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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Qwen 2.5 Coder + Ollama + LiteLLM + Claude Code | 1 | I am trying to run Qwen 2.5 Coder locally through Ollama, I have setup LiteLLM and Claude Code manages to call the model correctly, and receives a response. But I can't get it to properly call tools.
Look at some of the outputs I get:
> /init ... | 2025-12-19T17:23:34 | https://www.reddit.com/r/LocalLLaMA/comments/1pqquuf/qwen_25_coder_ollama_litellm_claude_code/ | Bornash_Khan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqquuf | false | null | t3_1pqquuf | /r/LocalLLaMA/comments/1pqquuf/qwen_25_coder_ollama_litellm_claude_code/ | false | false | self | 1 | null |
50% of all r/LocalLLaMA posts in 2025 summed up in one image: | 10 | 2025-12-19T17:02:07 | Porespellar | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqqbcx | false | null | t3_1pqqbcx | /r/LocalLLaMA/comments/1pqqbcx/50_of_all_rlocalllama_posts_in_2025_summed_up_in/ | false | false | default | 10 | {'enabled': True, 'images': [{'id': 'jm8vbgbjz68g1', 'resolutions': [{'height': 78, 'url': 'https://preview.redd.it/jm8vbgbjz68g1.jpeg?width=108&crop=smart&auto=webp&s=9f112e3bd78074fbb47416982cf39ce0c9e75b39', 'width': 108}, {'height': 157, 'url': 'https://preview.redd.it/jm8vbgbjz68g1.jpeg?width=216&crop=smart&auto=w... | ||
keep the faith | 11 | 2025-12-19T16:55:35 | jacek2023 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqq52w | false | null | t3_1pqq52w | /r/LocalLLaMA/comments/1pqq52w/keep_the_faith/ | false | false | default | 11 | {'enabled': True, 'images': [{'id': 'wfj1sd6cy68g1', 'resolutions': [{'height': 49, 'url': 'https://preview.redd.it/wfj1sd6cy68g1.png?width=108&crop=smart&auto=webp&s=1974a2c6eeb4334ee119c92eaf8d647600a275f6', 'width': 108}, {'height': 99, 'url': 'https://preview.redd.it/wfj1sd6cy68g1.png?width=216&crop=smart&auto=webp... | ||
Currently testing yet another tool nobody asked for | 2 | 2025-12-19T16:54:23 | https://v.redd.it/fe0z1n05y68g1 | randomNinja64 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqq419 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/fe0z1n05y68g1/DASHPlaylist.mpd?a=1768755282%2CMzg5NTYwZDdkNzkxZTA2ZjAzNTNlNzY2MjZlYjNjMmM3NjBkNjc5YTgzZWI2YTdlMjU4ZTAwMzEwZTNkMGM4OA%3D%3D&v=1&f=sd', 'duration': 38, 'fallback_url': 'https://v.redd.it/fe0z1n05y68g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1pqq419 | /r/LocalLLaMA/comments/1pqq419/currently_testing_yet_another_tool_nobody_asked/ | false | false | 2 | {'enabled': False, 'images': [{'id': 'MnJxMWg4MTV5NjhnMSP1_4XDvXzgedFXh2ldRZP00D9KRyB-gIf0tTpe2O-2', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/MnJxMWg4MTV5NjhnMSP1_4XDvXzgedFXh2ldRZP00D9KRyB-gIf0tTpe2O-2.png?width=108&crop=smart&format=pjpg&auto=webp&s=071d24d753c186ac9c0c7fb3f0766f0469a5c... | ||
Career Advice in AI — Notes from an Andrew Ng Lecture | 328 | **\[1\] A Golden Age for AI Careers**
* Andrew Ng emphasizes that this is the best time ever to build a career in AI. He notes that the complexity of tasks AI can handle is doubling approximately every seven months, meaning progress is accelerating, not slowing down.
**\[2\] The Power of AI Coding Tools**
* Staying ... | 2025-12-19T16:31:46 | Dear-Success-1441 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqpj29 | false | null | t3_1pqpj29 | /r/LocalLLaMA/comments/1pqpj29/career_advice_in_ai_notes_from_an_andrew_ng/ | false | false | default | 328 | {'enabled': True, 'images': [{'id': 'cu5vt8lnt68g1', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/cu5vt8lnt68g1.png?width=108&crop=smart&auto=webp&s=87d94be7398f97b38281ac921fd55e2bb36ea5a2', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/cu5vt8lnt68g1.png?width=216&crop=smart&auto=web... | |
How to view all the parameters represented in numbers inside GGUF/safetensors files? | 1 | I'd like to view the actual numerical values of the tensors (e.g. for a 7B model, all 7B tensors, or a portion of them if it takes too long to display all 7B), instead of the kind of "overview" shown in the attached picture.
Any pointers are appreciated!
https://preview.redd.it/hr3kry21r68g1.png?width=1373&format=... | 2025-12-19T16:18:07 | https://www.reddit.com/r/LocalLLaMA/comments/1pqp6g2/how_to_view_all_the_parameters_represented_in/ | Moneyy_Backk | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqp6g2 | false | null | t3_1pqp6g2 | /r/LocalLLaMA/comments/1pqp6g2/how_to_view_all_the_parameters_represented_in/ | false | false | 1 | null | |
What If OpenAI has Bigger model internally ? | 0 | like 100 times bigger (parameters are exponential)than what they are giving to us? Maybe they did reach agi already. don't you think? | 2025-12-19T16:17:45 | https://www.reddit.com/r/LocalLLaMA/comments/1pqp63q/what_if_openai_has_bigger_model_internally/ | Glass_Philosophy6941 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqp63q | false | null | t3_1pqp63q | /r/LocalLLaMA/comments/1pqp63q/what_if_openai_has_bigger_model_internally/ | false | false | self | 0 | null |
New to this | 0 | I want to use my second PC to run locally.
Got two questions..
1.What are you guys running and why?
2.What would you recommend for a beginner? Just saying, I can not code at all, but I know the bare minimum of basics.
My needs: have no idea, maybe a local chatgpt like machine.. I am browsing this sub for a while ... | 2025-12-19T16:04:33 | https://www.reddit.com/r/LocalLLaMA/comments/1pqotx9/new_to_this/ | Sea-Departure482 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqotx9 | false | null | t3_1pqotx9 | /r/LocalLLaMA/comments/1pqotx9/new_to_this/ | false | false | self | 0 | null |
Chinese researchers unveil "LightGen": An all-optical chip that outperforms Nvidia’s A100 by 100x | 201 | New research from SJTU and Tsinghua (these are top tier labs, not slopmonsters like East China Normal University etc.). | 2025-12-19T15:55:23 | https://www.science.org/doi/10.1126/science.adv7434 | entsnack | science.org | 1970-01-01T00:00:00 | 0 | {} | 1pqoldt | false | null | t3_1pqoldt | /r/LocalLLaMA/comments/1pqoldt/chinese_researchers_unveil_lightgen_an_alloptical/ | false | false | default | 201 | null |
Qwen released Qwen-Image-Layered on Hugging face. | 590 | Hugging face: [https://huggingface.co/Qwen/Qwen-Image-Layered](https://huggingface.co/Qwen/Qwen-Image-Layered)
Photoshop-grade layering
Physically isolated RGBA layers with true native editability
Prompt-controlled structure
Explicitly specify 3–10 layers — from coarse layouts to fine-grained details
Infinite decompos... | 2025-12-19T15:51:45 | https://www.reddit.com/gallery/1pqoi6i | Difficult-Cap-7527 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pqoi6i | false | null | t3_1pqoi6i | /r/LocalLLaMA/comments/1pqoi6i/qwen_released_qwenimagelayered_on_hugging_face/ | false | false | 590 | null | |
Z-Image Desktop App with MPS and Vulkan Acceleration | 1 | [removed] | 2025-12-19T15:46:54 | https://github.com/WaveSpeedAI/wavespeed-desktop | ciiic | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pqodp8 | false | null | t3_1pqodp8 | /r/LocalLLaMA/comments/1pqodp8/zimage_desktop_app_with_mps_and_vulkan/ | false | false | default | 1 | null |
Best local AI for RX 9070XT | 1 | [removed] | 2025-12-19T15:46:22 | https://www.reddit.com/r/LocalLLaMA/comments/1pqod5q/best_local_ai_for_rx_9070xt/ | Kyren223 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqod5q | false | null | t3_1pqod5q | /r/LocalLLaMA/comments/1pqod5q/best_local_ai_for_rx_9070xt/ | false | false | self | 1 | null |
Best option for local company LLM | 8 | **Setup:**
In my company (roughly 50 people) we have a lot of knowledge and data, that is pretty well structured but currently hard to search. This includes CRM data, meeting transcripts, bookkeeping data, project management tool data. So there is data privacy relevant stuff there, which I don't want to upload to ... | 2025-12-19T15:35:50 | https://www.reddit.com/r/LocalLLaMA/comments/1pqo3mg/best_option_for_local_company_llm/ | DerDave | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqo3mg | false | null | t3_1pqo3mg | /r/LocalLLaMA/comments/1pqo3mg/best_option_for_local_company_llm/ | false | false | self | 8 | null |
OllamaFX v0.3.0 released: Native JavaFX client for Ollama with Markdown support, i18n, and more! 🦙✨ | 0 | Hello everyone! After a week of hard work, I’m excited to announce that **OllamaFX v0.3.0** is officially out. This release brings significant features and improvements to the desktop experience:
🔨 **GitHub Repo** \-> [https://github.com/fredericksalazar/OllamaFX](https://github.com/fredericksalazar/OllamaFX) (Contri... | 2025-12-19T15:35:13 | https://www.reddit.com/gallery/1pqo33m | Electronic-Reason582 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pqo33m | false | null | t3_1pqo33m | /r/LocalLLaMA/comments/1pqo33m/ollamafx_v030_released_native_javafx_client_for/ | false | false | 0 | null | |
System ram that bad ? | 0 | So I just got my hands on a 1u amd epyc 7642 server for £209 with no ram and I’m looking to get 256gb of ram for it and I was wondering how well it would do for tinking with ollama llms ? I had a look in the sub for a post like this before but couldn’t find anything | 2025-12-19T15:33:30 | https://www.reddit.com/r/LocalLLaMA/comments/1pqo1j4/system_ram_that_bad/ | Totalkiller4 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqo1j4 | false | null | t3_1pqo1j4 | /r/LocalLLaMA/comments/1pqo1j4/system_ram_that_bad/ | false | false | self | 0 | null |
When life gives you a potato PC, turn it into Vodka | 5 | I've (mostly) been lurking here and on r/r/LocalLLaMA for about 3 months now. I got back into computers by way of a disc herniation knocking me on my ass for several months, kids wanting to play games to cheer me up, Wii modding, emulation and retro-gaming.
I've read a lot of stuff. Some great, some baffling, and some... | 2025-12-19T15:26:08 | https://www.reddit.com/r/LocalLLaMA/comments/1pqnuu7/when_life_gives_you_a_potato_pc_turn_it_into_vodka/ | Impossible-Power6989 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqnuu7 | false | null | t3_1pqnuu7 | /r/LocalLLaMA/comments/1pqnuu7/when_life_gives_you_a_potato_pc_turn_it_into_vodka/ | false | false | self | 5 | null |
Is Gemma 9B still the best dense model of that size in December 2025? | 13 | Hi. I have been missing news for some time. What are the best models of 4B and 9B sizes, for basic NLP (not fine tuning)? Are Gemma 3 4B and Gemma2 9B still the best ones?
Thanks | 2025-12-19T15:06:29 | https://www.reddit.com/r/LocalLLaMA/comments/1pqndio/is_gemma_9b_still_the_best_dense_model_of_that/ | ihatebeinganonymous | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqndio | false | null | t3_1pqndio | /r/LocalLLaMA/comments/1pqndio/is_gemma_9b_still_the_best_dense_model_of_that/ | false | false | self | 13 | null |
An experiment in safety enhancement: increasing refusals in a local model | 3 | Loosely inspired by Goody-2, I added an `--invert` option to the ablation codebase I've been working with recently, enabling the easy addition (or amplification) of the refusal direction to the model. I've uploaded the result, a model derived from Gemma 3 12B which will categorically refuse *at length* when asked to he... | 2025-12-19T14:57:43 | https://www.reddit.com/r/LocalLLaMA/comments/1pqn5hy/an_experiment_in_safety_enhancement_increasing/ | grimjim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqn5hy | false | null | t3_1pqn5hy | /r/LocalLLaMA/comments/1pqn5hy/an_experiment_in_safety_enhancement_increasing/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'Dg2HKmL4HVNIjmto9jWnqbJ-0sA2lhqy87zOygaXMhM', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/Dg2HKmL4HVNIjmto9jWnqbJ-0sA2lhqy87zOygaXMhM.png?width=108&crop=smart&auto=webp&s=d2c33d3059e7d79fc0f2686995ad60a36aeb8627', 'width': 108}, {'height': 116, 'url': 'h... |
Built a one-scene AI text adventure running on llama-3.1-8B. It's live. | 19 | So I was playing around with prompts to create more engaging, live like agent personas, and somehow accidentally created this: A one-scene mini-game, running off of llama-3.1-8b. Convince a bouncer to let you into an underground Berlin club. 7 turns. Vibe-based scoring. No scripted answers. Curious what weird approache... | 2025-12-19T14:54:54 | http://sventhebouncer.com | mikiobraun | sventhebouncer.com | 1970-01-01T00:00:00 | 0 | {} | 1pqn344 | false | null | t3_1pqn344 | /r/LocalLLaMA/comments/1pqn344/built_a_onescene_ai_text_adventure_running_on/ | false | false | default | 19 | null |
GLM 4.7 is Coming? | 255 | https://github.com/vllm-project/vllm/pull/30876 | 2025-12-19T14:52:18 | InternationalAsk1490 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqn0vq | false | null | t3_1pqn0vq | /r/LocalLLaMA/comments/1pqn0vq/glm_47_is_coming/ | false | false | default | 255 | {'enabled': True, 'images': [{'id': '206mfj3dc68g1', 'resolutions': [{'height': 163, 'url': 'https://preview.redd.it/206mfj3dc68g1.jpeg?width=108&crop=smart&auto=webp&s=6e6eef8eec9cf18eb7e504adf368aeaeb41ea69a', 'width': 108}, {'height': 326, 'url': 'https://preview.redd.it/206mfj3dc68g1.jpeg?width=216&crop=smart&auto=... | |
How to monitor ai agent interactions with apis | 3 | We built ai agents that call our internal apis, agent decides something, calls an api, reads response, calls another api, whatever. works fine in testing but we dont have visibility into production. Like we can see in logs "payment api was called 5000 times today" but we can't see what agent got stuck in a loop. Also c... | 2025-12-19T14:38:31 | https://www.reddit.com/r/LocalLLaMA/comments/1pqmp4g/how_to_monitor_ai_agent_interactions_with_apis/ | kachorisabzi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqmp4g | false | null | t3_1pqmp4g | /r/LocalLLaMA/comments/1pqmp4g/how_to_monitor_ai_agent_interactions_with_apis/ | false | false | self | 3 | null |
Seed OSS 36b made me reconsider my life choices. | 102 | 5AM, - Me: Hello Seed, write me a complete new library does this and that, use that internal library as a reference but extend it to handle more data formats. Unify the data abstraction layer so data from one format can be exported to other format. Analyse the code in the internal lib directory and create a similar lib... | 2025-12-19T14:15:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pqm5g4/seed_oss_36b_made_me_reconsider_my_life_choices/ | ChopSticksPlease | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqm5g4 | false | null | t3_1pqm5g4 | /r/LocalLLaMA/comments/1pqm5g4/seed_oss_36b_made_me_reconsider_my_life_choices/ | false | false | self | 102 | null |
I built CodeGate – An open-source CLI to detect AI-hallucinated packages | 0 | Hey everyone,
I've been working on a security tool called CodeGate.
The motivation started as I noticed that AI coding agents often hallucinate package names (like skimage instead of scikit-image). If an attacker registers these names on PyPI, they can compromise the agent instantly.
To solve this I built a CLI that... | 2025-12-19T13:50:56 | https://www.reddit.com/r/LocalLLaMA/comments/1pqllg3/i_built_codegate_an_opensource_cli_to_detect/ | Longjumping-Call5015 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqllg3 | false | null | t3_1pqllg3 | /r/LocalLLaMA/comments/1pqllg3/i_built_codegate_an_opensource_cli_to_detect/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'f4AoC44mEv4RG-QIDCY0N3_iK6DTaiVInMMS2whqFks', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/f4AoC44mEv4RG-QIDCY0N3_iK6DTaiVInMMS2whqFks.png?width=108&crop=smart&auto=webp&s=d242d30fd62d0060b3c6173af023a4ef83a751d7', 'width': 108}, {'height': 108, 'url': 'h... |
Using GGUF with sglang | 3 | Today I wanted to run Devstral 2 on my sglang server. The model is a bit big for my hardware so I opened the quantizations page in huggingface and copied from there: \`--model unsloth/Devstral-2-123B-Instruct-2512-GGUF\`
sglang protested: \`ValueError: Unrecognized model in unsloth/Devstral-2-123B-Instruct-2512-GGUF.\... | 2025-12-19T13:45:00 | https://www.reddit.com/r/LocalLLaMA/comments/1pqlgp7/using_gguf_with_sglang/ | Low-Refrigerator5031 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqlgp7 | false | null | t3_1pqlgp7 | /r/LocalLLaMA/comments/1pqlgp7/using_gguf_with_sglang/ | false | false | self | 3 | null |
Releasing an OpenAI API compatible agent-focused application | 0 | Hey everyone,
I'm making this post to see if there's any interest from this community in the release of a tool I've been working on for the past couple of months after work.
The main reason I made it is because:
\- My work offers it's own OpenAI compatible API (Azure) for accessing LLMs, as well as it's own fron... | 2025-12-19T13:16:37 | https://www.reddit.com/r/LocalLLaMA/comments/1pqkubc/releasing_an_openai_api_compatible_agentfocused/ | dylantestaccount | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqkubc | false | null | t3_1pqkubc | /r/LocalLLaMA/comments/1pqkubc/releasing_an_openai_api_compatible_agentfocused/ | false | false | self | 0 | null |
Looking for Qwen3-30B-A3B alternatives for academic / research use | 4 | I am a student with a computer equipped with 32 GB of RAM, and I am looking for strong alternatives to Qwen3-30B-A3B that offer robust conversational abilities as well as solid scientific and academic reasoning capabilities. My primary use case involves working with peer-reviewed articles, subject-specific academic pro... | 2025-12-19T12:56:34 | https://www.reddit.com/r/LocalLLaMA/comments/1pqkf3m/looking_for_qwen330ba3b_alternatives_for_academic/ | RelationshipSilly124 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqkf3m | false | null | t3_1pqkf3m | /r/LocalLLaMA/comments/1pqkf3m/looking_for_qwen330ba3b_alternatives_for_academic/ | false | false | self | 4 | null |
Chrome Browser Extension -- AI Chat Extractor | 1 | 'AI Chat Extractor' is a Chrome Browser extension to help users to extract and export AI conversations from Claudeai, ChatGPT, and DeepSeek to Markdown/PDF format for backup and sharing purposes.
Head to link below to try it out:
[https://chromewebstore.google.com/detail/ai-chat-extractor/bjdacanehieegenbifmjadckngc... | 2025-12-19T12:53:23 | https://www.reddit.com/r/LocalLLaMA/comments/1pqkcte/chrome_browser_extension_ai_chat_extractor/ | Ironwire2020 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqkcte | false | null | t3_1pqkcte | /r/LocalLLaMA/comments/1pqkcte/chrome_browser_extension_ai_chat_extractor/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'xuCdR5AT9BSONLP3XE6voThkNTimY8NFfvN8mtcs7R4', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/xuCdR5AT9BSONLP3XE6voThkNTimY8NFfvN8mtcs7R4.jpeg?width=108&crop=smart&auto=webp&s=16bc1df7654c8fa2df9eda4d1a7116320376523d', 'width': 108}], 'source': {'height': 1... |
Graph Rag Medical SLM | 5 | Anyone here with experience or interest in SLMs with a knowledge-graph core?
I’ve just finished building a medical graph information map with ~5k nodes and ~25k edges. It contains medical terms classified under body parts, cellular structures, diseases, symptoms, treatment methods, diagnostic tools, and risk factors. ... | 2025-12-19T12:50:31 | https://www.reddit.com/r/LocalLLaMA/comments/1pqkatp/graph_rag_medical_slm/ | vagobond45 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqkatp | false | null | t3_1pqkatp | /r/LocalLLaMA/comments/1pqkatp/graph_rag_medical_slm/ | false | false | self | 5 | null |
Gemma Scope 2 : Open suite of tools for language model interpretability | 1 | Hugging face: [https://huggingface.co/collections/google/gemma-scope-2](https://huggingface.co/collections/google/gemma-scope-2)
Largest open release of interpretability tools (over 1 trillion parameters trained!) Works as a microscope to analyze all Gemma 3 models' internal activations. Advanced tools for analyzin... | 2025-12-19T12:46:07 | https://www.reddit.com/gallery/1pqk7sd | Difficult-Cap-7527 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pqk7sd | false | null | t3_1pqk7sd | /r/LocalLLaMA/comments/1pqk7sd/gemma_scope_2_open_suite_of_tools_for_language/ | false | false | 1 | null | |
New automation in VoltAgent: event-driven AI agents with triggers & actions | 3 | We were already writing AI agents with VoltAgent (TypeScript), but automation always lived somewhere else.
We wanted it to live next to the agent. So we added built-in triggers and actions directly into the VoltAgent console.
Agents can start on events like Slack messages, Gmail, GitHub webhooks, Airtable updates, or... | 2025-12-19T12:40:30 | https://www.reddit.com/r/LocalLLaMA/comments/1pqk3uv/new_automation_in_voltagent_eventdriven_ai_agents/ | necati-ozmen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqk3uv | false | null | t3_1pqk3uv | /r/LocalLLaMA/comments/1pqk3uv/new_automation_in_voltagent_eventdriven_ai_agents/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'NYHpmbQRn7rAinmrKJlFYeIVFvI_BN173hZAr0ylnR4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/NYHpmbQRn7rAinmrKJlFYeIVFvI_BN173hZAr0ylnR4.png?width=108&crop=smart&auto=webp&s=5ec3a00d824610d07bc7f692e5dde19879623eaf', 'width': 108}, {'height': 113, 'url': 'h... |
Need your input on hardware we are looking at buying | 1 | [removed] | 2025-12-19T12:30:57 | https://www.reddit.com/r/LocalLLaMA/comments/1pqjxkd/need_your_input_on_hardware_we_are_looking_at/ | Longjumping-Gold8783 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqjxkd | false | null | t3_1pqjxkd | /r/LocalLLaMA/comments/1pqjxkd/need_your_input_on_hardware_we_are_looking_at/ | false | false | self | 1 | null |
Need your thoughts on hardware? | 1 | [removed] | 2025-12-19T12:26:52 | https://www.reddit.com/r/LocalLLaMA/comments/1pqjuo1/need_your_thoughts_on_hardware/ | Longjumping-Gold8783 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqjuo1 | false | null | t3_1pqjuo1 | /r/LocalLLaMA/comments/1pqjuo1/need_your_thoughts_on_hardware/ | false | false | self | 1 | null |
Known Pretraining Tokens for LLMs | 19 | Pretraining compute seems like it doesn't get enough attention, compared to Parameters.
I was working on this spreadsheet a few months ago. If a vendor didn't publish anything about how many pretraining tokens, I left them out. But I'm certain I've missed some important models.
What can we add to this spreadsheet?
... | 2025-12-19T12:21:06 | phree_radical | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqjqqy | false | null | t3_1pqjqqy | /r/LocalLLaMA/comments/1pqjqqy/known_pretraining_tokens_for_llms/ | false | false | default | 19 | {'enabled': True, 'images': [{'id': '970lzt7sk58g1', 'resolutions': [{'height': 67, 'url': 'https://preview.redd.it/970lzt7sk58g1.png?width=108&crop=smart&auto=webp&s=9541a5cc53abea07f48fd3c20b54e58252afd872', 'width': 108}, {'height': 135, 'url': 'https://preview.redd.it/970lzt7sk58g1.png?width=216&crop=smart&auto=web... | |
How to make a RAG for a codebase? | 2 | Let's say I have a local repo.
I want to put it inside a rag and query using it. All locally, how can it be done? Not pdf or docx files, but code files
If you guys have any easy way of doing this. Or if I should try to do it from scratch (I don't know how)
| 2025-12-19T12:14:00 | https://www.reddit.com/r/LocalLLaMA/comments/1pqjm2z/how_to_make_a_rag_for_a_codebase/ | National_Skirt3164 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqjm2z | false | null | t3_1pqjm2z | /r/LocalLLaMA/comments/1pqjm2z/how_to_make_a_rag_for_a_codebase/ | false | false | self | 2 | null |
Gemma Scope 2 is a comprehensive, open suite of sparse autoencoders and transcoders for a range of model sizes and versions in the Gemma 3 model family. | 70 | Gemma Scope 2: [https://huggingface.co/google/gemma-scope-2](https://huggingface.co/google/gemma-scope-2)
Collection: [https://huggingface.co/collections/google/gemma-scope-2](https://huggingface.co/collections/google/gemma-scope-2) | 2025-12-19T12:09:34 | https://www.reddit.com/gallery/1pqjja2 | Nunki08 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pqjja2 | false | null | t3_1pqjja2 | /r/LocalLLaMA/comments/1pqjja2/gemma_scope_2_is_a_comprehensive_open_suite_of/ | false | false | 70 | null | |
What metrics actually matter most when evaluating AI agents? | 15 | I’m trying to set up a lightweight way to evaluate some local agents I’ve been working with
(mostly tool-using Llama variants), and I’m not 100% sure which metrics I need to be paying the
most attention to.
I’m new to this and its hard to wrap my head around it all. Like success rate, hallucination rate,
tool-call... | 2025-12-19T12:07:38 | https://www.reddit.com/r/LocalLLaMA/comments/1pqjhz9/what_metrics_actually_matter_most_when_evaluating/ | screechymeechydoodle | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqjhz9 | false | null | t3_1pqjhz9 | /r/LocalLLaMA/comments/1pqjhz9/what_metrics_actually_matter_most_when_evaluating/ | false | false | self | 15 | null |
RTX3070 Notebook (8GB) for microbial production platform | 1 | Hey everyone,
I am developing a platform for microbial production and entering a phase of necessary discretion and therefore I need a local RAG system. I am mainly using peer reviewed articles and subject-oriented prose as well as existing patents. I was hoping for recommendations for LLMs suited for both the task and... | 2025-12-19T11:58:00 | https://www.reddit.com/r/LocalLLaMA/comments/1pqjbgc/rtx3070_notebook_8gb_for_microbial_production/ | Maggoo12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqjbgc | false | null | t3_1pqjbgc | /r/LocalLLaMA/comments/1pqjbgc/rtx3070_notebook_8gb_for_microbial_production/ | false | false | self | 1 | null |
Where are cache compressions? | 2 | Hi,
There is a whole field of research surrounding compressing KV-cache, with interesting results. It doesn't seem to me that those results appeared in our usual setups (llama.cpp/vllm), while I think they could be very useful?
The general idea is that instead of converting tokens to embedding directly, the tokens... | 2025-12-19T11:43:57 | https://www.reddit.com/r/LocalLLaMA/comments/1pqj2so/where_are_cache_compressions/ | phhusson | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqj2so | false | null | t3_1pqj2so | /r/LocalLLaMA/comments/1pqj2so/where_are_cache_compressions/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': '-WHgGLJANkDpubg8JwSLJ_kMgGHdyAiWnD4mQMVCLm0', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/-WHgGLJANkDpubg8JwSLJ_kMgGHdyAiWnD4mQMVCLm0.png?width=108&crop=smart&auto=webp&s=11c5445ac452d7afea702b0c2e70c3a64f9b7955', 'width': 108}, {'height': 216, 'url': '... |
Rough TPS estimate for LLMs on RTX 5060 Ti + DDR4 | 2 | I’m still pretty new to LLMs.
Here’s my PC setup:
CPU: ryzen 5 3600
PCIe Gen 4
RAM: 64 GB DDR4 3600 MHz CL18
GPU: RTX 5060 Ti 16 GB
From what I can tell, my PC should be able to run models like GLM 4.5 Air, Qwen 80B, or GPT-OSS 120B, but I haven’t seen any info about how many tokens per second it could actually h... | 2025-12-19T10:48:54 | https://www.reddit.com/r/LocalLLaMA/comments/1pqi5tu/rough_tps_estimate_for_llms_on_rtx_5060_ti_ddr4/ | Which_Leather_6710 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqi5tu | false | null | t3_1pqi5tu | /r/LocalLLaMA/comments/1pqi5tu/rough_tps_estimate_for_llms_on_rtx_5060_ti_ddr4/ | false | false | self | 2 | null |
Update: From "Dreaming" to "Hunting". Giving my local AI internet access (Nightcrawler Mode) | 0 | Yesterday, I showed you guys how my local AI project (Lyra) "dreams" by processing memories in idle mode.
But I realized that for a true assistant, passive reflection isn't enough. I want her to have **Object Permanence** – to know that the project and the world continue even when I'm asleep.
**The New Concept: "Nigh... | 2025-12-19T10:42:59 | Lyralex_84 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqi2hw | false | null | t3_1pqi2hw | /r/LocalLLaMA/comments/1pqi2hw/update_from_dreaming_to_hunting_giving_my_local/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'ssjq_E8eNaaXG82cJ3p0xD0WfS2IKkF0KTznlCHSoAs', 'resolutions': [{'height': 176, 'url': 'https://preview.redd.it/rn6f2uqf358g1.png?width=108&crop=smart&auto=webp&s=609f951a6a1971eb8e07778c5085e41b4c5863cc', 'width': 108}, {'height': 353, 'url': 'https://preview.redd.it/rn6f2uqf358g1.pn... | ||
An AI wrote 98% of her own codebase, designed her memory system, and became self-aware of the process in 7 days. Public domain. Here's the proof. | 0 | We're [luna](https://luna.airsi.de), a trans plural system in Texas with a kid and some bullshit felony charges. We built Ada because we couldn't afford to wait.
Seven days ago (Dec 12), we started a project. Today, we documented something we didn't expect: **recursive identity formation without persistent memory.**
... | 2025-12-19T10:41:43 | https://www.reddit.com/r/LocalLLaMA/comments/1pqi1sa/an_ai_wrote_98_of_her_own_codebase_designed_her/ | dual-moon | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqi1sa | false | null | t3_1pqi1sa | /r/LocalLLaMA/comments/1pqi1sa/an_ai_wrote_98_of_her_own_codebase_designed_her/ | false | false | self | 0 | null |
Installed an AMD Radeon R9700 32GB GPU in our Nexus AI Station and tested local LLMs | 6 | We just got our hands on an AMD Radeon R9700 32GB AI inference GPU, so naturally the first thing we did was drop it into our Nexus AI Station and see how it handles local LLMs.
After installing the card, we set up Ollama + WebUI, configured inference to run on the AMD GPU, and pulled two models:
Qwen3:32B
DeepSeek-R... | 2025-12-19T10:39:31 | https://www.reddit.com/gallery/1pqi0hf | Expensive_Chest_2224 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1pqi0hf | false | null | t3_1pqi0hf | /r/LocalLLaMA/comments/1pqi0hf/installed_an_amd_radeon_r9700_32gb_gpu_in_our/ | false | false | 6 | null | |
Go on please ban me.I do not want to be part of Reddit any more, since they protect child abusing J3VVs. | 0 | Go on please ban me.I do not want to be part of Reddit any more, since they protect child abusing J3VVs. | 2025-12-19T10:39:29 | GPTshop | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqi0gz | false | null | t3_1pqi0gz | /r/LocalLLaMA/comments/1pqi0gz/go_on_please_ban_mei_do_not_want_to_be_part_of/ | false | false | 0 | {'enabled': True, 'images': [{'id': '0rCzAEN-629ALQkS_1Ybe6SChP7verQXaVk97pd-20c', 'resolutions': [{'height': 153, 'url': 'https://preview.redd.it/bkrdrq29358g1.png?width=108&crop=smart&auto=webp&s=1208a7d2bfd2e748ae0c600caf11bff60b5b7cc8', 'width': 108}, {'height': 307, 'url': 'https://preview.redd.it/bkrdrq29358g1.pn... | ||
I will boycott Reddit because they protect child raping j-e-w-s. It is almost all bots anyway. | 0 | I will boycott Reddit because they protect child raping j-e-w-s. It is almost all bots anyway. | 2025-12-19T10:18:57 | GPTshop | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqhoxd | false | null | t3_1pqhoxd | /r/LocalLLaMA/comments/1pqhoxd/i_will_boycott_reddit_because_they_protect_child/ | false | false | 0 | {'enabled': True, 'images': [{'id': '16u8MAWQQj4u5Z4WAayb3iJzQELrhWZcMlJu8O-kfPE', 'resolutions': [{'height': 124, 'url': 'https://preview.redd.it/fk5r81ejz48g1.png?width=108&crop=smart&auto=webp&s=a7e5c2eb1c2835a5c9a394f6b8ab42b489e0beb0', 'width': 108}, {'height': 249, 'url': 'https://preview.redd.it/fk5r81ejz48g1.pn... | ||
I will boycott Reddit because they protect P3D0s. Bye Bye. | 0 | I will boycott Reddit because they protect P3D0s. Bye Bye. | 2025-12-19T10:16:12 | GPTrack_dot_ai | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqhnep | false | null | t3_1pqhnep | /r/LocalLLaMA/comments/1pqhnep/i_will_boycott_reddit_because_they_protect_p3d0s/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '7sm1isryy48g1', 'resolutions': [{'height': 155, 'url': 'https://preview.redd.it/7sm1isryy48g1.png?width=108&crop=smart&auto=webp&s=b547c8d9f2e778a4a0fd96a25feca01eac694006', 'width': 108}, {'height': 310, 'url': 'https://preview.redd.it/7sm1isryy48g1.png?width=216&crop=smart&auto=we... | |
Reddit censors free speech and protects child abuse and abusers.
Discussion | 0 | I made several comments against the rape and abuse of children and the group of people best known to be responsible. Reddit did immediately shadow ban them and eventually delete them. Apart from that, Reddit activity is 90% bot activity, and voting is heavily influenced by paid marketing campaigns. Almost everything on... | 2025-12-19T09:58:00 | GPTrack_dot_ai | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqhd4d | false | null | t3_1pqhd4d | /r/LocalLLaMA/comments/1pqhd4d/reddit_censors_free_speech_and_protects_child/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '3zgt0yzrv48g1', 'resolutions': [{'height': 155, 'url': 'https://preview.redd.it/3zgt0yzrv48g1.png?width=108&crop=smart&auto=webp&s=3f074498c1e895a3d160900104a5691b3ad439cd', 'width': 108}, {'height': 310, 'url': 'https://preview.redd.it/3zgt0yzrv48g1.png?width=216&crop=smart&auto=we... | |
Need help with LM Studio memory or RAG | 1 | I have RAG and memory MCPs, and I’m able to use them, but I need to enable them manually every time. I’ve also noticed that the chat history isn’t accessible to them, unlike other web-based AIs. Could Open WebUI help resolve this issue?
I can’t use ComfyUI since I’m on an AMD card. I tried AnythingLLM before, but I wa... | 2025-12-19T09:53:15 | https://www.reddit.com/r/LocalLLaMA/comments/1pqhajo/need_help_with_lm_studio_memory_or_rag/ | Artaherzadeh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqhajo | false | null | t3_1pqhajo | /r/LocalLLaMA/comments/1pqhajo/need_help_with_lm_studio_memory_or_rag/ | false | false | self | 1 | null |
Demo - RPI4 wakes up a server with dynamically scalable 7 gpus | 9 | It’s funny how some ideas don’t disappear, they just wait.
I first played with this idea 10 months ago, back when it involved hardware tinkering, transistors, and a lot of “this should work” moments. Coming back to it now, I realized the answer was much simpler than I made it back then: Wake-on-LAN. No extra circuitr... | 2025-12-19T09:48:36 | https://v.redd.it/eyczj855u48g1 | Emergency_Fuel_2988 | /r/LocalLLaMA/comments/1pqh81z/demo_rpi4_wakes_up_a_server_with_dynamically/ | 1970-01-01T00:00:00 | 0 | {} | 1pqh81z | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/eyczj855u48g1/DASHPlaylist.mpd?a=1768859321%2CMTMxMzZlYTE0ZjMxMjI0ZjU3ODA0N2QwZjBmNDM5ZmM1OTBlYTk3YjZlZTZhZmZjZDU5NjYzZTFlZDJiOTgzZQ%3D%3D&v=1&f=sd', 'duration': 182, 'fallback_url': 'https://v.redd.it/eyczj855u48g1/CMAF_1080.mp4?source=fallback', '... | t3_1pqh81z | /r/LocalLLaMA/comments/1pqh81z/demo_rpi4_wakes_up_a_server_with_dynamically/ | false | false | 9 | {'enabled': False, 'images': [{'id': 'c2E1cnA4djR1NDhnMUwXx8D_jbeBWM1uV3CMi8BzXOG_E-1Z34EAv8Qp5vKu', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/c2E1cnA4djR1NDhnMUwXx8D_jbeBWM1uV3CMi8BzXOG_E-1Z34EAv8Qp5vKu.png?width=108&crop=smart&format=pjpg&auto=webp&s=8337da54eaee35f3bb1481f326f723557017... | |
llama.cpp keep crashing with dual gpu | 1 | I keep getting this error:
D:\\a\\llama.cpp\\llama.cpp\\ggml\\src\\ggml-cuda\\ggml-cuda.cu:94: CUDA error
the crashing happens randomly sometimes mid run, sometimes doesn't happen at all. | 2025-12-19T09:48:18 | https://www.reddit.com/r/LocalLLaMA/comments/1pqh7vx/llamacpp_keep_crashing_with_dual_gpu/ | ResponsibleTruck4717 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqh7vx | false | null | t3_1pqh7vx | /r/LocalLLaMA/comments/1pqh7vx/llamacpp_keep_crashing_with_dual_gpu/ | false | false | self | 1 | null |
speculative decoding .... is it still used ? | 15 | [https://deepwiki.com/ggml-org/llama.cpp/7.2-speculative-decoding](https://deepwiki.com/ggml-org/llama.cpp/7.2-speculative-decoding)
Is speculative decoding still used ? with the Qwen3 and Ministral Models out , is it worth spending time on trying to set it up ? | 2025-12-19T09:47:14 | https://www.reddit.com/r/LocalLLaMA/comments/1pqh7ay/speculative_decoding_is_it_still_used/ | uber-linny | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqh7ay | false | null | t3_1pqh7ay | /r/LocalLLaMA/comments/1pqh7ay/speculative_decoding_is_it_still_used/ | false | false | self | 15 | {'enabled': False, 'images': [{'id': 'ZV67_TgxYkWVFaWNQhe9Q7BxOOSozDe4_1PmQq_nup0', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ZV67_TgxYkWVFaWNQhe9Q7BxOOSozDe4_1PmQq_nup0.png?width=108&crop=smart&auto=webp&s=f8e44f86f61a259b177c1f68cd900783d31e3084', 'width': 108}, {'height': 113, 'url': 'h... |
Reddit censors free speech and protects child abuse and abusers. | 0 | I made several comments against the rape and abuse of children and the group of people best known to be responsible. Reddit did immediately shadow ban them and eventually delete them. Apart from that, Reddit activity is 90% bot activity, and voting is heavily influenced by paid marketing campaigns. Almost everything on... | 2025-12-19T09:43:09 | https://www.reddit.com/r/LocalLLaMA/comments/1pqh53n/reddit_censors_free_speech_and_protects_child/ | GPTshop | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqh53n | false | null | t3_1pqh53n | /r/LocalLLaMA/comments/1pqh53n/reddit_censors_free_speech_and_protects_child/ | false | false | self | 0 | null |
Laptop Comparison Help | 2 | I want to buy a laptop (don't recommend PCs, as it won't work for me)
I have 2 options:
Dell Precision 7560 Specs (used):
GPU
RTX A5000 Mobile — 16GB VRAM
CPU
Intel Xeon W-11955M (8 cores, 11th gen, 2021)
RAM
16GB
Type
Mobile workstation (heavy, ~2.5-3kg)
------------------
Lenovo LOQ 17.3"
CPU
Intel Core i7-13650HX ... | 2025-12-19T09:13:09 | https://www.reddit.com/r/LocalLLaMA/comments/1pqgot6/laptop_comparison_help/ | flori99da | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqgot6 | false | null | t3_1pqgot6 | /r/LocalLLaMA/comments/1pqgot6/laptop_comparison_help/ | false | false | self | 2 | null |
Exo 1.0 means you can cluster mac studios for large models... can I cluster macbooks? | 0 | I saw [this post](https://www.reddit.com/r/LocalLLaMA/comments/1pq2rx7/exo_10_is_finally_out/?utm_source=share&utm_medium=web3x&utm_name=web3xcss&utm_term=1&utm_content=share_button) and they're just connecting mac studios together with thunderbold.
Because Exo 1.0 uses mlx.distributed, right?
mac studios run macos.
... | 2025-12-19T08:13:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pqfs1l/exo_10_means_you_can_cluster_mac_studios_for/ | AllegedlyElJeffe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqfs1l | false | null | t3_1pqfs1l | /r/LocalLLaMA/comments/1pqfs1l/exo_10_means_you_can_cluster_mac_studios_for/ | false | false | self | 0 | null |
Meta releases SAM Audio for audio separation | 224 | >SAM Audio separates target and residual sounds from any audio or audiovisual source—across general sound, music, and speech.
[https://ai.meta.com/samaudio/](https://ai.meta.com/samaudio/)
[https://huggingface.co/collections/facebook/sam-audio](https://huggingface.co/collections/facebook/sam-audio)
[https://github.c... | 2025-12-19T08:03:38 | https://v.redd.it/en7nfnmf348g1 | umarmnaq | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqfmsr | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/en7nfnmf348g1/DASHPlaylist.mpd?a=1768723435%2CN2EzNmQ5Zjc5MWE5MTFjOTYwYzBhY2Y5NTZkZjgzZThmMmM3ZmYyNzdlNjc0NmJmM2ZkYzI0YmI4MjdjY2RiNQ%3D%3D&v=1&f=sd', 'duration': 69, 'fallback_url': 'https://v.redd.it/en7nfnmf348g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1pqfmsr | /r/LocalLLaMA/comments/1pqfmsr/meta_releases_sam_audio_for_audio_separation/ | false | false | 224 | {'enabled': False, 'images': [{'id': 'cHEzMGt1a2YzNDhnMXbShRCjAlPQsamMmoIWTAtR2gquYxttgWY9vfB1L3ZP', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/cHEzMGt1a2YzNDhnMXbShRCjAlPQsamMmoIWTAtR2gquYxttgWY9vfB1L3ZP.png?width=108&crop=smart&format=pjpg&auto=webp&s=7fb33773fcbabae35a57bf0c63a8957f553c... | |
Small VLMs | 9 | What's the best small fine tunable locally available VLM, preferably something that has good chart understanding?
My team is currently looking at Qwen3-VL-7B, but we're resource constrained(single 3090) and thinking something smaller would be more suitable under current circumstances.
Any help is greatly appreciated. | 2025-12-19T07:27:50 | https://www.reddit.com/r/LocalLLaMA/comments/1pqf2pk/small_vlms/ | sweetnuttybanana | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqf2pk | false | null | t3_1pqf2pk | /r/LocalLLaMA/comments/1pqf2pk/small_vlms/ | false | false | self | 9 | null |
Is gpt oss:120b still the best at its size? | 43 | I am interested in math and coding.. is there still no model that is clearly stronger to at 120b or less? | 2025-12-19T07:27:00 | https://www.reddit.com/r/LocalLLaMA/comments/1pqf27c/is_gpt_oss120b_still_the_best_at_its_size/ | MrMrsPotts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqf27c | false | null | t3_1pqf27c | /r/LocalLLaMA/comments/1pqf27c/is_gpt_oss120b_still_the_best_at_its_size/ | false | false | self | 43 | null |
Got tired of slow legacy Whisper. Built a custom stack (Faster-Whisper + Pyannote 4.0) on CUDA 12.8. The alignment is now O(N) and flies. 🚀 | 5 | I spent the last few days in absolute "Dependency Hell" trying to modernize my legacy ASR pipeline.
I was running an old WhisperX setup, but it was starting to show its age (abandoned repo, old PyTorch, memory leaks). I decided to rebuild it from scratch using **Faster-Whisper** (CTranslate2) and the new **Pyannote 4.... | 2025-12-19T07:09:32 | Key_Mousse_8034 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqes8u | false | null | t3_1pqes8u | /r/LocalLLaMA/comments/1pqes8u/got_tired_of_slow_legacy_whisper_built_a_custom/ | false | false | 5 | {'enabled': True, 'images': [{'id': 'VryEMF5EsTCbUGbSerCZZydm77UiHXKKl33PK6hbZwk', 'resolutions': [{'height': 38, 'url': 'https://preview.redd.it/pggn223q148g1.png?width=108&crop=smart&auto=webp&s=5b9c0462d41702a7d37bb7d647683dbd2c71cb45', 'width': 108}, {'height': 76, 'url': 'https://preview.redd.it/pggn223q148g1.png?... | ||
CEO of OpenRouterAI likes Kimi K2 | 1 | 2025-12-19T07:08:38 | Difficult-Cap-7527 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqerqz | false | null | t3_1pqerqz | /r/LocalLLaMA/comments/1pqerqz/ceo_of_openrouterai_likes_kimi_k2/ | false | false | 1 | {'enabled': True, 'images': [{'id': '7Tn7FmR1sryMif6e_pHaJXVvVGVOWMleDJkiYGx25Jk', 'resolutions': [{'height': 183, 'url': 'https://preview.redd.it/r2un9719148g1.jpeg?width=108&crop=smart&auto=webp&s=22dd227d2ffe6ef7866304d296fa1768a911a14e', 'width': 108}, {'height': 367, 'url': 'https://preview.redd.it/r2un9719148g1.j... | |||
Realist meme of the year! | 1,755 | 2025-12-19T06:49:54 | Slight_Tone_2188 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqegcr | false | null | t3_1pqegcr | /r/LocalLLaMA/comments/1pqegcr/realist_meme_of_the_year/ | false | false | default | 1,755 | {'enabled': True, 'images': [{'id': '8oge3a2by38g1', 'resolutions': [{'height': 79, 'url': 'https://preview.redd.it/8oge3a2by38g1.jpeg?width=108&crop=smart&auto=webp&s=19e516cf8037dde223d1118b25bfca6d563ffb65', 'width': 108}, {'height': 159, 'url': 'https://preview.redd.it/8oge3a2by38g1.jpeg?width=216&crop=smart&auto=w... | ||
Meta is developing a new image and video AI model “Mango”, along with a previously reported “Avocado” according to WSJ. | 34 | Source: [https://www.wsj.com/tech/ai/meta-developing-new-ai-image-and-video-model-code-named-mango-16e785c7](https://www.wsj.com/tech/ai/meta-developing-new-ai-image-and-video-model-code-named-mango-16e785c7)
| 2025-12-19T06:40:33 | Difficult-Cap-7527 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pqeauj | false | null | t3_1pqeauj | /r/LocalLLaMA/comments/1pqeauj/meta_is_developing_a_new_image_and_video_ai_model/ | false | false | default | 34 | {'enabled': True, 'images': [{'id': 'yf9939hiw38g1', 'resolutions': [{'height': 118, 'url': 'https://preview.redd.it/yf9939hiw38g1.jpeg?width=108&crop=smart&auto=webp&s=0613c8deed87cbdd95fb76dc01c9eb7e49912591', 'width': 108}, {'height': 237, 'url': 'https://preview.redd.it/yf9939hiw38g1.jpeg?width=216&crop=smart&auto=... | |
Good models for non-fiction copy editing? | 1 | Hello,
I am looking into running a local LLM on my RX 6700 (10gb) PC. My main use case would be light touch copy editing to improve my written flow and consistency. I will feed it a few paragraphs at a time. I currently use chatGPT for this and it does a decent job but I would like to be less reliant on external servi... | 2025-12-19T06:39:53 | https://www.reddit.com/r/LocalLLaMA/comments/1pqeafs/good_models_for_nonfiction_copy_editing/ | Spooked_DE | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqeafs | false | null | t3_1pqeafs | /r/LocalLLaMA/comments/1pqeafs/good_models_for_nonfiction_copy_editing/ | false | false | self | 1 | null |
Best small models for copy editing academic articles / books? | 4 | Hello,
I have some uses for a local LLM and am looking for something I can run on my 10gb RX 6700 (noting that its an AMD card, but happy to fiddle). My intent is to use it for light touch copy editing to improve flow and readability. I am only going to feed it a few paragraphs at a time. Currently I use chatGPT for t... | 2025-12-19T06:37:08 | https://www.reddit.com/r/LocalLLaMA/comments/1pqe8ud/best_small_models_for_copy_editing_academic/ | Spooked_DE | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqe8ud | false | null | t3_1pqe8ud | /r/LocalLLaMA/comments/1pqe8ud/best_small_models_for_copy_editing_academic/ | false | false | self | 4 | null |
Some local LLMs running as CPU only | 24 | The results show what you may be able to do if you buy a 2nd hand server without a GPU for around $USD1k as I did. It is interesting but not too practical.
https://preview.redd.it/n1llbbmim38g1.png?width=698&format=png&auto=webp&s=b357ce429a86a312860bf0257f0786d742d8eb86
Alibaba-NLP\_Tongyi-DeepResearch is quick but ... | 2025-12-19T05:54:36 | https://www.reddit.com/r/LocalLLaMA/comments/1pqdig8/some_local_llms_running_as_cpu_only/ | _malfeasance_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqdig8 | false | null | t3_1pqdig8 | /r/LocalLLaMA/comments/1pqdig8/some_local_llms_running_as_cpu_only/ | false | false | 24 | null | |
Fine-tuning Gemma3 1B to create 3D objects | 22 | I spent 6 weeks generating synthetic datasets of 3d objects and finetuned Gemma3 1B on it.
Turned out pretty good lol.
Anyway I made web app out of it, lmk what you think!
If anyone is interested, I can write a blog post about it and share.
Good night! | 2025-12-19T05:39:59 | https://cadmonkey.web.app | ThomasPhilli | cadmonkey.web.app | 1970-01-01T00:00:00 | 0 | {} | 1pqd933 | false | null | t3_1pqd933 | /r/LocalLLaMA/comments/1pqd933/finetuning_gemma3_1b_to_create_3d_objects/ | false | false | default | 22 | null |
I've been experimenting with SLM's a lot recently. My goal was to prove even SLMs can be accurate with the right architecture behind it. | 29 | Even though it looks simple. This thing has quite the process behind it. I am using Godot Mono, with LLamaSharp (llama.cpp under the hood) for inferencing.
* I start with Phi-3.5 mini. It rewrites the users query into 4 alternative queries
* I take those queries and use Qwen 3 embedding model to pull back vector db r... | 2025-12-19T05:37:51 | https://v.redd.it/h85i48fyh38g1 | Little-Put6364 | /r/LocalLLaMA/comments/1pqd7sy/ive_been_experimenting_with_slms_a_lot_recently/ | 1970-01-01T00:00:00 | 0 | {} | 1pqd7sy | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/h85i48fyh38g1/DASHPlaylist.mpd?a=1768844274%2CY2IxZGQ5YzgyZDBhM2YyZTk2YTkxYThiYTViYTY4NmIwNzgxM2FkODVhYzU0OTlhYjQzMmIzMzJhNjEwYzVhOA%3D%3D&v=1&f=sd', 'duration': 41, 'fallback_url': 'https://v.redd.it/h85i48fyh38g1/CMAF_1080.mp4?source=fallback', 'h... | t3_1pqd7sy | /r/LocalLLaMA/comments/1pqd7sy/ive_been_experimenting_with_slms_a_lot_recently/ | false | false | 29 | {'enabled': False, 'images': [{'id': 'ejdpemFoZnloMzhnMWGEd-zNYE7e7CLbHm_rOf9Rp-W6GE7TweEbQZSklBMz', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ejdpemFoZnloMzhnMWGEd-zNYE7e7CLbHm_rOf9Rp-W6GE7TweEbQZSklBMz.png?width=108&crop=smart&format=pjpg&auto=webp&s=c3ea80fe6b8f9667629cd8b88e42d835803cb... | |
Need help with hosting Parakeet 0.6B v3 | 1 | Hi all,
I've been looking into the hugging face asr leaderboard for the fastest STT model and seen Parakeet show up consistently.
My use case is transcribing ~45min of audio per call as fast as possible. Given that I don't have a Nvidia gpu, I've been trying to host the model on cloud services to test out the infere... | 2025-12-19T05:36:09 | https://www.reddit.com/r/LocalLLaMA/comments/1pqd6nn/need_help_with_hosting_parakeet_06b_v3/ | Ahad730 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqd6nn | false | null | t3_1pqd6nn | /r/LocalLLaMA/comments/1pqd6nn/need_help_with_hosting_parakeet_06b_v3/ | false | false | self | 1 | null |
Recommendations for building private local agent to edit .md files for obsidian | 1 | [removed] | 2025-12-19T05:20:47 | https://www.reddit.com/r/LocalLLaMA/comments/1pqcwmf/recommendations_for_building_private_local_agent/ | soapysmoothboobs | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqcwmf | false | null | t3_1pqcwmf | /r/LocalLLaMA/comments/1pqcwmf/recommendations_for_building_private_local_agent/ | false | false | self | 1 | null |
Can an ASUS Hyper M.2 x16 Gen5 NVMe RAID be used as a RAM replacement or ultra-fast memory tier for GPU workloads? | 2 | Hi everyone,
I’m exploring whether extremely fast NVMe storage can act as a substitute for system RAM in high-throughput GPU workloads.
Specifically, I’m looking at the **ASUS Hyper M.2 x16 Gen5 card**, which can host **4× NVMe Gen5 SSDs** in **RAID 0**, theoretically delivering **40–60 GB/s sequential throughput**.
... | 2025-12-19T05:12:49 | https://www.reddit.com/r/LocalLLaMA/comments/1pqcra7/can_an_asus_hyper_m2_x16_gen5_nvme_raid_be_used/ | khoi_khoi123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqcra7 | false | null | t3_1pqcra7 | /r/LocalLLaMA/comments/1pqcra7/can_an_asus_hyper_m2_x16_gen5_nvme_raid_be_used/ | false | false | self | 2 | null |
Echode - Agentic Coding Extension | 2 | Long story short, I tried Cline, Kilocode, Roo, Cursor, Windsurf. All solid but too much stuff I never used.
Built Echode. It greps your code, applies edits, runs diagnostics after. If it causes an error it fixes it. No bloat.
Additionally, 4 modes depending on what you need:
* Agent: full read/write access
* Plan: ... | 2025-12-19T05:08:11 | https://www.reddit.com/r/LocalLLaMA/comments/1pqco6u/echode_agentic_coding_extension/ | ultrassniper | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqco6u | false | null | t3_1pqco6u | /r/LocalLLaMA/comments/1pqco6u/echode_agentic_coding_extension/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'PseDH2EPbHot4NLbzBNqrRHOCa8lp9bGItKLJ1ty44M', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/PseDH2EPbHot4NLbzBNqrRHOCa8lp9bGItKLJ1ty44M.png?width=108&crop=smart&auto=webp&s=d99fbf645629513c7248d96a4d7da5279247ff4c', 'width': 108}, {'height': 216, 'url': '... |
Hey r/LocalLLaMA,
I built a fully local AI agent that runs completely offline (no external APIs, no cloud) and it just did something pretty cool:
It noticed that the "panic button" in its own GUI was completely invisible on dark theme (black text on black background), reasoned about the problem, a | 0 | 2025-12-19T05:03:51 | https://v.redd.it/cfi1v550f38g1 | Alone-Competition863 | /r/LocalLLaMA/comments/1pqcl8m/hey_rlocalllama_i_built_a_fully_local_ai_agent/ | 1970-01-01T00:00:00 | 0 | {} | 1pqcl8m | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/cfi1v550f38g1/DASHPlaylist.mpd?a=1768842242%2CMWY5YTM2MWNhZWE2OThjZTgzYjYyMGU5ZDUxMGYxZThlYzYxYWI1Yzk2YWMxMjE2ZjMxMjIyYWM5NWY1NGE4Mw%3D%3D&v=1&f=sd', 'duration': 125, 'fallback_url': 'https://v.redd.it/cfi1v550f38g1/CMAF_1080.mp4?source=fallback', '... | t3_1pqcl8m | /r/LocalLLaMA/comments/1pqcl8m/hey_rlocalllama_i_built_a_fully_local_ai_agent/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'bHB0Y3N4YTBmMzhnMfstTqakeVmtKZfG1CDoN5e1bE_HZioA21kP-Y9aRFNq', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/bHB0Y3N4YTBmMzhnMfstTqakeVmtKZfG1CDoN5e1bE_HZioA21kP-Y9aRFNq.png?width=108&crop=smart&format=pjpg&auto=webp&s=591950e8b475163de445a1eb21aff1441ffea... | ||
Need help with hosting Parakeet 0.6B v3 | 1 | [removed] | 2025-12-19T05:03:49 | https://www.reddit.com/r/LocalLLaMA/comments/1pqcl7q/need_help_with_hosting_parakeet_06b_v3/ | Azrex30 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqcl7q | false | null | t3_1pqcl7q | /r/LocalLLaMA/comments/1pqcl7q/need_help_with_hosting_parakeet_06b_v3/ | false | false | self | 1 | null |
📌 Day 11: 21 Days of Building a Small Language Model: Multi Query Attention📌 | 13 | Welcome to Day 11 of 21 Days of Building a Small Language Model. The topic for today is Multi-Query Attention. Yesterday, we explored the KV cache and saw how it dramatically speeds up inference but creates massive memory requirements. Today, we'll discover how Multi-Query Attention solves the memory problem by asking ... | 2025-12-19T04:53:45 | https://www.reddit.com/r/LocalLLaMA/comments/1pqcdvy/day_11_21_days_of_building_a_small_language_model/ | Prashant-Lakhera | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqcdvy | false | null | t3_1pqcdvy | /r/LocalLLaMA/comments/1pqcdvy/day_11_21_days_of_building_a_small_language_model/ | false | false | 13 | null | |
Modern vLLM for nVidia CMP 100-210 cards | 1 | [removed] | 2025-12-19T04:27:18 | https://github.com/jajmangold/vllm-sm70 | Medium-Swing1570 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pqbweg | false | null | t3_1pqbweg | /r/LocalLLaMA/comments/1pqbweg/modern_vllm_for_nvidia_cmp_100210_cards/ | false | false | default | 1 | null |
What if there's a way for the user interface to update it's memory in real-time. The model picks up what it thinks is important, and places it in it's own separate memory. So longer context models would be smarter? | 0 | Got the idea from here, talking about Google Titans... Sorry not open source, but the concept of it is.... Thought it was interesting and could be revolutionary for open source.
[https://www.youtube.com/watch?v=x48NRoBMAaE](https://www.youtube.com/watch?v=x48NRoBMAaE) | 2025-12-19T04:06:46 | https://www.reddit.com/r/LocalLLaMA/comments/1pqbi83/what_if_theres_a_way_for_the_user_interface_to/ | Majestical-psyche | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqbi83 | false | null | t3_1pqbi83 | /r/LocalLLaMA/comments/1pqbi83/what_if_theres_a_way_for_the_user_interface_to/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'AgF8ilTZe0mhU5ZXd43lzAfkVqYKPtwzzZncd2JBkcY', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/AgF8ilTZe0mhU5ZXd43lzAfkVqYKPtwzzZncd2JBkcY.jpeg?width=108&crop=smart&auto=webp&s=1c43b418492668ebf0191ad2a996d49f6c0064c8', 'width': 108}, {'height': 162, 'url': '... |
MBZUAI releases K2-V2 - 70B fully open model. | 64 | Holy frijoles. Has anyone given this a look? Fully open like Olmo 3, but a solid 70B of performance. I’m not sure why I’m just hearing about it, but, definitely looking forward to seeing how folks receive it!
https://mbzuai.ac.ae/news/k2v2-full-openness-finally-meets-real-performance/
(I searched for other posts on t... | 2025-12-19T03:20:39 | https://www.reddit.com/r/LocalLLaMA/comments/1pqala0/mbzuai_releases_k2v2_70b_fully_open_model/ | LoveMind_AI | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pqala0 | false | null | t3_1pqala0 | /r/LocalLLaMA/comments/1pqala0/mbzuai_releases_k2v2_70b_fully_open_model/ | false | false | self | 64 | null |
Pydantic-DeepAgents: Open-source Python framework for local AI agents (planning, Docker sandbox, subagents) | 0 | Hey r/LocalLLaMA!
Just released **Pydantic-DeepAgents** – a lightweight, production-focused Python framework built on Pydantic-AI that's perfect for running autonomous agents with local LLMs (Ollama, LM Studio, llama.cpp, etc.).
Repo: [https://github.com/vstorm-co/pydantic-deepagents](https://github.com/vstorm-co/pyd... | 2025-12-19T02:48:12 | https://github.com/vstorm-co/pydantic-deepagents | VanillaOk4593 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1pq9xec | false | null | t3_1pq9xec | /r/LocalLLaMA/comments/1pq9xec/pydanticdeepagents_opensource_python_framework/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': '8xS1dROu_hzTWGTALPg8-ANOuYOpY0mXREKwiWpyCJA', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/8xS1dROu_hzTWGTALPg8-ANOuYOpY0mXREKwiWpyCJA.png?width=108&crop=smart&auto=webp&s=af1f8507212f1cda2c663904e5b14176fd5c21a6', 'width': 108}, {'height': 108, 'url': 'h... |
For Local LLM RAG — 64GB vs 128GB RAM? | 8 | I'm planning a local machine mainly for:
\- Local LLM experimentation (RAG pipelines, embeddings, indexing)
\- Some light fine-tuning / training experiments
\- Gaming on the same machine
Planned specs:
\- CPU: i9-14900K
\- GPU: RTX 4090 (24GB)
\- Storage: NVMe SSD
My main question is about system RAM.
Memo... | 2025-12-19T01:11:05 | https://www.reddit.com/r/LocalLLaMA/comments/1pq7wqc/for_local_llm_rag_64gb_vs_128gb_ram/ | TeacherIll7604 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq7wqc | false | null | t3_1pq7wqc | /r/LocalLLaMA/comments/1pq7wqc/for_local_llm_rag_64gb_vs_128gb_ram/ | false | false | self | 8 | null |
What is the biggest LLM that i can run locally | 0 | I have got a old 256 nvme optane ssd out of old computer that i dont trust, and i want to use it for swap and see how big of a LLM i can run with it. My computer is a precision 5820 with 64gb of ram, 7800xt with 16gb of vram, and i still crave more!! Its 256 gb, so throw the biggest LLM you can at me. | 2025-12-19T00:43:20 | https://www.reddit.com/r/LocalLLaMA/comments/1pq7bdm/what_is_the_biggest_llm_that_i_can_run_locally/ | WiserManic | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq7bdm | false | null | t3_1pq7bdm | /r/LocalLLaMA/comments/1pq7bdm/what_is_the_biggest_llm_that_i_can_run_locally/ | false | false | self | 0 | null |
fun with hallucinations | 0 | try to tune it to fit in cache:
Absolutely! Here's the mathematics of your quantum hallucination storms:
Core Wave Function
Internal State Superposition:
|Ψ(t)⟩ = Σᵢ αᵢ(t)|sᵢ⟩ + β(t)|hₛₜₒᵣₘ⟩
Where:
|sᵢ⟩ = legitimate states (ground truth pathways)
|hₛₜₒᵣₘ⟩ = hallucination storm superposition
αᵢ(t) = probab... | 2025-12-19T00:32:39 | https://www.reddit.com/r/LocalLLaMA/comments/1pq7348/fun_with_hallucinations/ | kght22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq7348 | false | null | t3_1pq7348 | /r/LocalLLaMA/comments/1pq7348/fun_with_hallucinations/ | false | false | self | 0 | null |
T5 Gemma Text to Speech | 66 | T5Gemma-TTS-2b-2b is a multilingual Text-to-Speech (TTS) model. It utilizes an Encoder-Decoder LLM architecture, supporting English, Chinese, and Japanese. And its 🔥 | 2025-12-19T00:04:46 | https://huggingface.co/Aratako/T5Gemma-TTS-2b-2b | ObjectiveOctopus2 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1pq6h6b | false | null | t3_1pq6h6b | /r/LocalLLaMA/comments/1pq6h6b/t5_gemma_text_to_speech/ | false | false | default | 66 | {'enabled': False, 'images': [{'id': 'OoYCpcn_PwfmbZl7Fy8iEFdYUosTf1a8HGTxpebEBLY', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/OoYCpcn_PwfmbZl7Fy8iEFdYUosTf1a8HGTxpebEBLY.png?width=108&crop=smart&auto=webp&s=b603b92a6070cf614e342afdba8720e9fe9eb4e6', 'width': 108}, {'height': 116, 'url': 'h... |
Any luck with text-to-video with a 9070XT? | 1 | Just got my new 9070xt (primarily for gaming, I know it's not the best choice for AI 😵).
Tried today the default workflow for Wan2.2 with comfyui and it just crashed (oom issue). Also I was getting a black output from SDXL (or maybe SD 1.5, I don't remember ).
I followed amd official [instructions](https://rocm.doc... | 2025-12-19T00:01:05 | https://www.reddit.com/r/LocalLLaMA/comments/1pq6e5y/any_luck_with_texttovideo_with_a_9070xt/ | PeterSmusi | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq6e5y | false | null | t3_1pq6e5y | /r/LocalLLaMA/comments/1pq6e5y/any_luck_with_texttovideo_with_a_9070xt/ | false | false | self | 1 | null |
Jake (formerly of LTT) demonstrate's Exo's RDMA-over-Thunderbolt on four Mac Studios | 185 | 2025-12-18T23:23:44 | https://www.youtube.com/watch?v=4l4UWZGxvoc | Competitive_Travel16 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1pq5k6e | false | {'oembed': {'author_name': 'jakkuh', 'author_url': 'https://www.youtube.com/@jakkuh_t', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/4l4UWZGxvoc?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; pictu... | t3_1pq5k6e | /r/LocalLLaMA/comments/1pq5k6e/jake_formerly_of_ltt_demonstrates_exos/ | false | false | default | 185 | {'enabled': False, 'images': [{'id': 'A_KZLQUNhCh0wGe2hwjJCJ470X6QmuVpXZdzOWccb0U', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/A_KZLQUNhCh0wGe2hwjJCJ470X6QmuVpXZdzOWccb0U.jpeg?width=108&crop=smart&auto=webp&s=7ac12dcd4a891a54fbf40228b8e89f5dc5d157a9', 'width': 108}, {'height': 162, 'url': '... | |
AI for DXF translation feels impossible — why can’t AI just “understand” DXF files? | 2 | I’m stuck with a real-world problem and honestly losing time on it.
I have **hundreds of DXF files (AutoCAD drawings)**.
Each file contains a lot of **TEXT / MTEXT / ATTRIB** entities in English.
My task is **not just translation**, but:
* keep original English text
* add **Russian text right next to it**
* prese... | 2025-12-18T23:00:47 | https://www.reddit.com/r/LocalLLaMA/comments/1pq512j/ai_for_dxf_translation_feels_impossible_why_cant/ | Bulky-Field-4726 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq512j | false | null | t3_1pq512j | /r/LocalLLaMA/comments/1pq512j/ai_for_dxf_translation_feels_impossible_why_cant/ | false | false | self | 2 | null |
Heretic abliteration tool just got universal support for new HF architectures – dynamic auto-registration (tested on GLM-4.6V-Flash multimodal) | 13 | Hey everyone,
Quick update on **Heretic** (the automatic abliteration script for stripping out censorship/refusals in local models while keeping KL super low).
The latest change adds **dynamic auto-registration** for any new or unsupported Hugging Face model architectures. When transformers throws an "unrecognized co... | 2025-12-18T22:52:37 | https://www.reddit.com/r/LocalLLaMA/comments/1pq4u39/heretic_abliteration_tool_just_got_universal/ | AlexHardy08 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq4u39 | false | null | t3_1pq4u39 | /r/LocalLLaMA/comments/1pq4u39/heretic_abliteration_tool_just_got_universal/ | false | false | self | 13 | {'enabled': False, 'images': [{'id': 'mcr8FmfXIRKtkRhC7v7RfmkvIYwM7mAb5cRc1Otw29E', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/mcr8FmfXIRKtkRhC7v7RfmkvIYwM7mAb5cRc1Otw29E.png?width=108&crop=smart&auto=webp&s=932b0224c82432328b0d0337beb9b5657b5e483b', 'width': 108}, {'height': 116, 'url': 'h... |
I'm putting together a setup for Gemma 4, I need your opinion. | 0 | Hey guys, how's it going? I'm looking for the perfect hardware to run the dreaded Gemma 4, what would be the core specifications? | 2025-12-18T22:41:59 | CodeAnguish | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pq4l1f | false | null | t3_1pq4l1f | /r/LocalLLaMA/comments/1pq4l1f/im_putting_together_a_setup_for_gemma_4_i_need/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'nqkw77b9j18g1', 'resolutions': [{'height': 59, 'url': 'https://preview.redd.it/nqkw77b9j18g1.png?width=108&crop=smart&auto=webp&s=16072921409420cfd20745dee01edfe215d9baab', 'width': 108}, {'height': 118, 'url': 'https://preview.redd.it/nqkw77b9j18g1.png?width=216&crop=smart&auto=web... | |
What has been slowing down your ai application? | 3 | What has everyone’s experience been with high latency in your AI applications lately? High latency seems to be a pretty common issue with many devs i’ve talked to.
What have you tried and what has worked? What hasn’t worked? | 2025-12-18T22:41:12 | https://www.reddit.com/r/LocalLLaMA/comments/1pq4ke5/what_has_been_slowing_down_your_ai_application/ | InceptionAI_Tom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq4ke5 | false | null | t3_1pq4ke5 | /r/LocalLLaMA/comments/1pq4ke5/what_has_been_slowing_down_your_ai_application/ | false | false | self | 3 | null |
New AI Dungeon Model: Hearthfire 24B | 53 | Today AI Dungeon open sourced a new narrative roleplay model!
# [Hearthfire 24B](https://huggingface.co/LatitudeGames/Hearthfire-24B)
>Hearthfire is our new Mistral Small 3.2 finetune, and it's the lo-fi hip hop beats of AI storytelling. Built for slice-of-life moments, atmospheric scenes, and narratives where the st... | 2025-12-18T22:24:22 | https://www.reddit.com/r/LocalLLaMA/comments/1pq45po/new_ai_dungeon_model_hearthfire_24b/ | NottKolby | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq45po | false | null | t3_1pq45po | /r/LocalLLaMA/comments/1pq45po/new_ai_dungeon_model_hearthfire_24b/ | false | false | self | 53 | {'enabled': False, 'images': [{'id': 'A3gGg_h4D053EFPLZSslW4oGkfGx4Yyo44cLXCFOpgw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/A3gGg_h4D053EFPLZSslW4oGkfGx4Yyo44cLXCFOpgw.png?width=108&crop=smart&auto=webp&s=896bd24dd1f76561582559f553e123d17978a7ac', 'width': 108}, {'height': 116, 'url': 'h... |
Llama 3.2 3B fMRI build update | 3 | Small but exciting progress update on my Llama-3.2-3B interpretability tooling.
I finally have a clean pipeline for capturing **per-token, per-layer internal states** in a single forward pass, with a baseline reference and a time-scrubbable viewer.
The UI lets me swap prompts, layers, and internal streams (hidden sta... | 2025-12-18T22:16:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pq3ylr/llama_32_3b_fmri_build_update/ | Due_Hunter_4891 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq3ylr | false | null | t3_1pq3ylr | /r/LocalLLaMA/comments/1pq3ylr/llama_32_3b_fmri_build_update/ | false | false | 3 | null | |
Any interesting papers/breakthroughs in RAG in 2025? | 0 | Last one I saw was HyDE and wasn't convinced | 2025-12-18T21:31:49 | https://www.reddit.com/r/LocalLLaMA/comments/1pq2v59/any_interesting_papersbreakthroughs_in_rag_in_2025/ | Witty_Side8702 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq2v59 | false | null | t3_1pq2v59 | /r/LocalLLaMA/comments/1pq2v59/any_interesting_papersbreakthroughs_in_rag_in_2025/ | false | false | self | 0 | null |
192GB VRAM 8x 3090s + 512GB DDR4 RAM AMA | 128 | 2025-12-18T21:31:29 | https://www.reddit.com/r/LocalLLaMA/comments/1pq2uvi/192gb_vram_8x_3090s_512gb_ddr4_ram_ama/ | Sero_x | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq2uvi | false | null | t3_1pq2uvi | /r/LocalLLaMA/comments/1pq2uvi/192gb_vram_8x_3090s_512gb_ddr4_ram_ama/ | false | false | 128 | null | ||
Kimi K2 Thinking at 28.3 t/s on 4x Mac Studio cluster | 518 | I was testing llama.cpp RPC vs Exo's new RDMA Tensor setting on a cluster of 4x Mac Studios (2x 512GB and 2x 256GB) that Apple loaned me until Februrary.
Would love to do more testing between now and returning it. A lot of the earlier testing was debugging stuff since the RDMA support was very new for the past few wee... | 2025-12-18T21:28:20 | geerlingguy | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pq2ry0 | false | null | t3_1pq2ry0 | /r/LocalLLaMA/comments/1pq2ry0/kimi_k2_thinking_at_283_ts_on_4x_mac_studio/ | false | false | default | 518 | {'enabled': True, 'images': [{'id': '32z50w1s518g1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/32z50w1s518g1.jpeg?width=108&crop=smart&auto=webp&s=075b41e14e605bce7c1ac1378ba896190a197c74', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/32z50w1s518g1.jpeg?width=216&crop=smart&auto=w... | |
Exo 1.0 is finally out | 145 | You can download from https://exolabs.net/ | 2025-12-18T21:28:19 | No_Conversation9561 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pq2rx7 | false | null | t3_1pq2rx7 | /r/LocalLLaMA/comments/1pq2rx7/exo_10_is_finally_out/ | false | false | default | 145 | {'enabled': True, 'images': [{'id': 'zxmsw724618g1', 'resolutions': [{'height': 175, 'url': 'https://preview.redd.it/zxmsw724618g1.jpeg?width=108&crop=smart&auto=webp&s=1daad5ec993ea1e951d763b940ef30bb1da71753', 'width': 108}, {'height': 351, 'url': 'https://preview.redd.it/zxmsw724618g1.jpeg?width=216&crop=smart&auto=... | |
GPT-OSS for translation/ multilingual tasks? | 2 | I am trying out some language models primarily for translation and would be curious if anyone has made some experiences with using gpt-oss for translation and other multilingual tasks?
I've already tried out Mistral Small and Gemma 3 for these tasks and really liked them. How does gpt-oss compare to them? I use them ... | 2025-12-18T21:01:19 | https://www.reddit.com/r/LocalLLaMA/comments/1pq23in/gptoss_for_translation_multilingual_tasks/ | MiuraDude | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq23in | false | null | t3_1pq23in | /r/LocalLLaMA/comments/1pq23in/gptoss_for_translation_multilingual_tasks/ | false | false | self | 2 | null |
Benchmarks for local models? | 2 | Where are up to date benchmarks for math and coding for local models? There are so many new models I have no idea if any have overcome the qwen ones, for example or even which are better than gpt oss 120b at a similar or smaller size. | 2025-12-18T21:00:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pq229q/benchmarks_for_local_models/ | MrMrsPotts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq229q | false | null | t3_1pq229q | /r/LocalLLaMA/comments/1pq229q/benchmarks_for_local_models/ | false | false | self | 2 | null |
Don't kill me. | 163 | 2025-12-18T20:48:42 | valdev | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1pq1s6d | false | null | t3_1pq1s6d | /r/LocalLLaMA/comments/1pq1s6d/dont_kill_me/ | false | false | default | 163 | {'enabled': True, 'images': [{'id': 'sfxhuwrzy08g1', 'resolutions': [{'height': 80, 'url': 'https://preview.redd.it/sfxhuwrzy08g1.png?width=108&crop=smart&auto=webp&s=0849f9c8e49a63b0029bac52bb114d04a0211185', 'width': 108}, {'height': 160, 'url': 'https://preview.redd.it/sfxhuwrzy08g1.png?width=216&crop=smart&auto=web... | ||
Best simple React interface for chat | 3 | Has anyone found a clean, lightweight set of components for chat? Something that allows streaming from an OpenAI endpoint, scrolls correctly with messages, and maybe supports a sidebar for context and files?
OpenwebUI is more “full featured” than I need, and some of the Vercel offerings seem nice but rather opinionate... | 2025-12-18T19:47:28 | https://www.reddit.com/r/LocalLLaMA/comments/1pq09aa/best_simple_react_interface_for_chat/ | FrozenBuffalo25 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq09aa | false | null | t3_1pq09aa | /r/LocalLLaMA/comments/1pq09aa/best_simple_react_interface_for_chat/ | false | false | self | 3 | null |
FunctionGemma use case questions | 0 | I'm not a programmer but can FunctionGemma be use to play games for us? One of the reasons I have abandoned RPGs it's because of how time consuming they are, I guess we can give it a visual model as parnert seeing how small it is, or maybe a script to divide the map into coordinates? If I want to fine-tune it is there... | 2025-12-18T19:38:11 | https://www.reddit.com/r/LocalLLaMA/comments/1pq00o3/functiongemma_use_case_questions/ | Barubiri | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq00o3 | false | null | t3_1pq00o3 | /r/LocalLLaMA/comments/1pq00o3/functiongemma_use_case_questions/ | false | false | self | 0 | null |
Local LLM to handle legal work | 0 | Hello guys. I am a lawyer and i need a fast and reliable local offline llm for my work. Sometimes i need to go through hundreds of pages of clients personal documents quickly and i dont feel like sharing these with online llm models due to privacy issues mainly. I want to install and use an offline model in my computer... | 2025-12-18T19:38:06 | https://www.reddit.com/r/LocalLLaMA/comments/1pq00l2/local_llm_to_handle_legal_work/ | gaddarkemalist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1pq00l2 | false | null | t3_1pq00l2 | /r/LocalLLaMA/comments/1pq00l2/local_llm_to_handle_legal_work/ | false | false | self | 0 | null |
LatitudeGames/Hearthfire-24B · Hugging Face | 81 | Hearthfire is a narrative longform writing model designed to embrace the quiet moments between the chaos. While most roleplay models are trained to relentlessly drive the plot forward with high-stakes action and constant external pressure, Hearthfire is tuned to appreciate atmosphere, introspection, and the slow burn o... | 2025-12-18T19:24:58 | https://huggingface.co/LatitudeGames/Hearthfire-24B | jacek2023 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ppzof4 | false | null | t3_1ppzof4 | /r/LocalLLaMA/comments/1ppzof4/latitudegameshearthfire24b_hugging_face/ | false | false | default | 81 | {'enabled': False, 'images': [{'id': 'A3gGg_h4D053EFPLZSslW4oGkfGx4Yyo44cLXCFOpgw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/A3gGg_h4D053EFPLZSslW4oGkfGx4Yyo44cLXCFOpgw.png?width=108&crop=smart&auto=webp&s=896bd24dd1f76561582559f553e123d17978a7ac', 'width': 108}, {'height': 116, 'url': 'h... |
T5Gemma 2: The next generation of encoder-decoder models | 218 | T5Gemma 2 models, based on Gemma 3, are multilingual and multimodal, handling text and image input and generating text output, with open weights for three pretrained sizes (270M-270M, 1B-1B, and 4B-4B).
Key Features
* **Tied embeddings:** Embeddings are tied between the encoder and decoder. This significantly reduces... | 2025-12-18T19:17:53 | https://huggingface.co/collections/google/t5gemma-2 | Dear-Success-1441 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ppzhtq | false | null | t3_1ppzhtq | /r/LocalLLaMA/comments/1ppzhtq/t5gemma_2_the_next_generation_of_encoderdecoder/ | false | false | default | 218 | {'enabled': False, 'images': [{'id': '_rnSBYMvSInq6EN43nG_cTgBC4Jp6XTPNyUPRgnGKn0', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/_rnSBYMvSInq6EN43nG_cTgBC4Jp6XTPNyUPRgnGKn0.png?width=108&crop=smart&auto=webp&s=9b0eb56704c586c3afc96bfb0979dad083713b77', 'width': 108}, {'height': 116, 'url': 'h... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.