AwB9dMGSjIyJ-v2II_QMEKNJJsxeaqUg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/eHwTMQ2CtT_AwB9dMGSjIyJ-v2II_QMEKNJJsxeaqUg.png?width=108&crop=smart&auto=webp&s=d275475091412086e499a3874bf44c91fde0ca47', 'width': 108}, {'height': 108, 'url': 'h... |
Are we facing an architectural bottleneck? A geometric critique of ReLU/Simplex-based data storage. | 0 | Hi everyone. As local LLM enthusiasts, we are all obsessed with efficiency (VRAM, quantization, tokens/s). However, today we would like to propose a debate regarding the \*\*geometric foundation\*\* of our current architectures.
\*\*1. The Problem of Spatial Fragmentation:\*\*
Almost all current models rely on ReLU-t... | 2026-02-14T18:22:36 | https://www.reddit.com/r/LocalLLaMA/comments/1r4rvlr/are_we_facing_an_architectural_bottleneck_a/ | wexionar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4rvlr | false | null | t3_1r4rvlr | /r/LocalLLaMA/comments/1r4rvlr/are_we_facing_an_architectural_bottleneck_a/ | false | false | self | 0 | null |
deepseek-r1-0528-qwen3-8b Dosent stop responding?? | 1 | Soo i just try this, with a simple "hi", to check speed and response clarity (if it likes to chit chat more than it should, to count tokens, simple test)
And it responds in chinnese 你好呀！😊 有什么我可以帮你的吗.
soo i try to force it in the system prompt to add "Answer only in \[input language\]. Do not use any other language.... | 2026-02-14T18:12:17 | https://www.reddit.com/r/LocalLLaMA/comments/1r4rm3w/deepseekr10528qwen38b_dosent_stop_responding/ | JamsDrak | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4rm3w | false | null | t3_1r4rm3w | /r/LocalLLaMA/comments/1r4rm3w/deepseekr10528qwen38b_dosent_stop_responding/ | false | false | self | 1 | null |
AirLLM on Openclaw | 0 | Has anyone used AirLLM on Openclaw, I havent seen anything about it? | 2026-02-14T18:00:53 | https://www.reddit.com/r/LocalLLaMA/comments/1r4rbb9/airllm_on_openclaw/ | project_paranoia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4rbb9 | false | null | t3_1r4rbb9 | /r/LocalLLaMA/comments/1r4rbb9/airllm_on_openclaw/ | false | false | self | 0 | null |
We got LLM + RAG running fully offline on Android using MNN | 15 | I’ve been experimenting with running LLMs fully offline on mobile for the past few months, and wanted to share some results + lessons.
Most “AI for documents” apps depend heavily on cloud APIs.
I wanted to see if a complete offline pipeline was actually practical on mid-range Android devices.
So I built a small exp... | 2026-02-14T17:55:57 | https://www.reddit.com/r/LocalLLaMA/comments/1r4r6ld/we_got_llm_rag_running_fully_offline_on_android/ | abuvanth | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4r6ld | false | null | t3_1r4r6ld | /r/LocalLLaMA/comments/1r4r6ld/we_got_llm_rag_running_fully_offline_on_android/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'ZQPQxdI5JCkP7pmtdg8DH29A8ZPAlYcUcwYoni2Wg-k', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ZQPQxdI5JCkP7pmtdg8DH29A8ZPAlYcUcwYoni2Wg-k.png?width=108&crop=smart&auto=webp&s=c020fd089dd1b8f096eb6d3f1de36308c5c5a861', 'width': 108}, {'height': 216, 'url': '... |
I built SnapLLM: switch between local LLMs in under 1 millisecond. Multi-model, multi-modal serving engine with Desktop UI and OpenAI/Anthropic-compatible API. | 1 | Hey everyone,
I've been working on SnapLLM for a while now and wanted to share it with the community.
**The problem:** If you run local models, you know the pain. You load Llama 3, chat with it, then want to try Gemma or Qwen. That means unloading the current model, waiting 30-60 seconds for the new one to load, and ... | 2026-02-14T17:55:11 | https://v.redd.it/mg3x0rlixhjg1 | Immediate-Cake6519 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1r4r5v2 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/mg3x0rlixhjg1/DASHPlaylist.mpd?a=1773683729%2CZGYzYTMyZGExMzI4ZWNlNGZjYWUyNDM1YTRlYzdhNTE4NjMxZGQwZmRkMmU0ZjNkOTM5MTYxZjYwNjJmODM0NA%3D%3D&v=1&f=sd', 'duration': 71, 'fallback_url': 'https://v.redd.it/mg3x0rlixhjg1/CMAF_1080.mp4?source=fallback', 'h... | t3_1r4r5v2 | /r/LocalLLaMA/comments/1r4r5v2/i_built_snapllm_switch_between_local_llms_in/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'dmNnamZ1bWl4aGpnMYj4Y-kpgDDqGP07GvUGsVz_GYiMZXUW_FUpE_QZTl8W', 'resolutions': [{'height': 64, 'url': 'https://external-preview.redd.it/dmNnamZ1bWl4aGpnMYj4Y-kpgDDqGP07GvUGsVz_GYiMZXUW_FUpE_QZTl8W.png?width=108&crop=smart&format=pjpg&auto=webp&s=cb01689461df286745a4ac6818f1ed8860500... | |
I built an MCP memory server with progressive-disclosure — LLMs only load memories they actually need, like how human recall works | 0 | LLM context windows are finite, and stuffing all memories into the system prompt doesn't scale. When context compresses or the session ends, memories vanish. I wanted something better, so I built **Nocturne Memory** — a local MCP server that gives LLMs structured, persistent long-term memory.
**GitHub:** [https://gith... | 2026-02-14T17:47:51 | https://www.reddit.com/r/LocalLLaMA/comments/1r4qz69/i_built_an_mcp_memory_server_with/ | niwatoriking | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4qz69 | false | null | t3_1r4qz69 | /r/LocalLLaMA/comments/1r4qz69/i_built_an_mcp_memory_server_with/ | false | false | 0 | null | |
Applio issues | 1 | Hey everyone I just wanted to introduce myself. I started playing around with this program and I installed it on my windows 11 but I ended up deciding to try to run it through WSL because it wasn't working with my 50 series GPU. I keep running into the same issue over and over. I've been fighting with it for hours. I'v... | 2026-02-14T17:46:06 | https://www.reddit.com/r/LocalLLaMA/comments/1r4qxjo/applio_issues/ | onedaat12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4qxjo | false | null | t3_1r4qxjo | /r/LocalLLaMA/comments/1r4qxjo/applio_issues/ | false | false | self | 1 | null |
A header-only C vector database library | 7 | 2026-02-14T17:44:09 | https://github.com/abdimoallim/vdb | IntrepidAttention56 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1r4qvt9 | false | null | t3_1r4qvt9 | /r/LocalLLaMA/comments/1r4qvt9/a_headeronly_c_vector_database_library/ | false | false | default | 7 | {'enabled': False, 'images': [{'id': '1B7NwWJdbrdg1z7xyRbhECy4tN5F9KUVizYgTNBTb-8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/1B7NwWJdbrdg1z7xyRbhECy4tN5F9KUVizYgTNBTb-8.png?width=108&crop=smart&auto=webp&s=b83864c2e4d87bf08b0dd85c9775938c09d327cb', 'width': 108}, {'height': 108, 'url': 'h... | |
I fine-tuned a “Safe” local LLM for people in crisis (self-harm/violence/paranoia) | 0 | # Why I bothered doing this
Most “safety” behaviour you see is either:
1. **Overly generic refusal** (“I can’t help with that.”)
2. **Overly detailed** in the wrong direction (unintentionally enabling)
3. **Emotionally tone-deaf** when the user is escalated
4. **Delusion-reinforcing** (the worst case)
What I wanted ... | 2026-02-14T17:37:04 | https://www.reddit.com/r/LocalLLaMA/comments/1r4qpbw/i_finetuned_a_safe_local_llm_for_people_in_crisis/ | LinkAmbitious8931 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4qpbw | false | null | t3_1r4qpbw | /r/LocalLLaMA/comments/1r4qpbw/i_finetuned_a_safe_local_llm_for_people_in_crisis/ | false | false | 0 | null | |
Benchmarked 9 VLMs for web UI detection (inc. Qwen 2.5 VL 72B, Sonnet 4.5 & Gemini 3 Flash) | 0 | Ended up going down a benchmarking path as part of one of my side projects, where I needed LLMs to help label website screenshots. It's essentially a browser based UI detection task, but wanted visual validation since DOM inspection has limitations with cross-origin iframes.
Had started with **Sonnet 4.5** as an ancho... | 2026-02-14T17:32:20 | https://www.reddit.com/r/LocalLLaMA/comments/1r4qkya/benchmarked_9_vlms_for_web_ui_detection_inc_qwen/ | Basic-Explorer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4qkya | false | null | t3_1r4qkya | /r/LocalLLaMA/comments/1r4qkya/benchmarked_9_vlms_for_web_ui_detection_inc_qwen/ | false | false | 0 | null | |
512GB Mac Studio & DGX Spark -- Disaggregation & Call for Fun | 0 | M3 Ultra (512GB) & DGX Spark (128GB Blackwell) networked via 10GbE. Benchmark testing indicates the Spark's abilities are not suitable for bandwidth-bound tasks, whatever that means. I sort of understand it -- I'm going to be testing some denser models. Looking for bleeding-edge projects like EXO...(apparently there ar... | 2026-02-14T17:06:48 | https://www.reddit.com/r/LocalLLaMA/comments/1r4px3s/512gb_mac_studio_dgx_spark_disaggregation_call/ | Unusual_Delivery2778 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4px3s | false | null | t3_1r4px3s | /r/LocalLLaMA/comments/1r4px3s/512gb_mac_studio_dgx_spark_disaggregation_call/ | false | false | self | 0 | null |
Best budget GPU(s) for local LLM inference? ~$850 budget | 1 | [removed] | 2026-02-14T17:00:35 | https://www.reddit.com/r/LocalLLaMA/comments/1r4pr6y/best_budget_gpus_for_local_llm_inference_850/ | AndWhatUThink | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4pr6y | false | null | t3_1r4pr6y | /r/LocalLLaMA/comments/1r4pr6y/best_budget_gpus_for_local_llm_inference_850/ | false | false | self | 1 | null |
The 2026 Blueprint: Why "MCP Agentic AI Systems" are replacing simple prompt chains in production. | 0 | We’ve all seen the limitations of building agents with basic ReAct loops or fragile prompt chains. In production, these usually fall apart when complexity scales or compliance kicks in.
I’ve been diving deep into the shift toward **MCP Agentic AI Systems** and how the **Model Context Protocol** is becoming the standar... | 2026-02-14T17:00:07 | https://www.reddit.com/r/LocalLLaMA/comments/1r4pqol/the_2026_blueprint_why_mcp_agentic_ai_systems_are/ | FieldFast7993 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4pqol | false | null | t3_1r4pqol | /r/LocalLLaMA/comments/1r4pqol/the_2026_blueprint_why_mcp_agentic_ai_systems_are/ | false | false | self | 0 | null |
MiniMax M2.5 has been very patient with my dumb ass | 33 | I kept trying to make a change to a simple HTML file but forgot I was in plan mode lol.
https://preview.redd.it/ofxvod0fqhjg1.png?width=991&format=png&auto=webp&s=4e45f65af3a65d10ba9e46466de20083fd298bfe
| 2026-02-14T16:57:02 | https://www.reddit.com/r/LocalLLaMA/comments/1r4pnsv/minimax_m25_has_been_very_patient_with_my_dumb_ass/ | dengar69 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4pnsv | false | null | t3_1r4pnsv | /r/LocalLLaMA/comments/1r4pnsv/minimax_m25_has_been_very_patient_with_my_dumb_ass/ | false | false | 33 | null | |
Deepseek CLI | 0 | https://github.com/yksanjo/deepseek-code
I love to know what people think about it | 2026-02-14T16:56:30 | https://www.reddit.com/r/LocalLLaMA/comments/1r4pnc9/deepseek_cli/ | Vivid-Researcher-666 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1r4pnc9 | false | null | t3_1r4pnc9 | /r/LocalLLaMA/comments/1r4pnc9/deepseek_cli/ | 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.