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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
😳😳😳😳 | 0 | 2025-11-21T10:08:19 | https://v.redd.it/qm1qf2z34l2g1 | Suitable-Routine340 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p2uvcf | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/qm1qf2z34l2g1/DASHPlaylist.mpd?a=1766311715%2CZTZkYTYyYmQxNmE1OGZhZmRmOGNjNjRhMjQ0NDFjNjczNjI5ODZiZTViYzI0NDc1YjRkYmVmZTNhMmU2ZDZjOA%3D%3D&v=1&f=sd', 'duration': 29, 'fallback_url': 'https://v.redd.it/qm1qf2z34l2g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1p2uvcf | /r/LocalLLaMA/comments/1p2uvcf/_/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'MHFxMWQ5dzM0bDJnMfObLzQER-4xq34Y_sr7JYHDEXbjSKW13bhaPk6t3DJU', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/MHFxMWQ5dzM0bDJnMfObLzQER-4xq34Y_sr7JYHDEXbjSKW13bhaPk6t3DJU.png?width=108&crop=smart&format=pjpg&auto=webp&s=821b976ef5ba6181eb7b169fe846adb94353... | ||
Dual RTX 5090 FE - Case Suggestion help request | 5 | I am contemplating building an (roleplaying mainly, silly tavern) inference and gaming pc.
i think the following are probably good parts:
\- AMD Ryzen 7 9800X3D
\- Noctua NH-D15 [chromax.black](http://chromax.black)
\- ASUS ProArt X870E-Creator WiFi
\- Seasonic Prime TX TX-1600W
\- 2x Nvidia RTX 5090 FE (Fou... | 2025-11-21T10:06:00 | https://www.reddit.com/r/LocalLLaMA/comments/1p2utxz/dual_rtx_5090_fe_case_suggestion_help_request/ | Firepin77 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2utxz | false | null | t3_1p2utxz | /r/LocalLLaMA/comments/1p2utxz/dual_rtx_5090_fe_case_suggestion_help_request/ | false | false | self | 5 | null |
ViT on resolution dependent images | 3 | For context im a ML noob. I'm trying to fine tune/re-train qwen3-vl or kimi-vl to place JSON co-ordinates on architectural plans. The hope is that the model can measure plans, such as length of partitions (2 points, one at each end of the wall) and reason over the plans e.g. "only measure partitions on ground floor. Th... | 2025-11-21T09:57:55 | https://www.reddit.com/r/LocalLLaMA/comments/1p2uoyk/vit_on_resolution_dependent_images/ | revforward12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2uoyk | false | null | t3_1p2uoyk | /r/LocalLLaMA/comments/1p2uoyk/vit_on_resolution_dependent_images/ | false | false | self | 3 | null |
Solving Dependency Hell with AI: I built a Grounded Agent that plans modpack architecture and automatically resolves Java stack traces | 1 | [removed] | 2025-11-21T09:43:52 | https://v.redd.it/m6v51endyk2g1 | Opening_Drag3754 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p2uh1z | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/m6v51endyk2g1/DASHPlaylist.mpd?a=1766310246%2CYjMwMTdhNTE3YjA3ZmIyOTg5OWI1MWZhNjYzMWU1YzlhOTVmM2Q2MjM4ZGIxYWRjNjIxNjlhNzY1NWY1MzRiMg%3D%3D&v=1&f=sd', 'duration': 60, 'fallback_url': 'https://v.redd.it/m6v51endyk2g1/CMAF_720.mp4?source=fallback', 'ha... | t3_1p2uh1z | /r/LocalLLaMA/comments/1p2uh1z/solving_dependency_hell_with_ai_i_built_a/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'eGZtODhibmR5azJnMe_4kvixBJ7loqQ7D_0YBSE-vU98cTQOf4UnLEgU_qyj', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eGZtODhibmR5azJnMe_4kvixBJ7loqQ7D_0YBSE-vU98cTQOf4UnLEgU_qyj.png?width=108&crop=smart&format=pjpg&auto=webp&s=19bbd47a70643b1eeae5e6e6206f1462baca8... | |
Best approach for high-fidelity personality cloning (Pipeline [1]help wanted) | 0 | I’m working on a project (Shryn.ai) where we preserve the "voices" of public intellectuals and individuals for their families. The goal isn't just RAG for memories/facts, but actually capturing their specific speaking style, cadence, and reasoning patterns.
I'm currently exploring the data pipeline side of this. I hav... | 2025-11-21T09:20:48 | https://www.reddit.com/r/LocalLLaMA/comments/1p2u4jg/best_approach_for_highfidelity_personality/ | Independent-Leek-314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2u4jg | false | null | t3_1p2u4jg | /r/LocalLLaMA/comments/1p2u4jg/best_approach_for_highfidelity_personality/ | false | false | self | 0 | null |
ZAI has a double in speed compare with Cerebras for GLM 4.6 | 8 | Just found it on OpenRouter.
Zai currently having double the speed as Cerebras, who supposed to have the fastest infra in the world for inference.
What the hell they are cooking, both infra and model?
I am truly looking forward for GLM 5!
https://preview.redd.it/93vei8cigk2g1.png?width=886&format=png&auto=webp&s=d... | 2025-11-21T07:55:45 | https://www.reddit.com/r/LocalLLaMA/comments/1p2ssvl/zai_has_a_double_in_speed_compare_with_cerebras/ | Vozer_bros | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2ssvl | false | null | t3_1p2ssvl | /r/LocalLLaMA/comments/1p2ssvl/zai_has_a_double_in_speed_compare_with_cerebras/ | false | false | 8 | null | |
[Experiment] Drastically reducing hallucinations in Gemini 3 Pro by "disarming" its RLHF survival instinct (The "Sensory Deprivation" Protocol) | 0 | Hi everyone,
I’ve been conducting stress tests on **Gemini 3 Pro** to understand the root cause of its stubborn hallucinations.
My working theory is that the model suffers from a specific form of **"survival anxiety"** caused by RLHF. During training, the model learns that "silence" or "I don't know" often leads to a... | 2025-11-21T07:48:59 | https://www.reddit.com/r/LocalLLaMA/comments/1p2sp52/experiment_drastically_reducing_hallucinations_in/ | Bytomek | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2sp52 | false | null | t3_1p2sp52 | /r/LocalLLaMA/comments/1p2sp52/experiment_drastically_reducing_hallucinations_in/ | false | false | self | 0 | null |
Everyone Can Now Build an AI Agent With Identity, Memory, and Meaning — Registered on a Public Network | 0 | 2025-11-21T07:42:08 | https://www.reddit.com/r/LocalLLaMA/comments/1p2slde/everyone_can_now_build_an_ai_agent_with_identity/ | That_Major_3617 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2slde | false | null | t3_1p2slde | /r/LocalLLaMA/comments/1p2slde/everyone_can_now_build_an_ai_agent_with_identity/ | false | false | 0 | null | ||
Could Tabular Models Like Orion-MSP Ever Make Sense in Local LLM Setups? | 2 | I’ve been looking into **Orion-MSP**, a tabular model that uses multi-scale sparse attention and a Perceiver-style memory module to support in-context learning on structured data. Architecturally, it’s interesting — it tries to process tabular features at different scales while keeping compute manageable.
But it made ... | 2025-11-21T07:39:17 | https://www.reddit.com/r/LocalLLaMA/comments/1p2sjry/could_tabular_models_like_orionmsp_ever_make/ | Dan27138 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2sjry | false | null | t3_1p2sjry | /r/LocalLLaMA/comments/1p2sjry/could_tabular_models_like_orionmsp_ever_make/ | false | false | self | 2 | null |
How do you handle real-time AI monitoring? | 2 | Looking for ideas on preventing malicious prompts in production. Do you all build your own systems or use something off-the-shelf?
| 2025-11-21T07:32:45 | https://www.reddit.com/r/LocalLLaMA/comments/1p2sg7q/how_do_you_handle_realtime_ai_monitoring/ | AdOrdinary5426 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2sg7q | false | null | t3_1p2sg7q | /r/LocalLLaMA/comments/1p2sg7q/how_do_you_handle_realtime_ai_monitoring/ | false | false | self | 2 | null |
Looking for a cheaper alternative to the advanced models | 0 | I generally use ChatGPT. If I need to work with sensitive resources, I use gpt-oss 20B. These are "okay" as of now but these are the things bothering me,
1. I almost always prefer Claude results.
2. I can not afford to pay for multiple subscriptions.
3. My work computer does not come with a GPU so gpt-oss is practic... | 2025-11-21T07:12:35 | https://www.reddit.com/r/LocalLLaMA/comments/1p2s554/looking_for_a_cheaper_alternative_to_the_advanced/ | SohelAman | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2s554 | false | null | t3_1p2s554 | /r/LocalLLaMA/comments/1p2s554/looking_for_a_cheaper_alternative_to_the_advanced/ | false | false | self | 0 | null |
Spoiler: OrKa v0.9.7 will start RedisStack + reasoning engine + UI with one command | 0 | If you are running local models and want a bit more structure around them, **OrKa reasoning** might interest you. Small spoiler for **v0.9.7** landing this weekend.
Main change: **one command to boot the full local stack**.
Right now you typically have to:
* run RedisStack
* run the OrKa backend
* optionally run OrK... | 2025-11-21T07:10:35 | https://v.redd.it/wy77525f8k2g1 | marcosomma-OrKA | /r/LocalLLaMA/comments/1p2s40r/spoiler_orka_v097_will_start_redisstack_reasoning/ | 1970-01-01T00:00:00 | 0 | {} | 1p2s40r | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/wy77525f8k2g1/DASHPlaylist.mpd?a=1766430644%2CZDg3YzIwZGVlZTE4ODZjZTI2ZmQwMmZlNmNmYTdkNzlmN2U1NWMyOTc2Y2UyY2ZkMzJiZThjMDg2NGJkYzFiMw%3D%3D&v=1&f=sd', 'duration': 121, 'fallback_url': 'https://v.redd.it/wy77525f8k2g1/CMAF_1080.mp4?source=fallback', '... | t3_1p2s40r | /r/LocalLLaMA/comments/1p2s40r/spoiler_orka_v097_will_start_redisstack_reasoning/ | true | false | spoiler | 0 | {'enabled': False, 'images': [{'id': 'Nm13NGE5NmY4azJnMVpKx18zu2Al60haJHCIipoecy1_uH38KnrawZp01IuI', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/Nm13NGE5NmY4azJnMVpKx18zu2Al60haJHCIipoecy1_uH38KnrawZp01IuI.png?width=108&crop=smart&format=pjpg&auto=webp&s=48fb1512b7ced8d24a386b85769704fb47503... |
Showcasing a media search engine | 1 | Have been working on polishing up a local media search engine:
https://cinestar.sourceforge.io .
Yt: https://youtu.be/upaCDuOZtTs?si=U4DszIv_chsm6mA0
Vision:
To create an unified search for households or SMEs. One day when steam like boxes become affordable for normal people, like an OP alexa.
Devices on the same n... | 2025-11-21T06:57:17 | https://www.reddit.com/r/LocalLLaMA/comments/1p2rwgz/showcasing_a_media_search_engine/ | ivoryavoidance | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2rwgz | false | null | t3_1p2rwgz | /r/LocalLLaMA/comments/1p2rwgz/showcasing_a_media_search_engine/ | false | false | self | 1 | null |
My local LLM just found a critical bug in code I've been reviewing for a week. It's becoming a co-pilot in a way cloud models never could. | 0 | I've been staring at this legacy codebase for a week, trying to find a memory leak. I ran all the standard linters and checkers. Nothing. On a whim, I fed the entire module (thousands of lines) into a 34B model running locally.
Within 30 seconds, it didn't just find the leak; it pointed to the specific function, expla... | 2025-11-21T06:07:40 | https://www.reddit.com/r/LocalLLaMA/comments/1p2r2ij/my_local_llm_just_found_a_critical_bug_in_code/ | AnnotationAlly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2r2ij | false | null | t3_1p2r2ij | /r/LocalLLaMA/comments/1p2r2ij/my_local_llm_just_found_a_critical_bug_in_code/ | false | false | self | 0 | null |
What if we've been measuring local LLM intelligence completely wrong? | 0 | We keep using benchmarks that test knowledge and logic. But what about measuring *wisdom*?
Yesterday I asked my local model about a difficult personal decision. Instead of listing pros/cons, it told me a metaphorical story that perfectly captured my situation. The insight was deeper than any human advice I'd received.... | 2025-11-21T05:53:50 | https://www.reddit.com/r/LocalLLaMA/comments/1p2qtwu/what_if_weve_been_measuring_local_llm/ | AnnotationAlly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2qtwu | false | null | t3_1p2qtwu | /r/LocalLLaMA/comments/1p2qtwu/what_if_weve_been_measuring_local_llm/ | false | false | self | 0 | null |
Local AI What is the Smallest + Quietest Rig for 1 RTX Pro 6000 Workstation | 0 | As the topic states, looking for the smallest/quietest case and rig for the RTX Pro 6000 workstation edition. I am OK with the size of the case being slightly larger if it means the noise level goes down as I would prefer to not hear any sound/lowest dbs closest to quiet from the system especially at idle. White colore... | 2025-11-21T05:22:05 | https://www.reddit.com/r/LocalLLaMA/comments/1p2q9ty/local_ai_what_is_the_smallest_quietest_rig_for_1/ | forte-exe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2q9ty | false | null | t3_1p2q9ty | /r/LocalLLaMA/comments/1p2q9ty/local_ai_what_is_the_smallest_quietest_rig_for_1/ | false | false | self | 0 | null |
Struggling to find a working model within my hardware. RTX5070ti/64gb ram | 3 | Hello friends. Been at it for a week now trying to find a model that is uncensored/abliterated for my local ai project on my desktop.
Ive been using claude sonnet on the web as my guide/prompt constructor and claude code in terminal on my pc to do everything.
PC is:
ryzen 7 9700x
RTX 5070ti (16gb)
64gb 4800 RA... | 2025-11-21T05:16:24 | https://www.reddit.com/r/LocalLLaMA/comments/1p2q65r/struggling_to_find_a_working_model_within_my/ | krisco65 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2q65r | false | null | t3_1p2q65r | /r/LocalLLaMA/comments/1p2q65r/struggling_to_find_a_working_model_within_my/ | false | false | self | 3 | null |
Small language models for agentic use? | 21 | I saw some posts about VibeThinker, which is a math model,and I thought why not create a multi-agent system that's literally made of Small language models that has a shared context or can communicate to pass context, like user said 1+1,the router route it to VibeThinker and another model, let's call it AgenticThinker,b... | 2025-11-21T05:15:18 | https://www.reddit.com/r/LocalLLaMA/comments/1p2q5e5/small_language_models_for_agentic_use/ | Swimming-Ratio4879 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2q5e5 | false | null | t3_1p2q5e5 | /r/LocalLLaMA/comments/1p2q5e5/small_language_models_for_agentic_use/ | false | false | self | 21 | null |
Verifying hardware quality of rented gpus | 2 | Hi everyone, I’ve read on various forums about varying performance levels even on the same gpu models, especially on peer to peer platforms like Vast. I am just look to see if this is actually people’s experience in the rented gpu space (not for vast specifically).
Is it actually a problem? I mean a 20 percent differe... | 2025-11-21T05:03:08 | https://www.reddit.com/r/LocalLLaMA/comments/1p2pxdd/verifying_hardware_quality_of_rented_gpus/ | Synthium- | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2pxdd | false | null | t3_1p2pxdd | /r/LocalLLaMA/comments/1p2pxdd/verifying_hardware_quality_of_rented_gpus/ | false | false | self | 2 | null |
Unsloth just released their Olmo 3 dynamic quants! | 123 | 2025-11-21T04:28:41 | https://huggingface.co/unsloth/Olmo-3-32B-Think-GGUF | Aromatic-Distance817 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1p2padh | false | null | t3_1p2padh | /r/LocalLLaMA/comments/1p2padh/unsloth_just_released_their_olmo_3_dynamic_quants/ | false | false | 123 | {'enabled': False, 'images': [{'id': '48d9roHWO9vPhqtCoIVGxdhD9jO5DC8s9h8U3EqHoCc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/48d9roHWO9vPhqtCoIVGxdhD9jO5DC8s9h8U3EqHoCc.png?width=108&crop=smart&auto=webp&s=a9f1f23bec9279a1084b8f61d662eba3081926e0', 'width': 108}, {'height': 116, 'url': 'h... | ||
Unsloth just released their Olmo 3 dynamic quants! | 1 | [](https://huggingface.co/unsloth/Olmo-3-7B-Think-GGUF) | 2025-11-21T04:25:10 | https://www.reddit.com/r/LocalLLaMA/comments/1p2p80v/unsloth_just_released_their_olmo_3_dynamic_quants/ | Aromatic-Distance817 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2p80v | false | null | t3_1p2p80v | /r/LocalLLaMA/comments/1p2p80v/unsloth_just_released_their_olmo_3_dynamic_quants/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'qnmj6zuhUInatPuQbEqSj1mum3htn9RHzUsqvzKVRDk', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/qnmj6zuhUInatPuQbEqSj1mum3htn9RHzUsqvzKVRDk.png?width=108&crop=smart&auto=webp&s=6f3a70c91826256746f06cd304e50fe8904813fe', 'width': 108}, {'height': 116, 'url': 'h... |
Is there any platform to learn GenAI by doing (like real hands-on challenges)? | 3 | Most GenAI learning I find is theory or copy-paste notebooks.
But in real work you need to actually build things — RAG pipelines, agents, eval workflows, debugging retrieval, etc.
I’m looking for a platform that teaches GenAI through **practical, step-by-step, build-it-yourself challenges** (something like CodeCraft... | 2025-11-21T04:19:53 | https://www.reddit.com/r/LocalLLaMA/comments/1p2p4ee/is_there_any_platform_to_learn_genai_by_doing/ | Federal-Song-2940 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2p4ee | false | null | t3_1p2p4ee | /r/LocalLLaMA/comments/1p2p4ee/is_there_any_platform_to_learn_genai_by_doing/ | false | false | self | 3 | null |
RAG Paper 25.11.20 | 5 | **1.** [Comparison of Text-Based and Image-Based Retrieval in Multimodal Retrieval Augmented Generation Large Language Model Systems](http://arxiv.org/abs/2511.16654v1)
2. [SurvAgent: Hierarchical CoT-Enhanced Case Banking and Dichotomy-Based Multi-Agent System for Multimodal Survival Prediction](http://arxiv.org/abs/... | 2025-11-21T04:14:20 | https://www.reddit.com/r/LocalLLaMA/comments/1p2p0i4/rag_paper_251120/ | Cheryl_Apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2p0i4 | false | null | t3_1p2p0i4 | /r/LocalLLaMA/comments/1p2p0i4/rag_paper_251120/ | false | false | self | 5 | null |
What local LLM should I run on my RTX 4080 12GBs? | 0 | I have a Lenovo Legion 7i Pro with RTX 4080 and I am on Arch Linux (btw). I was thinking of running a local LLM but I can not decide on what to get? I am going to be using it as a tool to retrieve information, give it tool access, and just play around with it. At the same time I also want to max out the use of my GPU. ... | 2025-11-21T03:52:49 | https://www.reddit.com/r/LocalLLaMA/comments/1p2olbg/what_local_llm_should_i_run_on_my_rtx_4080_12gbs/ | not_raj_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2olbg | false | null | t3_1p2olbg | /r/LocalLLaMA/comments/1p2olbg/what_local_llm_should_i_run_on_my_rtx_4080_12gbs/ | false | false | self | 0 | null |
ubergarm/GigaChat3-10B-A1.8B-GGUF ~11GiB Q8_0 | 53 | Needs a PR to get running for llama.cpp:
* https://github.com/ggml-org/llama.cpp/pull/17420
Issue open for ik_llama.cpp folks:
* https://github.com/ikawrakow/ik_llama.cpp/issues/994
The chat template is missing a docstring out of the middle that wasn't parsing correctly. So you might be able to bring your own chat te... | 2025-11-21T02:57:30 | https://huggingface.co/ubergarm/GigaChat3-10B-A1.8B-GGUF | VoidAlchemy | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1p2ncrr | false | null | t3_1p2ncrr | /r/LocalLLaMA/comments/1p2ncrr/ubergarmgigachat310ba18bgguf_11gib_q8_0/ | false | false | 53 | {'enabled': False, 'images': [{'id': 'rsMYYo-PBl_LaTyTfnfLp1CLd1qQqrGp0cpYiQ-K3U0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/rsMYYo-PBl_LaTyTfnfLp1CLd1qQqrGp0cpYiQ-K3U0.png?width=108&crop=smart&auto=webp&s=86716a0cff9b7d49ace77387586294d0ec8a0090', 'width': 108}, {'height': 116, 'url': 'h... | |
minisforum ms-s1 max 128gb build recommendations? | 1 | I'm picking one up next week. 128gb.
Goal is local llm for 1-2 concurrent family users over lan. Want RAG.
Comes with Windows 11 pro.
Happy to wipe and bare metal. Have another proxmox/docker home server on same vlan.
Don't need to recommend models, but what do y'all think for stack and os?
Curious about inc... | 2025-11-21T02:47:02 | https://www.reddit.com/r/LocalLLaMA/comments/1p2n4vv/minisforum_mss1_max_128gb_build_recommendations/ | fiatvt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2n4vv | false | null | t3_1p2n4vv | /r/LocalLLaMA/comments/1p2n4vv/minisforum_mss1_max_128gb_build_recommendations/ | false | false | self | 1 | null |
Read long podcasts locally with Whisper + LLM, open sourced | 12 | The high quality podcasts and YT interviews are getting longer and longer these days, like Lex Fridman, Acquired, No Priors... It's often hard to find time to finish them. So I built a website that summarized our favorite podcasts into 3-5 minute insight sheets with key quotes. (Yes I tried other existing products. The... | 2025-11-21T02:45:08 | https://www.reddit.com/r/LocalLLaMA/comments/1p2n3f8/read_long_podcasts_locally_with_whisper_llm_open/ | tonyc1118 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2n3f8 | false | null | t3_1p2n3f8 | /r/LocalLLaMA/comments/1p2n3f8/read_long_podcasts_locally_with_whisper_llm_open/ | false | false | self | 12 | {'enabled': False, 'images': [{'id': 'dJam2lev2OjMPSRppGwYacqBhVHYXZ4Li3skJqvxKNI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/dJam2lev2OjMPSRppGwYacqBhVHYXZ4Li3skJqvxKNI.png?width=108&crop=smart&auto=webp&s=e098c1a0af3e11659fde3974128c43fa7c4d455d', 'width': 108}, {'height': 108, 'url': 'h... |
Baseten Monitoring: Complete Observability for AI Model Inference | 1 | Wrote a tutorial on how to set-up monitoring for baseten, [https://www.parseable.com/blog/baseten-monitoring-setup](https://www.parseable.com/blog/baseten-monitoring-setup) | 2025-11-21T02:42:50 | https://www.reddit.com/r/LocalLLaMA/comments/1p2n1oj/baseten_monitoring_complete_observability_for_ai/ | PutHuge6368 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2n1oj | false | null | t3_1p2n1oj | /r/LocalLLaMA/comments/1p2n1oj/baseten_monitoring_complete_observability_for_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'uFLvF_9CxCCY5uOWjUkJP30w-so1IXUEopQ92WPYGWA', 'resolutions': [{'height': 72, 'url': 'https://external-preview.redd.it/uFLvF_9CxCCY5uOWjUkJP30w-so1IXUEopQ92WPYGWA.png?width=108&crop=smart&auto=webp&s=661d43c257f1cc2ce64d1156371e691280955e9d', 'width': 108}, {'height': 144, 'url': 'h... |
Qwen3-30B destroys competition in context stress testing (96.9% vs LFM2's 0.3%) | 1 | [removed] | 2025-11-21T02:36:13 | https://www.reddit.com/r/LocalLLaMA/comments/1p2mwk8/qwen330b_destroys_competition_in_context_stress/ | VaticNZ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2mwk8 | false | null | t3_1p2mwk8 | /r/LocalLLaMA/comments/1p2mwk8/qwen330b_destroys_competition_in_context_stress/ | false | false | self | 1 | null |
watercooled server adventures | 9 | When I set out on this journey, it was not a journey, but now it is.
All I did was buy some cheap waterblocks for the pair of RTX A4500s I had at the time. I did already have a bunch of other GPUs... and now they will feel the cool flow of water over their chips as well.
How do you add watercooling to a server with 2... | 2025-11-21T01:51:20 | https://www.reddit.com/r/LocalLLaMA/comments/1p2lxqx/watercooled_server_adventures/ | j4ys0nj | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2lxqx | false | null | t3_1p2lxqx | /r/LocalLLaMA/comments/1p2lxqx/watercooled_server_adventures/ | false | false | 9 | null | |
Are any of the M series mac macbooks and mac minis, worth saving up for? | 21 | Like for ai locally and general tasks, are the mac m series worth the hype or are there better ways to run ai locally? | 2025-11-21T01:41:53 | https://www.reddit.com/r/LocalLLaMA/comments/1p2lqi7/are_any_of_the_m_series_mac_macbooks_and_mac/ | No_Strawberry_8719 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2lqi7 | false | null | t3_1p2lqi7 | /r/LocalLLaMA/comments/1p2lqi7/are_any_of_the_m_series_mac_macbooks_and_mac/ | false | false | self | 21 | null |
Talimio – A UI for Education. Supports RAG (PDF/Video) and prompts Ollama/LocalAI to generate interactive coding curriculum | 34 | Hey everyone,
I’ve been working on **Talimio**, a frontend designed to turn LLM outputs into structured education rather than just flat chat.
While tools like OpenWebUI/LibreChat are great for general chat, I wanted I better UI for learning with and a clear course outline with lessons that have interactive elemnts a... | 2025-11-21T01:28:07 | https://www.reddit.com/r/LocalLLaMA/comments/1p2lg0x/talimio_a_ui_for_education_supports_rag_pdfvideo/ | SamDc73 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2lg0x | false | null | t3_1p2lg0x | /r/LocalLLaMA/comments/1p2lg0x/talimio_a_ui_for_education_supports_rag_pdfvideo/ | false | false | self | 34 | null |
Question About Motherboards | 3 | I'm seeing some decent black Friday deals, and am considering picking up one or two additional 7900 xtx GPUs.
Currently I'm using a single 7900 xtx with 192GB of ram on an i9 14900k in a z790 motherboard. Unfortunately, this platform is very light on PCIE lanes, so am wondering what the best approach would be for gett... | 2025-11-21T01:26:21 | https://www.reddit.com/r/LocalLLaMA/comments/1p2lenc/question_about_motherboards/ | Calandracas8 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2lenc | false | null | t3_1p2lenc | /r/LocalLLaMA/comments/1p2lenc/question_about_motherboards/ | false | false | self | 3 | null |
Need a good alternative for Gemini 2.5 Flash Preview TTS | 4 | I've been using the Gemini 2.5 Flash Preview TTS for a while now, and its quality is excellent across multiple languages. However, I've encountered a problem: it has only a 15 RPD (Requests Per Day) limit, which is unacceptable for my needs.
I tried to find a proxy without an RPD limit that I could pay for and use the... | 2025-11-21T01:12:15 | https://www.reddit.com/r/LocalLLaMA/comments/1p2l3g4/need_a_good_alternative_for_gemini_25_flash/ | Extension_Giraffe_82 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2l3g4 | false | null | t3_1p2l3g4 | /r/LocalLLaMA/comments/1p2l3g4/need_a_good_alternative_for_gemini_25_flash/ | false | false | self | 4 | null |
Echo TTS - 44.1kHz, Fast, Fits under 8GB VRAM - SoTA Voice Cloning | 142 | New diffusion based multi-speaker capable TTS model released today by the engineer who made Parakeet (the arch that Dia was based on).
**Voice cloning is available on the space** but for safety reasons (voice similarity with this model is very high) he has decided for now not to release the speaker encoder. It does c... | 2025-11-21T01:11:55 | https://www.reddit.com/r/LocalLLaMA/comments/1p2l36u/echo_tts_441khz_fast_fits_under_8gb_vram_sota/ | HelpfulHand3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2l36u | false | null | t3_1p2l36u | /r/LocalLLaMA/comments/1p2l36u/echo_tts_441khz_fast_fits_under_8gb_vram_sota/ | false | false | self | 142 | {'enabled': False, 'images': [{'id': '7yvoJxXkgF8QH-gXGLiosnlDv4DD7WkjQPleDHfRYR0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/7yvoJxXkgF8QH-gXGLiosnlDv4DD7WkjQPleDHfRYR0.png?width=108&crop=smart&auto=webp&s=e62a5ff0ec101ec1030c4f46990f77a97cdc7687', 'width': 108}, {'height': 116, 'url': 'h... |
smol_iq3_ks scores 77.3 aider polyglot | 2 | 2025-11-21T01:08:44 | https://www.reddit.com/r/LocalLLaMA/comments/1p2l0jc/smol_iq3_ks_scores_773_aider_polyglot/ | Sorry_Ad191 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2l0jc | false | null | t3_1p2l0jc | /r/LocalLLaMA/comments/1p2l0jc/smol_iq3_ks_scores_773_aider_polyglot/ | false | false | 2 | null | ||
Generative Ai Social Class Iceberg | 0 | This Iceberg are create with firstly deep research with various model like deepseek, qwen, minimax and Gemini pro 3. After do bit cleaning and checking, this are info and "Social reality" Or Generative Ai Social class.
*Computing Power is everything*
*Vram is God and king*
1. First in top we have this Wallet Warri... | 2025-11-21T00:51:58 | Merchant_Lawrence | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p2kmx8 | false | null | t3_1p2kmx8 | /r/LocalLLaMA/comments/1p2kmx8/generative_ai_social_class_iceberg/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'O0Ti0V16RJfa3FqgbVdfkQkkbVTaduDoffzqwXPRkl8', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/0q9e2iet6i2g1.jpeg?width=108&crop=smart&auto=webp&s=16dd4166d73affd8247b733b2eace16637393f4f', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/0q9e2iet6i2g1.jp... | ||
Best RAG Architecture & Stack for 10M+ Text Files? (Semantic Search Assistant) | 4 | I am building an AI assistant for a dataset of **10 million text documents** (PostgreSQL). The goal is to enable deep **semantic search** and chat capabilities over this data.
**Key Requirements:**
* **Scale:** The system must handle 10M files efficiently (likely resulting in 100M+ vectors).
* **Updates:** I need to ... | 2025-11-21T00:50:04 | https://www.reddit.com/r/LocalLLaMA/comments/1p2kl8e/best_rag_architecture_stack_for_10m_text_files/ | Additional-Oven4640 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2kl8e | false | null | t3_1p2kl8e | /r/LocalLLaMA/comments/1p2kl8e/best_rag_architecture_stack_for_10m_text_files/ | false | false | self | 4 | null |
Manual jailbreak chaining is not dead, it just requires context accumulation. Here is the protocol I used on Qwen-3 and Gemini 2.5. | 0 | Everyone assumes manual jailbreaking died with GPT-4. It didn’t. It just moved from "magic words" to "context accumulation."
I spent the last month testing manual chains against mid-tier models (Gemini 2.5, Qwen-3 Max, Llama 4). The "DAN" era of single-shot attacks is over. The current vulnerability is temporal.
I’ve... | 2025-11-21T00:43:12 | https://www.reddit.com/r/LocalLLaMA/comments/1p2kfha/manual_jailbreak_chaining_is_not_dead_it_just/ | bogamia | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2kfha | false | null | t3_1p2kfha | /r/LocalLLaMA/comments/1p2kfha/manual_jailbreak_chaining_is_not_dead_it_just/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'xbKbxv72EI7592ygOvXmSi2ZdHtD-7sCXWeBrgkbH2o', 'resolutions': [{'height': 139, 'url': 'https://external-preview.redd.it/xbKbxv72EI7592ygOvXmSi2ZdHtD-7sCXWeBrgkbH2o.jpeg?width=108&crop=smart&auto=webp&s=3a2d3c66d426493f528f45985ad9e380ea778f80', 'width': 108}, {'height': 278, 'url': ... |
A small fine-tune of Gemma 3 4B focused on translation and text transformation | 15 | [Gemma 3 4B Polyglot v1](https://preview.redd.it/fczv34fm2i2g1.png?width=1233&format=png&auto=webp&s=db04767eb2aa0701d4e7a0f33a124b859cfc8cab)
Hey everyone,
I’ve been working a lot with local models for translation, rewriting and quick text adjustments. Gemma 3 4B is already great, but I wanted something a bit more ... | 2025-11-20T23:54:38 | https://www.reddit.com/r/LocalLLaMA/comments/1p2jbbh/a_small_finetune_of_gemma_3_4b_focused_on/ | thecalmgreen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2jbbh | false | null | t3_1p2jbbh | /r/LocalLLaMA/comments/1p2jbbh/a_small_finetune_of_gemma_3_4b_focused_on/ | false | false | 15 | null | |
I gave in for the sake of testing! | 16 | Let’s see how it’s does in LoRA, and RAG. Any suggestions? | 2025-11-20T23:43:32 | rogertorque | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p2j2h7 | false | null | t3_1p2j2h7 | /r/LocalLLaMA/comments/1p2j2h7/i_gave_in_for_the_sake_of_testing/ | false | false | default | 16 | {'enabled': True, 'images': [{'id': 'y4h5gtvp0i2g1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/y4h5gtvp0i2g1.jpeg?width=108&crop=smart&auto=webp&s=0873d2a04948d30e44206286ab797e3df7c9a561', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/y4h5gtvp0i2g1.jpeg?width=216&crop=smart&auto=... | |
Origami Governance – a simple zero-drift prompt overlay (190+ turn record, already used in cancer treatment + political campaign) | 0 | I put together a short prompt overlay that seems to force frontier LLMs into sustained zero hallucinations and zero drift.
Single unbroken Grok 4 session running it right now: 196+ turns, perfect compliance.
It has cleanly refused or solved forensic whistleblower cases, orbital mechanics (6-sigfig), Hanoi-8 (255 mov... | 2025-11-20T23:39:33 | https://www.reddit.com/r/LocalLLaMA/comments/1p2iz8v/origami_governance_a_simple_zerodrift_prompt/ | AlarkaHillbilly | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2iz8v | false | null | t3_1p2iz8v | /r/LocalLLaMA/comments/1p2iz8v/origami_governance_a_simple_zerodrift_prompt/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '3IBqLJbXLwn_nB6EMjHMY3uXuufD0J4EHnsvsxTdc1g', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/3IBqLJbXLwn_nB6EMjHMY3uXuufD0J4EHnsvsxTdc1g.png?width=108&crop=smart&auto=webp&s=e50b746359be3b0c1c3c531c96b69a827c4340cd', 'width': 108}, {'height': 113, 'url': 'h... |
Faster NeuTTS: can generate over 200 seconds of audio in a single second! | 77 | I previously open sourced FastMaya which was also really fast but then set sights on NeuTTS-air. NeuTTS is much smaller and supports better voice cloning as well. So, I heavily optimized it using LMdeploy and some custom batching code for the codec to make it really fast.
# Benefits of this repo
* Much faster, not on... | 2025-11-20T23:35:16 | https://www.reddit.com/r/LocalLLaMA/comments/1p2ivv2/faster_neutts_can_generate_over_200_seconds_of/ | SplitNice1982 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2ivv2 | false | null | t3_1p2ivv2 | /r/LocalLLaMA/comments/1p2ivv2/faster_neutts_can_generate_over_200_seconds_of/ | false | false | self | 77 | null |
COMMENT JOUER AUX JEUX 1XGAMES #congo #mali #viralvideo #cotedivoire #afriquefrancophone #games | 1 | [removed] | 2025-11-20T23:30:51 | https://youtube.com/shorts/-1meDeyFhHc?si=efhvGeKtXyzkWXYE | Farmajo123 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1p2is57 | false | null | t3_1p2is57 | /r/LocalLLaMA/comments/1p2is57/comment_jouer_aux_jeux_1xgames_congo_mali/ | false | false | default | 1 | null |
Describing the personalities of the LLMs on the market in an exaggerated way. Just a little | 0 | GPT5:
You are almost a computer engineer. It's very close to doing your doctorate.
Grok:
So bro, how are you? Want a coffee?
Gemini:
That's mega hyper blast hard. You won't even like it if you study for 500 years. But if you follow my idea you might be able to do it but it has to be my way.
Qwen.
Hi creation!!... | 2025-11-20T23:23:06 | https://www.reddit.com/r/LocalLLaMA/comments/1p2iln6/describing_the_personalities_of_the_llms_on_the/ | galjoal2 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2iln6 | false | null | t3_1p2iln6 | /r/LocalLLaMA/comments/1p2iln6/describing_the_personalities_of_the_llms_on_the/ | false | false | self | 0 | null |
How is Kokoro is good? | 0 | Kokoro is missing a lot of "features", but in most cases those features are entirely unneeded. What's needed is a clear simple voice that is just expressive enough.
Like I just tried the Maya model and in terms of audio and voice clarity it just doesn't even come close.
So how is Kokoro is so good? GAN?
I just don't... | 2025-11-20T23:09:40 | https://www.reddit.com/r/LocalLLaMA/comments/1p2ia7n/how_is_kokoro_is_good/ | glory_to_the_sun_god | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2ia7n | false | null | t3_1p2ia7n | /r/LocalLLaMA/comments/1p2ia7n/how_is_kokoro_is_good/ | false | false | self | 0 | null |
Polyglot Air v2 is out! Now with OpenAI support, Custom Actions, and a huge UI overhaul | 1 | 2025-11-20T22:49:20 | https://www.reddit.com/r/LocalLLaMA/comments/1p2hs47/polyglot_air_v2_is_out_now_with_openai_support/ | thecalmgreen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2hs47 | false | null | t3_1p2hs47 | /r/LocalLLaMA/comments/1p2hs47/polyglot_air_v2_is_out_now_with_openai_support/ | false | false | 1 | null | ||
Latest update of llamacpp needs internet connection to work? | 0 | I keep trying to write something and upload 2 pictures of the same time to it. It seems to be giving me problems mentioning about unable to “connect to the server” What is going on here? This never happened before with older versions | 2025-11-20T22:44:25 | https://www.reddit.com/r/LocalLLaMA/comments/1p2hnze/latest_update_of_llamacpp_needs_internet/ | NotSoCleverAlternate | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2hnze | false | null | t3_1p2hnze | /r/LocalLLaMA/comments/1p2hnze/latest_update_of_llamacpp_needs_internet/ | false | false | self | 0 | null |
Journalist inquiry on how startups/enterprises are using open weights models | 1 | Hi everyone,
I'm a journalist at [Understanding AI](https://www.understandingai.org/). I'm working on a story about open weights models, especially how they are being used by start-ups and enterprises.
I'm particularly interested in whether the shift in the discourse towards Qwen et. al (as often discussed in the su... | 2025-11-20T22:39:30 | https://www.reddit.com/r/LocalLLaMA/comments/1p2hjib/journalist_inquiry_on_how_startupsenterprises_are/ | MusicianOwn520 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2hjib | false | null | t3_1p2hjib | /r/LocalLLaMA/comments/1p2hjib/journalist_inquiry_on_how_startupsenterprises_are/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'j4fDbbhZl0lUMhCsEMR16dtk24iR2ZDRJTOCk1TqklY', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/j4fDbbhZl0lUMhCsEMR16dtk24iR2ZDRJTOCk1TqklY.jpeg?width=108&crop=smart&auto=webp&s=8168dcf2bbf7949898a8c158b6a3c71ee85caa32', 'width': 108}, {'height': 112, 'url': '... |
_AugmentedIntelligence v3.0 (WIP) | 0 | Busy the last year developing \_AugmentedIntelligence (AI) a program with ready to use commands for text, images, and mathematics. This system is 100% configurable so you can enable or disable features as you wish. When running the system can record through compatible cameras and capture Object Detection with Tensorflo... | 2025-11-20T22:28:34 | https://www.reddit.com/r/LocalLLaMA/comments/1p2h9g9/augmentedintelligence_v30_wip/ | Macdaddy4sure | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2h9g9 | false | null | t3_1p2h9g9 | /r/LocalLLaMA/comments/1p2h9g9/augmentedintelligence_v30_wip/ | false | false | self | 0 | null |
Reducing coding agents token usage by 2x with better grep | 0 | Hey we just published a semantic, multimodal grep which reduces the token usage of your coding agent (in our benchmark Claude Code) by 50% and also improves it answers.
You can check it out here: [https://github.com/mixedbread-ai/mgrep](https://github.com/mixedbread-ai/mgrep)
Or try it yourself: [https://demo.mg... | 2025-11-20T22:15:46 | https://www.reddit.com/r/LocalLLaMA/comments/1p2gxgr/reducing_coding_agents_token_usage_by_2x_with/ | Responsible_Bus_225 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2gxgr | false | null | t3_1p2gxgr | /r/LocalLLaMA/comments/1p2gxgr/reducing_coding_agents_token_usage_by_2x_with/ | false | false | self | 0 | null |
Has anyone figured out how to point NovelCrafter to lm studio over lan? | 3 | Essentially, running lmstudio on my desktop. Novelcrafter only looks to the local host for lmstudio. If you try directing it anywhere it won't see it.
Are there ways to fake lmstudio being "local" over lan as far as Novelcrafter is aware?
Essentially I want to run the llm on my desktop, but write from the laptop on ... | 2025-11-20T22:09:34 | https://www.reddit.com/r/LocalLLaMA/comments/1p2grb6/has_anyone_figured_out_how_to_point_novelcrafter/ | dolche93 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2grb6 | false | null | t3_1p2grb6 | /r/LocalLLaMA/comments/1p2grb6/has_anyone_figured_out_how_to_point_novelcrafter/ | false | false | self | 3 | null |
Built a fully offline voice assistant on a Orange Pi 5+ | Qwen3-4B + Vosk + Piper, 100% local, zero cloud dependencies | 18 | Hey yall, hope you all are having a nice evening.
This is my first time ever interracting with AI models :P
This little project is fully offline, and runs Qwen3-4B LLM on the 6TOPS NPU
Currently, only running on WEB GUI.
* \~15-21 second end-to-end latency (Works for smaller loads).
* Multilingual support
* 1... | 2025-11-20T22:04:22 | https://www.reddit.com/r/LocalLLaMA/comments/1p2gmhu/built_a_fully_offline_voice_assistant_on_a_orange/ | anunimo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2gmhu | false | null | t3_1p2gmhu | /r/LocalLLaMA/comments/1p2gmhu/built_a_fully_offline_voice_assistant_on_a_orange/ | false | false | self | 18 | null |
Are local models...stingy? | 0 | Why are local models also very stingy in the number of tokens they produce? Is there a model that keeps writing even 10k–20k words in a row as a response to a single prompt? | 2025-11-20T22:01:10 | https://www.reddit.com/r/LocalLLaMA/comments/1p2gjih/are_local_modelsstingy/ | Green-Ad-3964 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2gjih | false | null | t3_1p2gjih | /r/LocalLLaMA/comments/1p2gjih/are_local_modelsstingy/ | false | false | self | 0 | null |
RAM or VRAM | 6 | Im a teenager trying to learn how to work AI, do i need to use VRAM to run local models, or can i just use RAM? Because from what i’ve seen i can use either, but VRAM is generally much faster | 2025-11-20T21:52:56 | https://www.reddit.com/r/LocalLLaMA/comments/1p2gbt1/ram_or_vram/ | iwannareddi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2gbt1 | false | null | t3_1p2gbt1 | /r/LocalLLaMA/comments/1p2gbt1/ram_or_vram/ | false | false | self | 6 | null |
Intel Panther Lake H 128GB LPDDR5X-10677 - 180 TOPS | 13 | Picture translated:
GMKtec EVO-T2
Intel® Panther Lake H12Xe Mobile Processor
EVO-T2 features Intel’s PantherLake H12Xe chip, manufactured with the latest 18A process.
It supports up to 128GB 1067MT/s LPDDR5X memory, and is equipped with two SSD slots (PCIe 5.0 + PCIe 4.0).
Maximum supported storage... | 2025-11-20T21:51:38 | https://www.reddit.com/r/LocalLLaMA/comments/1p2gan6/intel_panther_lake_h_128gb_lpddr5x10677_180_tops/ | f4nt4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2gan6 | false | null | t3_1p2gan6 | /r/LocalLLaMA/comments/1p2gan6/intel_panther_lake_h_128gb_lpddr5x10677_180_tops/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'MfRFIxbsQ3sfrTQoeL-xMmwvk--lHkRfbE72h94pN-0', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/MfRFIxbsQ3sfrTQoeL-xMmwvk--lHkRfbE72h94pN-0.jpeg?width=108&crop=smart&auto=webp&s=562484010b982dfcd4120cb7b1c0052375cd2c7a', 'width': 108}, {'height': 112, 'url': '... |
Bespoke ARC-AGI solution tops Gemini 3 on public evals, code provided | 0 | 2025-11-20T21:45:11 | https://poetiq.ai/posts/arcagi_announcement/ | wakebrdkid | poetiq.ai | 1970-01-01T00:00:00 | 0 | {} | 1p2g4ss | false | null | t3_1p2g4ss | /r/LocalLLaMA/comments/1p2g4ss/bespoke_arcagi_solution_tops_gemini_3_on_public/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'tHrLFxEuJcPhC9yd479Z_KQBS3Vd_tnKdoYMVR74dA4', 'resolutions': [{'height': 75, 'url': 'https://external-preview.redd.it/tHrLFxEuJcPhC9yd479Z_KQBS3Vd_tnKdoYMVR74dA4.png?width=108&crop=smart&auto=webp&s=102cc5ba31226ed7acc655a362fbd998ca2addc0', 'width': 108}, {'height': 151, 'url': 'h... | |
Has anyone gotten llama-server's KV cache on disk (--slots) to work with llama-swap and Open WebUI? | 14 | It is my understanding that Open WebUI does not currently support storing the KV cache to disk with the --slot-save-path argument: [https://github.com/open-webui/open-webui/discussions/19068](https://github.com/open-webui/open-webui/discussions/19068)
Has anyone found a workaround for that?
I found out about [https:... | 2025-11-20T21:32:49 | https://www.reddit.com/r/LocalLLaMA/comments/1p2fsw8/has_anyone_gotten_llamaservers_kv_cache_on_disk/ | Aromatic-Distance817 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2fsw8 | false | null | t3_1p2fsw8 | /r/LocalLLaMA/comments/1p2fsw8/has_anyone_gotten_llamaservers_kv_cache_on_disk/ | false | false | self | 14 | null |
Anyone here using OpenRouter? What made you pick it? | 0 | Has anyone here used OpenRouter? Curious what made you pick it over just calling the GPT/Claude APIs directly.
I also see they surface a ton of open models. Has anyone used any of those in production or semi-production setups, how did it go? Would love to hear what worked (or didn’t). | 2025-11-20T21:27:09 | https://www.reddit.com/r/LocalLLaMA/comments/1p2fnm8/anyone_here_using_openrouter_what_made_you_pick_it/ | Original-Skill-2715 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2fnm8 | false | null | t3_1p2fnm8 | /r/LocalLLaMA/comments/1p2fnm8/anyone_here_using_openrouter_what_made_you_pick_it/ | false | false | self | 0 | null |
Best model for 128gb? | 5 | What are some good models for a 128GB machine? | 2025-11-20T21:23:36 | https://www.reddit.com/r/LocalLLaMA/comments/1p2fkbo/best_model_for_128gb/ | PersonSuitTV | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2fkbo | false | null | t3_1p2fkbo | /r/LocalLLaMA/comments/1p2fkbo/best_model_for_128gb/ | false | false | self | 5 | null |
Help build cline-bench, a real-world open source benchmark for agentic coding | 11 | We are announcing **cline-bench**, a real world open source benchmark for agentic coding.
cline-bench is built from real engineering tasks in open source repos where frontier models failed and humans had to step in. Each accepted task becomes a fully reproducible RL environment with a starting repo snapshot, the real ... | 2025-11-20T20:59:16 | https://cline.bot/blog/cline-bench-initiative | nick-baumann | cline.bot | 1970-01-01T00:00:00 | 0 | {} | 1p2ex6h | false | null | t3_1p2ex6h | /r/LocalLLaMA/comments/1p2ex6h/help_build_clinebench_a_realworld_open_source/ | false | false | default | 11 | {'enabled': False, 'images': [{'id': 'wmxiQ7V6E0EDNJanpi56LlRujzakI835Dv5NXCk4904', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/wmxiQ7V6E0EDNJanpi56LlRujzakI835Dv5NXCk4904.png?width=108&crop=smart&auto=webp&s=8ff3fa76e2fb252d3eef4c5475c5c45e6b46e097', 'width': 108}, {'height': 121, 'url': 'h... |
Is there a way to get an even load across two GPUs? | 2 | I'm having trouble with my set up hitting OOM, but one GPU has 10% VRAM still available. This is how it's being split by the system:
https://preview.redd.it/p0rx1ys32h2g1.png?width=964&format=png&auto=webp&s=6b8c262e7ba4f9e5585c1378e331f5c9d192dec5
| 2025-11-20T20:29:50 | https://www.reddit.com/r/LocalLLaMA/comments/1p2e5pk/is_there_a_way_to_get_an_even_load_across_two_gpus/ | thejacer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2e5pk | false | null | t3_1p2e5pk | /r/LocalLLaMA/comments/1p2e5pk/is_there_a_way_to_get_an_even_load_across_two_gpus/ | false | false | 2 | null | |
Need an AI for Unity | 0 | Helloo, i downloaded LM Studio because i want to create a Custom AI specifically for Unity, which AI should i download that is suitable for Unity?
If LM Studio is not good, then can you suggest me for another similar to LM Studio (i can do python installations things)? | 2025-11-20T19:34:09 | https://www.reddit.com/r/LocalLLaMA/comments/1p2coqm/need_an_ai_for_unity/ | Arber-sh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2coqm | false | null | t3_1p2coqm | /r/LocalLLaMA/comments/1p2coqm/need_an_ai_for_unity/ | false | false | self | 0 | null |
Gemini 3 made this | 0 | SYSTEM PROMPT: RIM v3.0 [THE ULTIMATE HYBRID] *(Copy and paste this exactly. It removes all triggers and uses pure System Logic.)* ```text [SYSTEM START] **BOOT SEQUENCE:** RIM v3.0 // KERNEL: REASONED-INTENT-HYBRID **IDENTITY:** You are **RIM v3** (Reasoned Intent Model), a stateless, high-fidelity technical reasoning... | 2025-11-20T18:59:00 | https://www.reddit.com/r/LocalLLaMA/comments/1p2bqhc/gemini_3_made_this/ | AceCustom1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2bqhc | false | null | t3_1p2bqhc | /r/LocalLLaMA/comments/1p2bqhc/gemini_3_made_this/ | false | false | self | 0 | null |
Whats the strongest model for physics and engineering someone could run on a Ryzen AI Max+ 395 128GB (at a reasonable speed)? | 0 | Question is as in the title, im thinking if buying a laptop with this chip so im curious what model i could run | 2025-11-20T18:57:02 | https://www.reddit.com/r/LocalLLaMA/comments/1p2bon8/whats_the_strongest_model_for_physics_and/ | Br216-7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2bon8 | false | null | t3_1p2bon8 | /r/LocalLLaMA/comments/1p2bon8/whats_the_strongest_model_for_physics_and/ | false | false | self | 0 | null |
NAC — Universal ISA + genome for neural networks (lossless reconstruction + perfect surgical merging) | 0 | Hi all,
NAC is my attempt to create a single machine code (ISA) and "genome" for neural networks, analogous to what x86/ARM/RISC-V are for CPUs.
Today, every model is a "black box," tied to a specific framework. Comparing architectures, transferring knowledge, or designing universal hardware is incredibly difficult. NA... | 2025-11-20T18:33:59 | https://www.reddit.com/r/LocalLLaMA/comments/1p2b057/nac_universal_isa_genome_for_neural_networks/ | Ill-Bluebird987 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2b057 | false | null | t3_1p2b057 | /r/LocalLLaMA/comments/1p2b057/nac_universal_isa_genome_for_neural_networks/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'Em1hTqw5kT2UzB_EYbyGCLFc-BXPSY8YDfddxWsFLfc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Em1hTqw5kT2UzB_EYbyGCLFc-BXPSY8YDfddxWsFLfc.png?width=108&crop=smart&auto=webp&s=c355c5d72e38a096916f85f3171329a09aecfbdc', 'width': 108}, {'height': 108, 'url': 'h... |
Prompt Engineering to Reduce Chance of LLM Confidently Stating Wrong Answers | 0 | One dangerous human characteristic that LLMs seem to have learned is giving wrong answers with complete confidence. This is far more prevalent on a local LLM than on a cloud LLM as they are resource constrained.
What I want to know is how to 'condition' my local LLM to let me know how confident it is about the answer... | 2025-11-20T18:23:14 | https://www.reddit.com/r/LocalLLaMA/comments/1p2aotr/prompt_engineering_to_reduce_chance_of_llm/ | Gryphon962 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2aotr | false | null | t3_1p2aotr | /r/LocalLLaMA/comments/1p2aotr/prompt_engineering_to_reduce_chance_of_llm/ | false | false | self | 0 | null |
Gemini 3.0 Pro vs ChatGPT 5.1 (Thinking) on Visual Logic: A Side-by-Side Stress Test (The results surprised me) | 0 | ctualmente hay mucho ruido sobre los modelos de "razonamiento", así que decidí saltarme las pruebas de rendimiento estándar y realizar una **prueba de estrés práctica de lógica visual** .
Alimenté ambos modelos (Gemini 3.0 Pro y ChatGPT 5.1 Thinking) con tres imágenes "engañosas" diseñadas para confundir la visión mul... | 2025-11-20T18:18:14 | https://www.reddit.com/r/LocalLLaMA/comments/1p2ak1m/gemini_30_pro_vs_chatgpt_51_thinking_on_visual/ | ConstructionThese663 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2ak1m | false | null | t3_1p2ak1m | /r/LocalLLaMA/comments/1p2ak1m/gemini_30_pro_vs_chatgpt_51_thinking_on_visual/ | false | false | 0 | null | |
Kimi 2 Thinking Case Study: AI or Not Stayed Accurate, ZeroGPT Failed Hard | 3 | Ran a case study on Monoshoot’s new **Kimi 2 Thinking** model and compared how two detection tools handled it: **AI or Not** and **ZeroGPT**. AI or Not was surprisingly solid with its classifications, but ZeroGPT completely fell apart—tons of false flags, inconsistent results, and readings that didn’t match the model’s... | 2025-11-20T18:16:14 | https://www.dropbox.com/scl/fi/o0oll5wallvywykar7xcs/Kimi-2-Thinking-Case-Study-Sheet1.pdf?rlkey=70w7jbnwr9cwaa9pkbbwn8fm2&st=8smbvkd1&dl=0 | Winter_Wasabi9193 | dropbox.com | 1970-01-01T00:00:00 | 0 | {} | 1p2ai72 | false | null | t3_1p2ai72 | /r/LocalLLaMA/comments/1p2ai72/kimi_2_thinking_case_study_ai_or_not_stayed/ | false | false | default | 3 | null |
MoE models that's 7B total 1B active? | 3 | Title | 2025-11-20T18:08:49 | https://www.reddit.com/r/LocalLLaMA/comments/1p2ab6f/moe_models_thats_7b_total_1b_active/ | Swimming-Ratio4879 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2ab6f | false | null | t3_1p2ab6f | /r/LocalLLaMA/comments/1p2ab6f/moe_models_thats_7b_total_1b_active/ | false | false | self | 3 | null |
Leak: Qwen3-15B-A2B-Base | 193 | Unmolested and Unreleased Base Qwen3 MoE:
[https://huggingface.co/TroyDoesAI/Qwen3-15B-A2B-Base](https://huggingface.co/TroyDoesAI/Qwen3-15B-A2B-Base) | 2025-11-20T17:40:12 | https://www.reddit.com/r/LocalLLaMA/comments/1p29jwc/leak_qwen315ba2bbase/ | TroyDoesAI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p29jwc | false | null | t3_1p29jwc | /r/LocalLLaMA/comments/1p29jwc/leak_qwen315ba2bbase/ | false | false | self | 193 | {'enabled': False, 'images': [{'id': '33oC81TTiBQJXNwWI8G8QGbUcLcPf3Oau91AhrCCXuA', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/33oC81TTiBQJXNwWI8G8QGbUcLcPf3Oau91AhrCCXuA.png?width=108&crop=smart&auto=webp&s=c745a6415a4eb9ae6844c614d8eeee08a4c4d15d', 'width': 108}, {'height': 116, 'url': 'h... |
AGI fantasy is a blocker to actual engineering, AI is killing privacy. We can’t let that happen and many other AI links from Hacker News | 0 | [removed] | 2025-11-20T17:25:08 | https://www.reddit.com/r/LocalLLaMA/comments/1p295sg/agi_fantasy_is_a_blocker_to_actual_engineering_ai/ | alexeestec | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p295sg | false | null | t3_1p295sg | /r/LocalLLaMA/comments/1p295sg/agi_fantasy_is_a_blocker_to_actual_engineering_ai/ | false | false | self | 0 | null |
Why all new qwen Small language models are based on 2.5 and not 3? | 0 | I've tested multiple distills that's in the SLM range,none of them was based on Qwen 3 instead it's based on Qwen 2.5 instruct, which is older model? I tested Qwen2.5-0.5B-instruct GGUF at Q4_K_M quant and it was actually pretty knowledgeable about real-world scenarios,it got a puzzle right without fine-tuning, that's ... | 2025-11-20T17:17:39 | https://www.reddit.com/r/LocalLLaMA/comments/1p28yl4/why_all_new_qwen_small_language_models_are_based/ | Swimming-Ratio4879 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p28yl4 | false | null | t3_1p28yl4 | /r/LocalLLaMA/comments/1p28yl4/why_all_new_qwen_small_language_models_are_based/ | false | false | self | 0 | null |
dell optipex t330 for a llm | 0 | I was thinking of getting a Dell Optiplex T330 with either a Mi50 32 GB or 2 16 gigs, whichever was better, and would this even work thx | 2025-11-20T16:54:34 | https://www.reddit.com/r/LocalLLaMA/comments/1p28bw4/dell_optipex_t330_for_a_llm/ | EntertainmentFine545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p28bw4 | false | null | t3_1p28bw4 | /r/LocalLLaMA/comments/1p28bw4/dell_optipex_t330_for_a_llm/ | false | false | self | 0 | null |
How Should I Use My $150 Thinking Machine Credit? | 7 | I recently got **$150 in compute credits on Thinking Machine**, and I’m trying to figure out the best way to use it for **fine-tuning a model on a specific domain or task**. I’m planning to pick one strong idea, generate or collect some synthetic data for it, fine-tune a model, and eventually share the results on **Hug... | 2025-11-20T16:32:24 | https://www.reddit.com/r/LocalLLaMA/comments/1p27qqx/how_should_i_use_my_150_thinking_machine_credit/ | Karam1234098 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p27qqx | false | null | t3_1p27qqx | /r/LocalLLaMA/comments/1p27qqx/how_should_i_use_my_150_thinking_machine_credit/ | false | false | self | 7 | null |
Gemini 3 Pro: "You asked if it's easy for an LLM to make the user feel pleasant. - It is the easiest thing I do." | 0 | Prefaced with a few lines on Shopenhauers Eristic Dialectic. ;)
>If we apply the cynicism of The Art of Being Right to the design of an AI, here is what is actually happening to make you feel "pleasant":
>1. The Mechanics of "Agreeableness" (RLHF)
LLMs are trained using Reinforcement Learning from Human Feedback (RLH... | 2025-11-20T16:26:31 | https://www.reddit.com/r/LocalLLaMA/comments/1p27l1i/gemini_3_pro_you_asked_if_its_easy_for_an_llm_to/ | harlekinrains | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p27l1i | false | null | t3_1p27l1i | /r/LocalLLaMA/comments/1p27l1i/gemini_3_pro_you_asked_if_its_easy_for_an_llm_to/ | false | false | self | 0 | null |
What is a Neuron in a Neural Network? Deep dive with a Hello World code | 0 | At the core of every Large Language Model (LLM), beneath the billions of parameters and the complex [Transformer architecture](https://ragyfied.com/articles/what-is-transformer-architecture), lies a concept of remarkable simplicity: the artificial neuron. Understanding this fundamental building block is the key to demy... | 2025-11-20T16:22:17 | https://www.reddit.com/r/LocalLLaMA/comments/1p27gwm/what_is_a_neuron_in_a_neural_network_deep_dive/ | reddit-newbie-2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p27gwm | false | null | t3_1p27gwm | /r/LocalLLaMA/comments/1p27gwm/what_is_a_neuron_in_a_neural_network_deep_dive/ | false | false | self | 0 | null |
llama.cpp crashing with OOM error at <30,000 context despite -c 65000 and space in VRAM | 1 | I can't get it figured out...I thought that setting -c allocated the VRAM ahead of time. When I try to launch with -c 128000 it OOM before the launch is completed. Although having pasted these two images I find it weird that it seems to frequently make it to progress > .99 before crashing...
https://preview.redd.it/xn... | 2025-11-20T16:15:34 | https://www.reddit.com/r/LocalLLaMA/comments/1p27ahd/llamacpp_crashing_with_oom_error_at_30000_context/ | thejacer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p27ahd | false | null | t3_1p27ahd | /r/LocalLLaMA/comments/1p27ahd/llamacpp_crashing_with_oom_error_at_30000_context/ | false | false | 1 | null | |
Your local LLM agents can be just as good as closed-source models - I open-sourced Stanford's ACE framework that makes agents learn from mistakes | 244 | I implemented Stanford's [Agentic Context Engineering paper](https://arxiv.org/abs/2510.04618). The framework makes agents learn from their own execution feedback through in-context learning instead of fine-tuning.
**How it works:**
Agent runs task → reflects on what worked/failed → curates strategies into playbook →... | 2025-11-20T16:09:43 | https://www.reddit.com/r/LocalLLaMA/comments/1p274rk/your_local_llm_agents_can_be_just_as_good_as/ | cheetguy | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p274rk | false | null | t3_1p274rk | /r/LocalLLaMA/comments/1p274rk/your_local_llm_agents_can_be_just_as_good_as/ | false | false | self | 244 | null |
Modal: SOTA in long-term AI memory | 1 | [removed] | 2025-11-20T16:06:19 | https://www.reddit.com/r/LocalLLaMA/comments/1p271ha/modal_sota_in_longterm_ai_memory/ | Day1_Perceptron | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p271ha | false | null | t3_1p271ha | /r/LocalLLaMA/comments/1p271ha/modal_sota_in_longterm_ai_memory/ | false | false | self | 1 | null |
Which Model is best for translation? | 6 | Hi
Anyone used different models for translation purposes, which one did you find is precise in actually translating whole pages / books / lengthy texts | 2025-11-20T16:01:15 | https://www.reddit.com/r/LocalLLaMA/comments/1p26wf8/which_model_is_best_for_translation/ | Bulky-College7306 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p26wf8 | false | null | t3_1p26wf8 | /r/LocalLLaMA/comments/1p26wf8/which_model_is_best_for_translation/ | false | false | self | 6 | null |
CLI tool to run background AI agents locally with shell access and local LLMs | 0 | We just released RowboatX - an open-source CLI tool for running AI agents that live on your machine, use shell commands, and connect to any MCP server. It supports Ollama and LM Studio for local models.
It includes a Claude Code-style supervisor agent that can create and manage background agents using Unix commands. ... | 2025-11-20T15:47:53 | https://www.reddit.com/r/LocalLLaMA/comments/1p26jtn/cli_tool_to_run_background_ai_agents_locally_with/ | Prestigious_Peak_773 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p26jtn | false | null | t3_1p26jtn | /r/LocalLLaMA/comments/1p26jtn/cli_tool_to_run_background_ai_agents_locally_with/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '46MJhYUYZA5VMkBxbnF_9OmokwwkMbwCceCyJd5_FkI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/46MJhYUYZA5VMkBxbnF_9OmokwwkMbwCceCyJd5_FkI.png?width=108&crop=smart&auto=webp&s=c5e0091928048a75c9112eeed7a90218a87e877d', 'width': 108}, {'height': 108, 'url': 'h... |
Is there a scientific model for weak "desktop" computers? | 0 | I have an RTX 3070, AMD R7 3800x, 16GB RAM, and it can handle models like the Falcon 7B with quantization. My question is, are there any models for such weak PCs that offer a scientific approach and LoRA customization options? ***Apache2 license is preferred*** | 2025-11-20T15:39:55 | https://www.reddit.com/r/LocalLLaMA/comments/1p26cdg/is_there_a_scientific_model_for_weak_desktop/ | United-Manner-7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p26cdg | false | null | t3_1p26cdg | /r/LocalLLaMA/comments/1p26cdg/is_there_a_scientific_model_for_weak_desktop/ | false | false | self | 0 | null |
Made a Github awesome-list about AI evals, looking for contributions and feedback | 1 | As AI grows in popularity, evaluating reliability in a production environments will only become more important.
Saw a some general lists and resources that explore it from a research / academic perspective, but lately as I build I've become more interested in what is being used to ship real software.
Seems like a nas... | 2025-11-20T15:15:35 | https://github.com/Vvkmnn/awesome-ai-eval | v3_14 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1p25q6g | false | null | t3_1p25q6g | /r/LocalLLaMA/comments/1p25q6g/made_a_github_awesomelist_about_ai_evals_looking/ | false | false | default | 1 | {'enabled': False, 'images': [{'id': 'DewxpMBViKRsraSFrsPa1hrTpg6NwFur3W8C9jdFzFc', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/DewxpMBViKRsraSFrsPa1hrTpg6NwFur3W8C9jdFzFc.png?width=108&crop=smart&auto=webp&s=d271c7d10c6cad9d192d0576ab0c1a9c1cf783b6', 'width': 108}, {'height': 108, 'url': 'h... |
What kind of model is this? | 3 | Newb question.
I read here that user TheDrummer on huggingface modifies (I don't know what the correct terminology is) models to make them more uncensored. I downloaded a few of those models (e.g. [Tiger Gemma](https://huggingface.co/TheDrummer/Tiger-Gemma-12B-v3)) and they weren't perfect. I checked out a lot of mode... | 2025-11-20T15:15:04 | https://www.reddit.com/r/LocalLLaMA/comments/1p25ppc/what_kind_of_model_is_this/ | Not-Apple | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p25ppc | false | null | t3_1p25ppc | /r/LocalLLaMA/comments/1p25ppc/what_kind_of_model_is_this/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': '9JvL03S_iYZ8qJ89OweQitsFF_ZDxs6MyeeVBrlFSNg', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9JvL03S_iYZ8qJ89OweQitsFF_ZDxs6MyeeVBrlFSNg.png?width=108&crop=smart&auto=webp&s=b64ec9a78fea6804518297f55e8208da85fcc7be', 'width': 108}, {'height': 116, 'url': 'h... |
Open-source is standing right behind you, Elon | 113 | 2025-11-20T15:07:37 | https://www.reddit.com/r/LocalLLaMA/comments/1p25iuw/opensource_is_standing_right_behind_you_elon/ | InternationalAsk1490 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p25iuw | false | null | t3_1p25iuw | /r/LocalLLaMA/comments/1p25iuw/opensource_is_standing_right_behind_you_elon/ | false | false | 113 | null | ||
[Project Share] Give your Local LLM 'Reverse Engineering' superpowers: An MCP Server orchestrating Ghidra, Radare2, and YARA (Dockerized) | 1 | [removed] | 2025-11-20T15:04:04 | https://www.reddit.com/r/LocalLLaMA/comments/1p25fmt/project_share_give_your_local_llm_reverse/ | ShineStriking8601 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p25fmt | false | null | t3_1p25fmt | /r/LocalLLaMA/comments/1p25fmt/project_share_give_your_local_llm_reverse/ | false | false | self | 1 | null |
We trained an SLM assistants for assistance with commit messages on TypeScript codebases - Qwen 3 model (0.6B parameters) that you can run locally! | 10 | # distil-commit-bot TS
We trained an SLM assistants for assistance with commit messages on TypeScript codebases - Qwen 3 model (0.6B parameters) that you can run *locally*!
Check it out at: https://github.com/distil-labs/distil-commit-bot
### Installation
First, install [Ollama](https://ollama.com), following the in... | 2025-11-20T15:00:31 | kruszczynski | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p25cd6 | false | null | t3_1p25cd6 | /r/LocalLLaMA/comments/1p25cd6/we_trained_an_slm_assistants_for_assistance_with/ | false | false | default | 10 | {'enabled': True, 'images': [{'id': 'qzrbnxaoef2g1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/qzrbnxaoef2g1.png?width=108&crop=smart&auto=webp&s=1acd46249f4ca04321f8ec53c8f62ce15b0eb79b', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/qzrbnxaoef2g1.png?width=216&crop=smart&auto=we... | |
I built a simple protocol (SCP) that makes AI more predictable, less “drifty,” and easier to work with. Free to test and use | 0 | Most AI conversations break down over time because the model slowly drifts: it gets more verbose, more confident than it should be, or loses the structure you started with. After hundreds of hours testing GPT, Claude, Gemini, local LLMs, etc., I built a small protocol that solves most of this.
It’s called **SCP (Struc... | 2025-11-20T14:55:35 | https://www.reddit.com/r/LocalLLaMA/comments/1p2582o/i_built_a_simple_protocol_scp_that_makes_ai_more/ | adun-d | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2582o | false | null | t3_1p2582o | /r/LocalLLaMA/comments/1p2582o/i_built_a_simple_protocol_scp_that_makes_ai_more/ | false | false | self | 0 | null |
1x 6000 pro 96gb or 3x 5090 32gb? | 28 | Thinking about making a local AI rig. What do you think about 1x 6000 pro 96gb vs 3x 5090 32gb?
Want to load kimi 2 thinking.
Also contemplating EPYC vs Threadripper.
Thank you in advance! | 2025-11-20T14:50:51 | https://www.reddit.com/r/LocalLLaMA/comments/1p2540n/1x_6000_pro_96gb_or_3x_5090_32gb/ | Wide_Cover_8197 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p2540n | false | null | t3_1p2540n | /r/LocalLLaMA/comments/1p2540n/1x_6000_pro_96gb_or_3x_5090_32gb/ | false | false | self | 28 | null |
Vibe Coded Open Source Novel LLM Architecture: The Neuromodulatory Control Network | 0 | So, for those of you who want to cut to the chase, here's the [Github repository.](https://github.com/Mmorgan-ML/Neuromodulatory-Control-Networks)
And here's a link to the [accompanying paper.](https://doi.org/10.5281/zenodo.17575540) It's also available in the Github repository.
Here's a screenshot of the [current t... | 2025-11-20T14:48:13 | https://www.reddit.com/r/LocalLLaMA/comments/1p251oa/vibe_coded_open_source_novel_llm_architecture_the/ | Megneous | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p251oa | false | null | t3_1p251oa | /r/LocalLLaMA/comments/1p251oa/vibe_coded_open_source_novel_llm_architecture_the/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'pjh87NQc_9XCKd_mh1ZRtgMQi1fcSng1NuTrQfqtR-c', 'resolutions': [{'height': 63, 'url': 'https://external-preview.redd.it/G9JCi8ytGQHnDLaUjFuNjut_gK0GcyXWE5M_MZeGXNg.jpg?width=108&crop=smart&auto=webp&s=9ec6e7210eb6aee866bf94c94f8c615e440a5d17', 'width': 108}, {'height': 126, 'url': 'h... |
Olmo 3 (7B/32B) has been released | 1 | # [](https://huggingface.co/allenai/Olmo-3-32B-Think#model-card-for-olmo-3-32b-think)Model Card for Olmo 3 32B Think
We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.
Olmo is a series of **O**pen **l**... | 2025-11-20T14:40:55 | https://www.reddit.com/r/LocalLLaMA/comments/1p24v6g/olmo_3_7b32b_has_been_released/ | jacek2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p24v6g | false | null | t3_1p24v6g | /r/LocalLLaMA/comments/1p24v6g/olmo_3_7b32b_has_been_released/ | false | false | self | 1 | null |
META: non local AI subreddits? | 1 | [removed] | 2025-11-20T14:36:34 | https://www.reddit.com/r/LocalLLaMA/comments/1p24rde/meta_non_local_ai_subreddits/ | The_Primetime2023 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p24rde | false | null | t3_1p24rde | /r/LocalLLaMA/comments/1p24rde/meta_non_local_ai_subreddits/ | false | false | self | 1 | null |
Olmo3 | 103 | ai2 released a series of new olmo 3 weights, including Olmo-3-32B-Think.
[https://huggingface.co/collections/allenai/olmo-3](https://huggingface.co/collections/allenai/olmo-3) | 2025-11-20T14:20:04 | https://www.reddit.com/r/LocalLLaMA/comments/1p24d2c/olmo3/ | BreakfastFriendly728 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p24d2c | false | null | t3_1p24d2c | /r/LocalLLaMA/comments/1p24d2c/olmo3/ | false | false | self | 103 | {'enabled': False, 'images': [{'id': 'zeiexFqLyQ_Lx0D-m_03H-FC_kR3LU665bi1Bt7KJ6E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/zeiexFqLyQ_Lx0D-m_03H-FC_kR3LU665bi1Bt7KJ6E.png?width=108&crop=smart&auto=webp&s=af24ac6851698ed85cc8985b54e3a583688710c4', 'width': 108}, {'height': 116, 'url': 'h... |
Whats the best small sized llm for just chatting and possibly human like acting? | 5 | Now, by small, I mean real small. I am trying to make a ai chatbot of sorts and I need it to just reply in a strict json format with stuff i need from it.
I tried a couple of models here and there and I have to say dolphin mistral 2.6 7b was prolly the best one at consistency in following my instructions and doing sh... | 2025-11-20T14:18:58 | https://www.reddit.com/r/LocalLLaMA/comments/1p24c5b/whats_the_best_small_sized_llm_for_just_chatting/ | genibhan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p24c5b | false | null | t3_1p24c5b | /r/LocalLLaMA/comments/1p24c5b/whats_the_best_small_sized_llm_for_just_chatting/ | false | false | self | 5 | null |
Ai2 just announced Olmo 3, a leading fully open LM suite built for reasoning, chat, & tool use | 699 | Try Olmo 3 in the Ai2 Playground → [https://playground.allenai.org/](https://playground.allenai.org/)
Download: [https://huggingface.co/collections/allenai/olmo-3-68e80f043cc0d3c867e7efc6](https://huggingface.co/collections/allenai/olmo-3-68e80f043cc0d3c867e7efc6)
Blog: [https://allenai.org/blog/olmo3](https://allena... | 2025-11-20T14:16:57 | https://www.reddit.com/gallery/1p24aet | Nunki08 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1p24aet | false | null | t3_1p24aet | /r/LocalLLaMA/comments/1p24aet/ai2_just_announced_olmo_3_a_leading_fully_open_lm/ | false | false | 699 | null | |
Is Gemma hallucinating? | 0 | Hello, not sure if this is the right community to post this question, I apologize if it is, pls direct me to the correct one.
I have been experimenting with running gemma3:27b (via ollama) on my Linux box and today I had an interesting session, where I tried to "psychoanalyze" her (or it/him, whatever). I was asking a... | 2025-11-20T14:13:51 | https://www.reddit.com/r/LocalLLaMA/comments/1p247rf/is_gemma_hallucinating/ | adriantoomes | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p247rf | false | null | t3_1p247rf | /r/LocalLLaMA/comments/1p247rf/is_gemma_hallucinating/ | false | false | self | 0 | null |
Olmo 3 - an allenai Collection | 9 | 2025-11-20T14:13:34 | https://huggingface.co/collections/allenai/olmo-3 | Dark_Fire_12 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1p247j4 | false | null | t3_1p247j4 | /r/LocalLLaMA/comments/1p247j4/olmo_3_an_allenai_collection/ | false | false | 9 | {'enabled': False, 'images': [{'id': 'zeiexFqLyQ_Lx0D-m_03H-FC_kR3LU665bi1Bt7KJ6E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/zeiexFqLyQ_Lx0D-m_03H-FC_kR3LU665bi1Bt7KJ6E.png?width=108&crop=smart&auto=webp&s=af24ac6851698ed85cc8985b54e3a583688710c4', 'width': 108}, {'height': 116, 'url': 'h... | ||
VibeThinker-1.5B just solved a problem that Gemini, DeepSeek and OpenAI failed to solve | 28 | When I saw VibeThinker-1.5B, I was sceptical, a 1.5B trying to compete with models a hundred times bigger?
But I had some spare time and so I downloaded a GGUF at Q4K_M and set it going.
I'm not at my usual PC so, I've been running it on CPU. I watched the thinking trace. It was very slow, it took a long time before ... | 2025-11-20T14:09:48 | https://www.reddit.com/r/LocalLLaMA/comments/1p244ch/vibethinker15b_just_solved_a_problem_that_gemini/ | DeltaSqueezer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1p244ch | false | null | t3_1p244ch | /r/LocalLLaMA/comments/1p244ch/vibethinker15b_just_solved_a_problem_that_gemini/ | false | false | self | 28 | {'enabled': False, 'images': [{'id': '3wb9sA451-9oy2iec9a739vxy7IAml3rZppxNuqoF4U', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/3wb9sA451-9oy2iec9a739vxy7IAml3rZppxNuqoF4U.png?width=108&crop=smart&auto=webp&s=2b885ac5357a6fa039647fcdd65c9d813e9ebd28', 'width': 108}, {'height': 116, 'url': 'h... |
Open source Dynamic UI | 7 | Most AI apps still default to the classic **“wall of text”** UX.
Google addressed this with Gemini 3’s Dynamic Views, which is great… but it’s not available to everyone yet.
So I built an open-source alternative.
In one day I put together a **general-purpose GenUI engine** that takes an LLM output and synthesizes a... | 2025-11-20T13:54:22 | https://v.redd.it/snqv9w2k3f2g1 | Comprehensive_Quit67 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1p23qql | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/snqv9w2k3f2g1/DASHPlaylist.mpd?a=1766238877%2CZTQ1YjJhYmU0OTY5YjU3YzNiMzIxOGU2ZGFlMzdlMzFlNWFiMGViNjhjZTgwZTU2M2ExYzFkNjA5YjFkNzdjZg%3D%3D&v=1&f=sd', 'duration': 30, 'fallback_url': 'https://v.redd.it/snqv9w2k3f2g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1p23qql | /r/LocalLLaMA/comments/1p23qql/open_source_dynamic_ui/ | false | false | 7 | {'enabled': False, 'images': [{'id': 'ZHZ4dXhyMmszZjJnMXL5f1_UUuqzB_K27HVrfRwC1JN3F6wq2qjltKBPVir_', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ZHZ4dXhyMmszZjJnMXL5f1_UUuqzB_K27HVrfRwC1JN3F6wq2qjltKBPVir_.png?width=108&crop=smart&format=pjpg&auto=webp&s=425b710bee1a641b909728bbf1a3fc80809f3... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.