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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Hi, I'm new here and I'm looking for an LLM provider for study and role-playing. | 5 | Well, this is my story. I'm a software student, and recently we've been asked to do a project that has to do with LLM servers, so I've been looking for free servers for that and failing miserably. Although I admit that I've also been looking for these servers for roleplay, something like kicks before it became paid. I'... | 2025-09-19T13:29:21 | https://www.reddit.com/r/LocalLLaMA/comments/1nl3m43/hi_im_new_here_and_im_looking_for_an_llm_provider/ | Daylight_0708 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl3m43 | false | null | t3_1nl3m43 | /r/LocalLLaMA/comments/1nl3m43/hi_im_new_here_and_im_looking_for_an_llm_provider/ | false | false | self | 5 | null |
The new coderabbit cli tool is incredible | 0 | 2025-09-19T13:27:57 | https://v.redd.it/1eyd2787i4qf1 | Motor_Cycle7600 | /r/LocalLLaMA/comments/1nl3kxs/the_new_coderabbit_cli_tool_is_incredible/ | 1970-01-01T00:00:00 | 0 | {} | 1nl3kxs | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/1eyd2787i4qf1/DASHPlaylist.mpd?a=1761042276%2CM2UwNzFmM2NlY2UzZGU2Y2E1YzM5NzQ4YjQwM2UzZGIxODgxYzRjZTI0NzFmM2JiODJjZGFjNDA4NDIxN2FiNw%3D%3D&v=1&f=sd', 'duration': 137, 'fallback_url': 'https://v.redd.it/1eyd2787i4qf1/DASH_1080.mp4?source=fallback', '... | t3_1nl3kxs | /r/LocalLLaMA/comments/1nl3kxs/the_new_coderabbit_cli_tool_is_incredible/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'cHV2OXV4NzdpNHFmMcZyht-0YIVdicLMYIUqqzvtJfCrBkdrbd5yMoNloEzo', 'resolutions': [{'height': 73, 'url': 'https://external-preview.redd.it/cHV2OXV4NzdpNHFmMcZyht-0YIVdicLMYIUqqzvtJfCrBkdrbd5yMoNloEzo.png?width=108&crop=smart&format=pjpg&auto=webp&s=22dc618fa689bfe4e860e6d5ff5a2a49089aa... | ||
Thoughts about AI potentially winning Person of the Year? | 0 | 2025-09-19T13:06:19 | Extension-Cut-5535 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nl32gv | false | null | t3_1nl32gv | /r/LocalLLaMA/comments/1nl32gv/thoughts_about_ai_potentially_winning_person_of/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'vvb1cafie4qf1', 'resolutions': [{'height': 88, 'url': 'https://preview.redd.it/vvb1cafie4qf1.png?width=108&crop=smart&auto=webp&s=6a75f8ab58663d185d8447ddb8e937873d8cb43d', 'width': 108}, {'height': 177, 'url': 'https://preview.redd.it/vvb1cafie4qf1.png?width=216&crop=smart&auto=web... | ||
Able to use LMStudio plugins on Windows but not Linux? | 4 | I run LM Studio on both Windows 11 and Pop!_OS 22.04. On Windows, the sidebar shows a "Plugins" option right under Models. On Linux, that option isn’t there. Same version number, downloaded from the official site.
Is anyone else seeing this discrepancy? I haven’t found any release notes that explain whether the featur... | 2025-09-19T12:46:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nl2lgb/able_to_use_lmstudio_plugins_on_windows_but_not/ | FreshmanCult | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl2lgb | false | null | t3_1nl2lgb | /r/LocalLLaMA/comments/1nl2lgb/able_to_use_lmstudio_plugins_on_windows_but_not/ | false | false | self | 4 | null |
LLM association | 4 | I needed to analyze a complex scientific text and generate ideas.
Problems:
1. gpt oss gpt-oss-120b-F16 - uncreative and knows little
2. kimi-k2 - knows a lot, but is poor at expressing his thoughts mathematically.
What I did:
1. I learned everything kimi-k2 knows on the topic. Context - 60k
2. I changed the IP a... | 2025-09-19T12:41:39 | https://www.reddit.com/r/LocalLLaMA/comments/1nl2hym/llm_association/ | Defiant_Diet9085 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl2hym | false | null | t3_1nl2hym | /r/LocalLLaMA/comments/1nl2hym/llm_association/ | false | false | self | 4 | null |
How do you block telemetry of apps? | 0 | Some of you do use Proprietary / Closed source apps like Ollama, Msty, LMStudio, etc., Even I want to use those apps for few features. But how do you block telemetry of those apps? Any Opensource tools/utilities for this? | 2025-09-19T12:32:19 | https://www.reddit.com/r/LocalLLaMA/comments/1nl2ald/how_do_you_block_telemetry_of_apps/ | pmttyji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl2ald | false | null | t3_1nl2ald | /r/LocalLLaMA/comments/1nl2ald/how_do_you_block_telemetry_of_apps/ | false | false | self | 0 | null |
llama.cpp build 6517 fails to parse gpt-oss-20b harmony tags | 1 | Hi guys, llama.cpp fails to parse harmony tags for me.
https://preview.redd.it/s848nbcv14qf1.png?width=750&format=png&auto=webp&s=ed444dbd2a9c361e8d3d7d29be88082161979c98
Logs: [https://pastebin.com/7xQ1fLfk](https://pastebin.com/7xQ1fLfk)
version: 6517 (69ffd891)
built with cc (Ubuntu 11.4.0-1ubuntu1~22.04)... | 2025-09-19T11:59:32 | https://www.reddit.com/r/LocalLLaMA/comments/1nl1lb0/llamacpp_build_6517_fails_to_parse_gptoss20b/ | lifeequalsfalse | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl1lb0 | false | null | t3_1nl1lb0 | /r/LocalLLaMA/comments/1nl1lb0/llamacpp_build_6517_fails_to_parse_gptoss20b/ | false | false | 1 | null | |
Destkop CPU choice for inference: 8700G or 9900X? | 4 | Hi,
I'm building a new desktop and I also want it to run larger LLMs. I'm getting 192GB of DDR5-6000, and I'm installing a 7900 XTX along my old 7600 XT for a combined 40GB of VRAM.
I'm in doubt whether the 8700G's integrated graphics could bring something to the table when running larger parameter counts that don't ... | 2025-09-19T11:08:10 | https://www.reddit.com/r/LocalLLaMA/comments/1nl0lqk/destkop_cpu_choice_for_inference_8700g_or_9900x/ | spaceman_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl0lqk | false | null | t3_1nl0lqk | /r/LocalLLaMA/comments/1nl0lqk/destkop_cpu_choice_for_inference_8700g_or_9900x/ | false | false | self | 4 | null |
China will stop sharing more capable models, and so will frontier labs | 0 | [https://www.alignmentforum.org/posts/Bz2gPtqRJJDWyKxnX/ai-companies-have-started-saying-safeguards-are-load-bearing](https://www.alignmentforum.org/posts/Bz2gPtqRJJDWyKxnX/ai-companies-have-started-saying-safeguards-are-load-bearing)
>There are two ways to show that an AI system is safe: show that it doesn't have dan... | 2025-09-19T11:03:57 | https://www.reddit.com/r/LocalLLaMA/comments/1nl0j11/china_will_stop_sharing_more_capable_models_and/ | kaggleqrdl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nl0j11 | false | null | t3_1nl0j11 | /r/LocalLLaMA/comments/1nl0j11/china_will_stop_sharing_more_capable_models_and/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'yc3FKegVFTsn5106cI_Oymuw-5KC_sVfj1V3NGUsJ5w', 'resolutions': [{'height': 77, 'url': 'https://external-preview.redd.it/yc3FKegVFTsn5106cI_Oymuw-5KC_sVfj1V3NGUsJ5w.png?width=108&crop=smart&auto=webp&s=ac3c5d3fbed1eb5491cec16247f779e8145fc835', 'width': 108}, {'height': 154, 'url': 'h... |
AI-powered JEE prep tools (notes + flashcards + chatbot) 🚀📚 | 1 | Hey guys, I’ve been working on something fun — an AI-based study helper for JEE prep. It currently has:
📑 Topic-wise notes
🔗 NCERT reference links
🧠 Flashcards (concepts + practice questions)
🤖 Chatbot for quick doubt-solving
📝 Formula sheets (coming soon)
The idea is to make JEE prep a little less painful ... | 2025-09-19T10:56:47 | Distinct-Mode-7415 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nl0e21 | false | null | t3_1nl0e21 | /r/LocalLLaMA/comments/1nl0e21/aipowered_jee_prep_tools_notes_flashcards_chatbot/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'Ke2XaIl8jUz3nN_JgxM4qPvBUbXflqHEn50TPXbPHAo', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/i96iqoaer3qf1.png?width=108&crop=smart&auto=webp&s=0f2cf42174a02ecb88b3617c8cc8cb0be7990e55', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/i96iqoaer3qf1.pn... | ||
GitHub - gruai/koifish: A c++ framework on efficient training & fine-tuning LLMs | 22 | Now you can speed run training. Train GPT2-1558M in 30 hours on a single 4090! | 2025-09-19T10:52:28 | https://github.com/gruai/koifish | DeltaSqueezer | github.com | 1970-01-01T00:00:00 | 0 | {} | 1nl0bay | false | null | t3_1nl0bay | /r/LocalLLaMA/comments/1nl0bay/github_gruaikoifish_a_c_framework_on_efficient/ | false | false | default | 22 | {'enabled': False, 'images': [{'id': 'Ip5tq3IGjmyJr17Rld7StDK76hE-5Hx6xnwIgFhhwT8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Ip5tq3IGjmyJr17Rld7StDK76hE-5Hx6xnwIgFhhwT8.png?width=108&crop=smart&auto=webp&s=305c682adebb304e23b7aa4c05d43efffcdcd347', 'width': 108}, {'height': 108, 'url': 'h... |
Most people who say "LLMs are so stupid" totally fall into this trap | 0 | 2025-09-19T10:50:12 | FinnFarrow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nl09ur | false | null | t3_1nl09ur | /r/LocalLLaMA/comments/1nl09ur/most_people_who_say_llms_are_so_stupid_totally/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'GXOeeCISgU0Z8xs3smV9m7V2V4XGHmRrOlQCylWYNCU', 'resolutions': [{'height': 106, 'url': 'https://preview.redd.it/5s462dg5q3qf1.png?width=108&crop=smart&auto=webp&s=d82dd29462bde518e5d7f534c3982ee928079fa6', 'width': 108}, {'height': 213, 'url': 'https://preview.redd.it/5s462dg5q3qf1.pn... | |||
Zenbot Chrome Nonautomation - An LLM-Driven Web Co-Browser using Smolagents, Zendriver, Trafilatura | 1 | [removed] | 2025-09-19T09:58:43 | https://github.com/michaelsoftmd/zenbot-chrome | dredgesta | github.com | 1970-01-01T00:00:00 | 0 | {} | 1nkzeij | false | null | t3_1nkzeij | /r/LocalLLaMA/comments/1nkzeij/zenbot_chrome_nonautomation_an_llmdriven_web/ | false | false | default | 1 | null |
Today I'm competing against Apple on Product Hunt. I need some help, guys. | 0 | Two years ago I left my job( tesla ) to build SuperU - an AI voice agent platform. For this, i burned through savings, lived on ramen, coded in my apartment, the whole thing.
I launched on Product Hunt today and just found out Google and Apple are launching their products the same day. My heart literally sank when I s... | 2025-09-19T09:58:39 | Distinct_Criticism36 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkzehc | false | null | t3_1nkzehc | /r/LocalLLaMA/comments/1nkzehc/today_im_competing_against_apple_on_product_hunt/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'p1rc3d7xg3qf1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/p1rc3d7xg3qf1.jpeg?width=108&crop=smart&auto=webp&s=9e9bafb17ef5fc21abf8eac5f0b8875ce70af735', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/p1rc3d7xg3qf1.jpeg?width=216&crop=smart&auto=... | |
Introducing Zenbot - Your Web Browser Companion | 1 | [removed] | 2025-09-19T09:48:26 | https://www.reddit.com/r/LocalLLaMA/comments/1nkz8ck/introducing_zenbot_your_web_browser_companion/ | dredgesta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkz8ck | false | null | t3_1nkz8ck | /r/LocalLLaMA/comments/1nkz8ck/introducing_zenbot_your_web_browser_companion/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'MFq-9F2ZNcKykUryu4kDKZRxKS1KeBKrueOZlpoNcz8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MFq-9F2ZNcKykUryu4kDKZRxKS1KeBKrueOZlpoNcz8.png?width=108&crop=smart&auto=webp&s=4e615e91bc22f6485dd80d2dad7e6bb3fcd4a03a', 'width': 108}, {'height': 108, 'url': 'h... | |
Introducing Zenbot - Your Web Browser Companion | 1 | [removed] | 2025-09-19T09:39:55 | https://www.reddit.com/r/LocalLLaMA/comments/1nkz3d5/introducing_zenbot_your_web_browser_companion/ | dredgesta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkz3d5 | false | null | t3_1nkz3d5 | /r/LocalLLaMA/comments/1nkz3d5/introducing_zenbot_your_web_browser_companion/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'MFq-9F2ZNcKykUryu4kDKZRxKS1KeBKrueOZlpoNcz8', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/MFq-9F2ZNcKykUryu4kDKZRxKS1KeBKrueOZlpoNcz8.png?width=108&crop=smart&auto=webp&s=4e615e91bc22f6485dd80d2dad7e6bb3fcd4a03a', 'width': 108}, {'height': 108, 'url': 'h... |
Solutions to the sycophant problem? | 8 | tl;dr - are there any models that handle conflict in a realistic way? That is to say, characters in-fiction will refuse each other and behave somewhat rationally.
\---
I've been playing around with AI as a writing assistant, essentially prompting it with what I have so far and seeing how it might complete a sentence/... | 2025-09-19T09:26:32 | https://www.reddit.com/r/LocalLLaMA/comments/1nkyvty/solutions_to_the_sycophant_problem/ | TurpentineEnjoyer | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkyvty | false | null | t3_1nkyvty | /r/LocalLLaMA/comments/1nkyvty/solutions_to_the_sycophant_problem/ | false | false | self | 8 | null |
nvivida vs Mac Studio M4 Max - gemma3 vision input performance Q | 0 | So for gemma3 12b with the appropriate mmproj in llama3-tmtd-cli ,
I'm seeing an RTX4090 (\~1000gb/sec memory) encode image input near instantly '252ms'
.. whilst the mac studio M4 36gb (400gb/sec memory) takes around at least 6 seconds.
the gap is huge, wheras for text inference the gap is closer to the memory b... | 2025-09-19T09:23:26 | https://www.reddit.com/r/LocalLLaMA/comments/1nkyu2c/nvivida_vs_mac_studio_m4_max_gemma3_vision_input/ | dobkeratops | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkyu2c | false | null | t3_1nkyu2c | /r/LocalLLaMA/comments/1nkyu2c/nvivida_vs_mac_studio_m4_max_gemma3_vision_input/ | false | false | self | 0 | null |
I want to get y'all's take on KV Cache | 0 | My whole LYRN system is built around efficient KV cache reuse and it's essentially turning the system prompt into an entire stateful mindspace. I wanted to see what you guys understand KV cache to be and how you are using it with your systems.
I think that KV cache is the greatest thing since sliced bread and I compl... | 2025-09-19T09:22:13 | https://www.reddit.com/r/LocalLLaMA/comments/1nkytdh/i_want_to_get_yalls_take_on_kv_cache/ | PayBetter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkytdh | false | null | t3_1nkytdh | /r/LocalLLaMA/comments/1nkytdh/i_want_to_get_yalls_take_on_kv_cache/ | false | false | self | 0 | null |
What are your most-wanted datasets? | 2 | We have received a grant and would like to spend a portion of the funds on curating and releasing free and open source datasets on huggingface, what would you say are the modalities / types of datasets you would like to have readily available? | 2025-09-19T09:17:12 | https://www.reddit.com/r/LocalLLaMA/comments/1nkyqpy/what_are_your_mostwanted_datasets/ | superbardibros | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkyqpy | false | null | t3_1nkyqpy | /r/LocalLLaMA/comments/1nkyqpy/what_are_your_mostwanted_datasets/ | false | false | self | 2 | null |
SFT for response style: train on per-turn completion tokens converges fast, train on assistant only responses underfits | 2 | Hey folks, looking for advice on SFT setup for “baking in” response style on a small multi-turn conv dataset (\~10k samples, multi turn conversations, mostly english and code mixed hindi and english)
I tried two approaches
1. train on assistant responses only (user and system prompt is masked)
2. train on completio... | 2025-09-19T09:13:58 | https://www.reddit.com/r/LocalLLaMA/comments/1nkyoym/sft_for_response_style_train_on_perturn/ | okbromonke | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkyoym | false | null | t3_1nkyoym | /r/LocalLLaMA/comments/1nkyoym/sft_for_response_style_train_on_perturn/ | false | false | self | 2 | null |
Do we have any Android/Windows app that has a playground feature for base LLMs | 2 | Thx.
| 2025-09-19T09:04:04 | https://www.reddit.com/r/LocalLLaMA/comments/1nkyjl9/do_we_have_any_androidwindows_app_that_has_a/ | Own-Potential-2308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkyjl9 | false | null | t3_1nkyjl9 | /r/LocalLLaMA/comments/1nkyjl9/do_we_have_any_androidwindows_app_that_has_a/ | false | false | self | 2 | null |
GPU power limiting measurements update | 48 | This is an update to this thread: [https://old.reddit.com/r/LocalLLaMA/comments/1n89wi8/power\_limit\_your\_gpus\_to\_reduce\_electricity\_costs/](https://old.reddit.com/r/LocalLLaMA/comments/1n89wi8/power_limit_your_gpus_to_reduce_electricity_costs/)
In that thread I was recommended to use a special tool from Nvidia ... | 2025-09-19T08:51:47 | https://www.reddit.com/gallery/1nkycpq | MelodicRecognition7 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nkycpq | false | null | t3_1nkycpq | /r/LocalLLaMA/comments/1nkycpq/gpu_power_limiting_measurements_update/ | false | false | 48 | null | |
ssd on m.2 to chipset vs directly to CPU? f | 1 | so i'm considering the asus pro creator x870e, which has 2 pcie gen 5.0x16
now if i understand correctly if i use dual GPU setup it would give m2 x8, but if i add the m.2 ssd on the top slot i would get x8 for first GPU and x4 for the 2nd GPU and x4 for the ssd
but if i use the m.2 slot connected to the chipset i w... | 2025-09-19T08:44:02 | https://www.reddit.com/r/LocalLLaMA/comments/1nky8c4/ssd_on_m2_to_chipset_vs_directly_to_cpu_f/ | emaayan | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nky8c4 | false | null | t3_1nky8c4 | /r/LocalLLaMA/comments/1nky8c4/ssd_on_m2_to_chipset_vs_directly_to_cpu_f/ | false | false | self | 1 | null |
I made project called Local Agent personal artificial intelligence also known as LAPAI, i need some advice or what do you think about my project, because i still new on this thing, AI offline for support dev integrate AI to their project entirely offline | 9 | Here i made AI engine that improve and enhance tiny model like 8B have ability to have memory and stuff like that, and work entirely offline the reason for this it's for support dev who want to integrate AI to their project without data go to cloud, entirely offline, but i still need some advice, because i am still new... | 2025-09-19T08:33:57 | https://www.reddit.com/r/LocalLLaMA/comments/1nky2vh/i_made_project_called_local_agent_personal/ | Ambitious_Cry3080 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nky2vh | false | null | t3_1nky2vh | /r/LocalLLaMA/comments/1nky2vh/i_made_project_called_local_agent_personal/ | false | false | self | 9 | {'enabled': False, 'images': [{'id': 'Yhih5PwKa-ZXXfZXRpN9in-Szwct0zQu7PBeMEwjA0U', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Yhih5PwKa-ZXXfZXRpN9in-Szwct0zQu7PBeMEwjA0U.png?width=108&crop=smart&auto=webp&s=5a8faec068e4241814b46e0e9e2dbf209ffc2566', 'width': 108}, {'height': 108, 'url': 'h... |
The comparison results between Qwen3-Next-80B-A3B and Qwen3-30B-A3B are similar. Why? | 1 | [removed] | 2025-09-19T08:32:07 | https://www.reddit.com/r/LocalLLaMA/comments/1nky1wf/the_comparison_results_between_qwen3next80ba3b/ | ProfitFeeling216 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nky1wf | false | null | t3_1nky1wf | /r/LocalLLaMA/comments/1nky1wf/the_comparison_results_between_qwen3next80ba3b/ | false | false | self | 1 | null |
Found a Handy Study & Exam Resource — Examsprint | 1 | Hey folks, I came across Examsprint and thought it might be useful for students here.
👉 What it offers:
Exam prep resources (notes, practice Qs, tips)
Study-friendly layout (clean, mobile-friendly)
Free access (no annoying popups or ads)
Updated material for different boards/exams
If you’re into local/community... | 2025-09-19T08:29:45 | Immediate_Video_2850 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nky0js | false | null | t3_1nky0js | /r/LocalLLaMA/comments/1nky0js/found_a_handy_study_exam_resource_examsprint/ | false | false | 1 | {'enabled': True, 'images': [{'id': 'IB2ppBX1UeO6l4jmrwhptMluPLa1mV_v8N4Imn74_QM', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/04hhuxy513qf1.jpeg?width=108&crop=smart&auto=webp&s=a048aebb139de7365da7501fca629ee35219eba2', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/04hhuxy513qf1.j... | ||
Use VLLM to guard your house | 1 | 2025-09-19T07:58:35 | https://www.reddit.com/r/LocalLLaMA/comments/1nkxjch/use_vllm_to_guard_your_house/ | LJ-Hao | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkxjch | false | null | t3_1nkxjch | /r/LocalLLaMA/comments/1nkxjch/use_vllm_to_guard_your_house/ | false | false | 1 | null | ||
Documents-Parsing-Lab : Exploring OCR & Document AI models on real-world PDFs, tables, and charts | 1 | [removed] | 2025-09-19T07:56:41 | https://www.reddit.com/r/LocalLLaMA/comments/1nkxich/documentsparsinglab_exploring_ocr_document_ai/ | Mobile-Cartoonist-48 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkxich | false | null | t3_1nkxich | /r/LocalLLaMA/comments/1nkxich/documentsparsinglab_exploring_ocr_document_ai/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '0oeL8KVUDiLyZN1M4ZcMjiM7HZASZNfFI62TNGdRVpo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0oeL8KVUDiLyZN1M4ZcMjiM7HZASZNfFI62TNGdRVpo.png?width=108&crop=smart&auto=webp&s=1ed533a7be66c339b5c0b583703db1956c8cd376', 'width': 108}, {'height': 108, 'url': 'h... |
Everyone’s trying vectors and graphs for AI memory. We went back to SQL. | 245 | When we first started building with LLMs, the gap was obvious: they could reason well in the moment, but forgot everything as soon as the conversation moved on.
You could tell an agent, *“I don’t like coffee,”* and three steps later it would suggest espresso again. It wasn’t broken logic, it was missing memory.
Over ... | 2025-09-19T07:17:52 | https://www.reddit.com/r/LocalLLaMA/comments/1nkwx12/everyones_trying_vectors_and_graphs_for_ai_memory/ | Arindam_200 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkwx12 | false | null | t3_1nkwx12 | /r/LocalLLaMA/comments/1nkwx12/everyones_trying_vectors_and_graphs_for_ai_memory/ | false | false | self | 245 | {'enabled': False, 'images': [{'id': '5CIvF7mkfXgexa7qOnPDVB8ezpM2-4q4ovSFJmhz71Y', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/5CIvF7mkfXgexa7qOnPDVB8ezpM2-4q4ovSFJmhz71Y.png?width=108&crop=smart&auto=webp&s=3fb82fa807d6ffbe8bcf55a6f25b45bd80e321f7', 'width': 108}, {'height': 108, 'url': 'h... |
Streaming TTS on google colab? | 3 | I'm looking for a TTS that can work with a streaming text from a LLM, and also able to run on colab. I been looking for one but only saw stuff that only work on a laptop/pc and not colab, so i don't know if it even possible. | 2025-09-19T06:57:20 | https://www.reddit.com/r/LocalLLaMA/comments/1nkwl09/streaming_tts_on_google_colab/ | Kiyumaa | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkwl09 | false | null | t3_1nkwl09 | /r/LocalLLaMA/comments/1nkwl09/streaming_tts_on_google_colab/ | false | false | self | 3 | null |
Grok 2 anyone? | 0 | I feel a little dirty even bringing it up considering that it came from an org headed by a literal nazi but am still a little curious about it. At 250B it's about the same class as Qwen3 and GLM 4.5, two of the best open source/weight models, but one generation behind which should make for interesting comparisons.
Any... | 2025-09-19T06:49:01 | https://www.reddit.com/r/LocalLLaMA/comments/1nkwgew/grok_2_anyone/ | ikkiyikki | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkwgew | false | null | t3_1nkwgew | /r/LocalLLaMA/comments/1nkwgew/grok_2_anyone/ | false | false | self | 0 | null |
Unit-test style fairness / bias checks for LLM prompts. Worth building? | 3 | Bias in LLMs doesn't just come from the training data but also shows up at the prompt layer too within applications. The same template can generate very different tones for different cohorts (e.g. job postings - one role such as lawyer gets "ambitious and driven," another such as a nurse gets "caring and nurturing"). R... | 2025-09-19T06:43:47 | https://www.reddit.com/r/LocalLLaMA/comments/1nkwdel/unittest_style_fairness_bias_checks_for_llm/ | The__Bear_Jew | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkwdel | false | null | t3_1nkwdel | /r/LocalLLaMA/comments/1nkwdel/unittest_style_fairness_bias_checks_for_llm/ | false | false | self | 3 | null |
Favorite agentic coding llm up to 144GB of vram? | 17 | Hi,
in past weeks I've been evaluating agentic coding setups on server with 6x 24 GB gpus (5x 3090 + 1x 4090).
I'd like to have setup that will allow me to have inline completion (can be separate model) and agentic coder (crush, opencode, codex, ...).
Inline completion isn't really issue I use [https://github.com... | 2025-09-19T06:35:44 | https://www.reddit.com/r/LocalLLaMA/comments/1nkw8v6/favorite_agentic_coding_llm_up_to_144gb_of_vram/ | Grouchy_Ad_4750 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkw8v6 | false | null | t3_1nkw8v6 | /r/LocalLLaMA/comments/1nkw8v6/favorite_agentic_coding_llm_up_to_144gb_of_vram/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'Iwf9JRlZ5dU1u_zmUtnWK5kCBNPVy7DYwTAKBKaezNo', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Iwf9JRlZ5dU1u_zmUtnWK5kCBNPVy7DYwTAKBKaezNo.png?width=108&crop=smart&auto=webp&s=66b8f9bd2a9976229dc51d81de1811558bed13f3', 'width': 108}, {'height': 108, 'url': 'h... |
when canva needed domo’s spice | 0 | built a boring slide deck in canva. exported the images, ran them through domo restyle with retro zine vibes. suddenly school project looked like comic flyers. canva = base, domoai = flair. | 2025-09-19T06:01:53 | https://www.reddit.com/r/LocalLLaMA/comments/1nkvowm/when_canva_needed_domos_spice/ | lailith_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkvowm | false | null | t3_1nkvowm | /r/LocalLLaMA/comments/1nkvowm/when_canva_needed_domos_spice/ | false | false | self | 0 | null |
Gemma 3 27b context shifting not supported in llama.cpp? | 3 | I’ve recently upgraded my VRAM and decided to finally switch to llama.cpp for my inference, and a huge issue with Gemma 3 that I had on ollama is gone now - it doesn’t take half an hour to get to the first token on huge context!
But now I have a different problem:
```
common_init_from_params: KV cache shifting is not ... | 2025-09-19T05:55:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nkvkle/gemma_3_27b_context_shifting_not_supported_in/ | ABLPHA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkvkle | false | null | t3_1nkvkle | /r/LocalLLaMA/comments/1nkvkle/gemma_3_27b_context_shifting_not_supported_in/ | false | false | self | 3 | null |
Wow, Moondream 3 preview is goated | 432 | If the "preview" is this great, how great will the full model be? | 2025-09-19T05:48:41 | Brave-Hold-9389 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkvgn0 | false | null | t3_1nkvgn0 | /r/LocalLLaMA/comments/1nkvgn0/wow_moondream_3_preview_is_goated/ | false | false | 432 | {'enabled': True, 'images': [{'id': 'xUR_Rr73-8QFKoiGKfPpF7PS4T1VUkgvYJfvRt2U1Nc', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/nwfm02if82qf1.jpeg?width=108&crop=smart&auto=webp&s=109dd33a67670e97c3433a396112fc60c00098c5', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/nwfm02if82qf1.j... | ||
Ideas on AI coding companion (NOT coding assistent) | 1 | I’ve been thinking about building a coding companion that combines Live2D, LLMs, and multimodal interactions. The concept is somewhat similar to *Neuro-sama*, but instead of focusing on gaming, it’s designed to accompany developers while they’re working on projects.
The inspiration came from a Chinese company that cre... | 2025-09-19T05:11:37 | https://www.reddit.com/r/LocalLLaMA/comments/1nkuts7/ideas_on_ai_coding_companion_not_coding_assistent/ | Overall_Two_2447 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkuts7 | false | null | t3_1nkuts7 | /r/LocalLLaMA/comments/1nkuts7/ideas_on_ai_coding_companion_not_coding_assistent/ | false | false | self | 1 | null |
Depth upscaling? | 0 | I was and still am incredibly fascinated with the concept of "Depth Upscaling" (DUS) and how the solar model felt really smart especially considering it only had around 11b parameters Given that most of us do not have the hardware or budget to pretrain models at home, I was never able to try it in practice for myself. ... | 2025-09-19T04:55:44 | https://www.reddit.com/r/LocalLLaMA/comments/1nkuj6z/depth_upscaling/ | WyattTheSkid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkuj6z | false | null | t3_1nkuj6z | /r/LocalLLaMA/comments/1nkuj6z/depth_upscaling/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': '9GgDYkPT-Gxip2OFhO7vxaxnJ4YtO6DF4-8qcJNHN4M', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/9GgDYkPT-Gxip2OFhO7vxaxnJ4YtO6DF4-8qcJNHN4M.png?width=108&crop=smart&auto=webp&s=3fb1f71e89eea175a5ad0701bcb97fb17f89c367', 'width': 108}, {'height': 116, 'url': 'h... |
NVIDIA + Intel collab means better models for us locally | 17 | I think this personal computing announcement directly implies they’re building unified memory similar to Apple devices
https://newsroom.intel.com/artificial-intelligence/intel-and-nvidia-to-jointly-develop-ai-infrastructure-and-personal-computing-products | 2025-09-19T04:46:35 | https://www.reddit.com/r/LocalLLaMA/comments/1nkud68/nvidia_intel_collab_means_better_models_for_us/ | ChipCrafty4327 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkud68 | false | null | t3_1nkud68 | /r/LocalLLaMA/comments/1nkud68/nvidia_intel_collab_means_better_models_for_us/ | false | false | self | 17 | {'enabled': False, 'images': [{'id': 'NFgrUkd8cvY6wu9MojRIISpVL-PMVNB83Uxn_op60Js', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/NFgrUkd8cvY6wu9MojRIISpVL-PMVNB83Uxn_op60Js.jpeg?width=108&crop=smart&auto=webp&s=3f62a6499e5d21d7f3de6655baa69ada657f55c9', 'width': 108}, {'height': 121, 'url': '... |
What have you found to be the most empathetic/conversational <96GB local model? | 3 | I'm doing some evaluations in consideration for experimenting with a personal companion/journal, and am curious what folks have found to be the most conversational, personable, and empathetic/high-EQ model under 96GB. gemma3:27b has been pretty solid in my testing, and the Dolphin Venice Mistral tune is exceptional in ... | 2025-09-19T04:45:04 | https://www.reddit.com/r/LocalLLaMA/comments/1nkuc4u/what_have_you_found_to_be_the_most/ | CharlesStross | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkuc4u | false | null | t3_1nkuc4u | /r/LocalLLaMA/comments/1nkuc4u/what_have_you_found_to_be_the_most/ | false | false | self | 3 | null |
RTX 3080 10gb vs M4 pro 24gb for LocalLLM | 1 | Hello!
I just got permission to use local LLM to help with coding 'VSCode' using Continue extension. For my work.
I have two platforms as I mentioned, an 3080 and a MBP M4 pro with 24gb unified memory. I am currently setting up work pc and appreciate the responses and tips if you guys have any! | 2025-09-19T04:41:49 | https://www.reddit.com/r/LocalLLaMA/comments/1nkua0k/rtx_3080_10gb_vs_m4_pro_24gb_for_localllm/ | exivor01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkua0k | false | null | t3_1nkua0k | /r/LocalLLaMA/comments/1nkua0k/rtx_3080_10gb_vs_m4_pro_24gb_for_localllm/ | false | false | self | 1 | null |
SongBloom : Open-Sourced model for full song generation with vocals and instruments, 2 minute> audios | 1 | Developed by researchers from **CUHK, Tencent, and Nanjing University**
Generates **coherent** full-length songs
Includes lyrics, vocals, instruments
Creates intros, choruses, outros
Produces songs **2+ minutes** long
Huggingface : [https://huggingface.co/CypressYang/SongBloom](https://huggingface.co/CypressYan... | 2025-09-19T04:39:31 | https://www.reddit.com/r/LocalLLaMA/comments/1nku8hb/songbloom_opensourced_model_for_full_song/ | Technical-Love-8479 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nku8hb | false | null | t3_1nku8hb | /r/LocalLLaMA/comments/1nku8hb/songbloom_opensourced_model_for_full_song/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '8kBUKotVk1MdYn1G2e50R_3DFd4CFoPZ68RHxREyxDw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/8kBUKotVk1MdYn1G2e50R_3DFd4CFoPZ68RHxREyxDw.png?width=108&crop=smart&auto=webp&s=fe6d85a475e3d60ba03ce36f13effb312d26b611', 'width': 108}, {'height': 116, 'url': 'h... |
Open source Voice AI Agents | 8 | Hello!
Is there any Ready-to-go open source Voice AI Agents/pipelines like 11Labs's AI Agents?
I've found intervo.ai, but it seems dead. I also know about LiveKit, but this one not Ready-to-go at all. | 2025-09-19T04:10:48 | https://www.reddit.com/r/LocalLLaMA/comments/1nktpac/open_source_voice_ai_agents/ | MrCrabPhantom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nktpac | false | null | t3_1nktpac | /r/LocalLLaMA/comments/1nktpac/open_source_voice_ai_agents/ | false | false | self | 8 | null |
Frustrated by inability to perform simple human tasks | 0 | I love LLMs but I am frustrated I can't get any to do the following simple human task. I want to summarize the plays that are either currently on or upcoming in my area. For each of them I want any published star ratings along with the source of the rating.
Can any local model do this? | 2025-09-19T04:03:39 | https://www.reddit.com/r/LocalLLaMA/comments/1nktkcx/frustrated_by_inability_to_perform_simple_human/ | MrMrsPotts | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nktkcx | false | null | t3_1nktkcx | /r/LocalLLaMA/comments/1nktkcx/frustrated_by_inability_to_perform_simple_human/ | false | false | self | 0 | null |
New Wan MoE video model | 185 | Wan AI just dropped this new MoE video diffusion model: Wan2.2-Animate-14B | 2025-09-19T03:57:51 | https://huggingface.co/Wan-AI/Wan2.2-Animate-14B | edward-dev | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1nktfxl | false | null | t3_1nktfxl | /r/LocalLLaMA/comments/1nktfxl/new_wan_moe_video_model/ | false | false | 185 | {'enabled': False, 'images': [{'id': 'TgMeHU4GJUa5aR0M3117isJqdoSEY-Q0uxO6S138yuw', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/TgMeHU4GJUa5aR0M3117isJqdoSEY-Q0uxO6S138yuw.png?width=108&crop=smart&auto=webp&s=1cabb3203dd2428008dcf71b7e06f5b9b6c4df14', 'width': 108}, {'height': 116, 'url': 'h... | |
Name of this model | 0 | Name of this model | 2025-09-19T03:54:04 | Ravi1802 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nktdab | false | null | t3_1nktdab | /r/LocalLLaMA/comments/1nktdab/name_of_this_model/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'jo4z22czn1qf1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/jo4z22czn1qf1.jpeg?width=108&crop=smart&auto=webp&s=3bdf26bb66678080f8d89ccb63408841c3ce4165', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/jo4z22czn1qf1.jpeg?width=216&crop=smart&auto=... | |
Serving API for personal use?? | 0 | HI, what service can I use to make an API to use uncensored model for personal private use like lambda AI vastai runpod etc??? I want it to be an API and id like to serve custom API tool not something super premade so I can either call it from python or call it from my discord bot. Thanks… | 2025-09-19T03:41:39 | https://www.reddit.com/r/LocalLLaMA/comments/1nkt4ju/serving_api_for_personal_use/ | KaouSakura | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkt4ju | false | null | t3_1nkt4ju | /r/LocalLLaMA/comments/1nkt4ju/serving_api_for_personal_use/ | false | false | self | 0 | null |
What's your favorite all-rounder stack? | 8 | I've been a little curious about this for a while now, if you wanted to run a single server that could do a little of everything with local LLMs, what would your combo be? I see a lot of people mentioning the downsides of ollama, when other ones can shine, preferred ways to run MCP servers or other tool servicesfor RAG... | 2025-09-19T02:12:34 | https://www.reddit.com/r/LocalLLaMA/comments/1nkrau1/whats_your_favorite_allrounder_stack/ | SocietyTomorrow | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkrau1 | false | null | t3_1nkrau1 | /r/LocalLLaMA/comments/1nkrau1/whats_your_favorite_allrounder_stack/ | false | false | self | 8 | null |
Qwen3-Next experience so far | 156 | I have been using this model as my primary model and its safe to say , the benchmarks don't lie.
This model is amazing, i have been using a mix of GLM-4.5-Air, Gpt-oss-120b, llama 4 scout and llama 3.3 in comparison to it.
And its safe to say it beat them by a good margin , i used both the thinking and instruct ... | 2025-09-19T02:07:13 | https://www.reddit.com/r/LocalLLaMA/comments/1nkr6op/qwen3next_experience_so_far/ | Daemontatox | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkr6op | false | null | t3_1nkr6op | /r/LocalLLaMA/comments/1nkr6op/qwen3next_experience_so_far/ | false | false | self | 156 | null |
ModernBERT for financial domain | 4 | Fin-ModernBERT is a domain-adapted pretrained language model for the **financial domain**, obtained by continual pretraining of [ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) with a **context length of 1024 tokens** on large-scale finance-related corpora.
[Fin-ModernBERT](https://huggingface.co... | 2025-09-19T01:57:24 | https://www.reddit.com/r/LocalLLaMA/comments/1nkqz4j/modernbert_for_financial_domain/ | hungnm009 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkqz4j | false | null | t3_1nkqz4j | /r/LocalLLaMA/comments/1nkqz4j/modernbert_for_financial_domain/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'iuwZRbPUy1HTAXteDMQohDvRsb7U_InfZ-bqT99kqR8', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/iuwZRbPUy1HTAXteDMQohDvRsb7U_InfZ-bqT99kqR8.png?width=108&crop=smart&auto=webp&s=bab16fdbc54f2f24ee0e30bc7280216211b057c7', 'width': 108}, {'height': 116, 'url': 'h... |
Improved performance for Qwen3-next 80B on MLX, now on LM Studio (v0.27.1) | 1 | Thanks to Gated-Delta Fused Kernel (Qwen3Next) - [https://github.com/ml-explore/mlx-lm/pull/454](https://github.com/ml-explore/mlx-lm/pull/454)
| 2025-09-19T01:31:54 | onil_gova | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkqffd | false | null | t3_1nkqffd | /r/LocalLLaMA/comments/1nkqffd/improved_performance_for_qwen3next_80b_on_mlx_now/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': '6659pzv2y0qf1', 'resolutions': [{'height': 120, 'url': 'https://preview.redd.it/6659pzv2y0qf1.jpeg?width=108&crop=smart&auto=webp&s=71265bed544ca5e86017e32cb8688df99e92e74b', 'width': 108}, {'height': 240, 'url': 'https://preview.redd.it/6659pzv2y0qf1.jpeg?width=216&crop=smart&auto=... | |
Anyone have access to the Nemotron Dataset(s)? | 4 | Hi guys, idk what happened but for some reason I got denied access to the nemotron pretraining datasets (the sft and the code ones). I used my institutional email address as requested idk what happened. Was wondering if anyone had torrents or a mirror of them they wouldn’t mind sharing. Thanks | 2025-09-19T01:22:14 | https://www.reddit.com/r/LocalLLaMA/comments/1nkq84j/anyone_have_access_to_the_nemotron_datasets/ | WyattTheSkid | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkq84j | false | null | t3_1nkq84j | /r/LocalLLaMA/comments/1nkq84j/anyone_have_access_to_the_nemotron_datasets/ | false | false | self | 4 | null |
I can can get GPUs as a tax write off. Thinking of doubling down on my LLM/ML learning adventure by buying one or two RTX 6000 pros. | 30 | I was having a lot of fun a few months back learning graph/vector based RAG. Then work unloaded a ridiculous level of work. I started by trying to use my ASUS M16 with a 4090 for local 3b models. It didn't work as I hoped. Now I'll probably sell the thing to build a local desktop rig that I can remotely use across the ... | 2025-09-19T00:56:21 | https://www.reddit.com/r/LocalLLaMA/comments/1nkpohe/i_can_can_get_gpus_as_a_tax_write_off_thinking_of/ | Tired__Dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkpohe | false | null | t3_1nkpohe | /r/LocalLLaMA/comments/1nkpohe/i_can_can_get_gpus_as_a_tax_write_off_thinking_of/ | false | false | self | 30 | null |
Poor man's LLM server | 2 | 2025-09-18T23:44:41 | rayzinnz | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nko504 | false | null | t3_1nko504 | /r/LocalLLaMA/comments/1nko504/poor_mans_llm_server/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': 'yoy5eknhf0qf1', 'resolutions': [{'height': 96, 'url': 'https://preview.redd.it/yoy5eknhf0qf1.jpeg?width=108&crop=smart&auto=webp&s=af60334879ed7b4c1be9c82f89985c772712eef4', 'width': 108}, {'height': 192, 'url': 'https://preview.redd.it/yoy5eknhf0qf1.jpeg?width=216&crop=smart&auto=w... | ||
System prompt to make a model help users guess its name? | 31 | I’m working on this bot (you can find it in the /r/LocalLLaMa Discord server) that plays a game asking users to guess which model it is. My system prompt asks the model to switch to riddles if the user directly asks for its identity, because that’s how some users may choose to play the game. But what I’m finding is tha... | 2025-09-18T23:24:54 | entsnack | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nknpgd | false | null | t3_1nknpgd | /r/LocalLLaMA/comments/1nknpgd/system_prompt_to_make_a_model_help_users_guess/ | false | false | default | 31 | {'enabled': True, 'images': [{'id': 'shq50qtyb0qf1', 'resolutions': [{'height': 77, 'url': 'https://preview.redd.it/shq50qtyb0qf1.jpeg?width=108&crop=smart&auto=webp&s=3afb49b28141ec8c24206209ad149b295d9e19aa', 'width': 108}, {'height': 154, 'url': 'https://preview.redd.it/shq50qtyb0qf1.jpeg?width=216&crop=smart&auto=w... | |
[Research] Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens | 13 | I thought this would be relevant for us here in local llama, since reasoning models are coming into fashion for local inference, with the new GPT OSS models and friends (and that reflexion fiasco; for those that remember) | 2025-09-18T23:19:10 | https://arxiv.org/abs/2508.01191 | Confident-Honeydew66 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1nknkyr | false | null | t3_1nknkyr | /r/LocalLLaMA/comments/1nknkyr/research_is_chainofthought_reasoning_of_llms_a/ | false | false | default | 13 | null |
Vllm with mistral small 3.2 | 1 | Hi, I have a VM with Ubuntu running vllm with unsloth mistral small (tried 3.2 gguf and 3.1 awq). Previously I had same 3.2 but in ollama. Running in nvidia L4 24gb
Problem is that inference speed is much slower in vllm for some reason. Context with 500 tokens and output with 100.
What am I missing here? Does someone... | 2025-09-18T23:11:16 | https://www.reddit.com/r/LocalLLaMA/comments/1nknen7/vllm_with_mistral_small_32/ | justlows | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nknen7 | false | null | t3_1nknen7 | /r/LocalLLaMA/comments/1nknen7/vllm_with_mistral_small_32/ | false | false | self | 1 | null |
Moondream 3 (Preview) -- hybrid reasoning vision language model | 114 | 2025-09-18T22:24:59 | https://huggingface.co/moondream/moondream3-preview | radiiquark | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1nkmc7z | false | null | t3_1nkmc7z | /r/LocalLLaMA/comments/1nkmc7z/moondream_3_preview_hybrid_reasoning_vision/ | false | false | default | 114 | {'enabled': False, 'images': [{'id': '4djziNvQ2zvOfJv3_xVajpCMtf-Z4Exi5Qyi8qcyMmc', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/4djziNvQ2zvOfJv3_xVajpCMtf-Z4Exi5Qyi8qcyMmc.png?width=108&crop=smart&auto=webp&s=7f4bc05396c9eef82562c7442117229573183441', 'width': 108}, {'height': 116, 'url': 'h... | |
Could small language models (SLMs) be a better fit for domain-specific tasks? | 4 | Hi everyone! Quick question for those working with AI models: do you think we might be over-relying on large language models even when we don’t need all their capabilities? I’m exploring whether there’s a shift happening toward using smaller, more niche-focused models SLMs that are fine-tuned just for a specific domain... | 2025-09-18T22:15:37 | https://www.reddit.com/r/LocalLLaMA/comments/1nkm44c/could_small_language_models_slms_be_a_better_fit/ | Money-Psychology6769 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkm44c | false | null | t3_1nkm44c | /r/LocalLLaMA/comments/1nkm44c/could_small_language_models_slms_be_a_better_fit/ | false | false | self | 4 | null |
Local real-time assistant that remembers convo + drafts a doc | 12 | I wired up a local “brainstorming assistant” that keeps memory of our chat and then writes a Google doc based on what we talked about.
Demo was simple:
1. Talked with it about cats.
2. Asked it to generate a doc with what we discussed.
Results: it dropped a few details, but it captured the main points surprisingly w... | 2025-09-18T21:56:53 | https://v.redd.it/g7qj66kitzpf1 | Weary-Wing-6806 | /r/LocalLLaMA/comments/1nklnqi/local_realtime_assistant_that_remembers_convo/ | 1970-01-01T00:00:00 | 0 | {} | 1nklnqi | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/g7qj66kitzpf1/DASHPlaylist.mpd?a=1760954218%2CYWFjMGVkZjk4NjU1MmE5NzJiNWRjM2RjM2NhNTliYWZkZGNjYTdlMDIxNTM2MzJiMjM2ZDQ5OGNkNWI3NTI0Yw%3D%3D&v=1&f=sd', 'duration': 108, 'fallback_url': 'https://v.redd.it/g7qj66kitzpf1/DASH_720.mp4?source=fallback', 'h... | t3_1nklnqi | /r/LocalLLaMA/comments/1nklnqi/local_realtime_assistant_that_remembers_convo/ | false | false | 12 | {'enabled': False, 'images': [{'id': 'cDVmYTE2a2l0enBmMX1sjDttlx_mQ45DeDKL-DubvjOdCDAQ-7LC5FNwPoBD', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/cDVmYTE2a2l0enBmMX1sjDttlx_mQ45DeDKL-DubvjOdCDAQ-7LC5FNwPoBD.png?width=108&crop=smart&format=pjpg&auto=webp&s=ca33bf8405b3dc5bd404f2c8928d940835ccd... | |
How can I control emotions/tone in Higgs Audio — can I make it be sad at the start and happy at the end? | 0 | Hey everyone — quick question about Higgs Audio: is it possible to control emotions within a single input (for example: sad at the start, neutral in the middle, then happy at the end)? If yes, how do you do it in practice? Can you guys give a example? And if this is not possible with higgs then are there any moddels th... | 2025-09-18T21:22:22 | https://www.reddit.com/r/LocalLLaMA/comments/1nkksml/how_can_i_control_emotionstone_in_higgs_audio_can/ | Adept_Lawyer_4592 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkksml | false | null | t3_1nkksml | /r/LocalLLaMA/comments/1nkksml/how_can_i_control_emotionstone_in_higgs_audio_can/ | false | false | self | 0 | null |
Decart-AI releases “Open Source Nano Banana for Video” | 138 | We are building “Open Source Nano Banana for Video” - here is open source demo v0.1
We are open sourcing Lucy Edit, the first foundation model for text-guided video editing!
Lucy Edit lets you prompt to try on uniforms or costumes - with motion, face, and identity staying perfectly preserved
Get the model on @huggin... | 2025-09-18T21:09:20 | ResearchCrafty1804 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkkghp | false | null | t3_1nkkghp | /r/LocalLLaMA/comments/1nkkghp/decartai_releases_open_source_nano_banana_for/ | false | false | 138 | {'enabled': True, 'images': [{'id': '5Ufq-8-sVIe9gs2Ea19Xt0BvSMm2DG5sKDXfqYeq2vs', 'resolutions': [{'height': 143, 'url': 'https://preview.redd.it/eisyod0snzpf1.jpeg?width=108&crop=smart&auto=webp&s=448ae3bf251dad89bc99f1e9fc18517ab4c3fc23', 'width': 108}, {'height': 287, 'url': 'https://preview.redd.it/eisyod0snzpf1.j... | ||
What are the best current text "humanization" methods/models? | 1 | I've been loosely following the evolution of AI-detection methods, along with the various subsequent websites that have emerged offering it as a service. From what I can tell, the main methods are:
1. Token-rank and entropy signals (histogram of top-k ranks, perplexity);
2. Curvature of log-probability (https://arxiv.... | 2025-09-18T20:59:25 | https://www.reddit.com/r/LocalLLaMA/comments/1nkk79t/what_are_the_best_current_text_humanization/ | louis-debroglie | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkk79t | false | null | t3_1nkk79t | /r/LocalLLaMA/comments/1nkk79t/what_are_the_best_current_text_humanization/ | false | false | self | 1 | null |
I built APM – a package manager for agent workflows and context (works with local LLaMA too) | 6 | I’ve been hacking on a side project I’m calling **APM (Agent Package Manager)**. The idea is simple: treat agent prompts + workflows like code packages you can version, share, and reuse.
My pain point was always the same:
– I’d write complex prompt/rule files, but couldn’t easily reuse them in another project.
– T... | 2025-09-18T20:57:53 | https://www.reddit.com/r/LocalLLaMA/comments/1nkk5tv/i_built_apm_a_package_manager_for_agent_workflows/ | Amazing_Midnight_813 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkk5tv | false | null | t3_1nkk5tv | /r/LocalLLaMA/comments/1nkk5tv/i_built_apm_a_package_manager_for_agent_workflows/ | false | false | self | 6 | {'enabled': False, 'images': [{'id': 'xguMc4QbyVyC-YFGUkERRZvoqyunAzwGK5aWn9RbY0o', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/xguMc4QbyVyC-YFGUkERRZvoqyunAzwGK5aWn9RbY0o.png?width=108&crop=smart&auto=webp&s=b76222e3b45de8b4f25c07d01cbfb93ec498b01a', 'width': 108}, {'height': 108, 'url': 'h... |
Model: Qwen3 Next Pull Request llama.cpp | 183 | 2025-09-18T20:40:40 | https://www.reddit.com/r/LocalLLaMA/comments/1nkjpu3/model_qwen3_next_pull_request_llamacpp/ | Loskas2025 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkjpu3 | false | null | t3_1nkjpu3 | /r/LocalLLaMA/comments/1nkjpu3/model_qwen3_next_pull_request_llamacpp/ | false | false | 183 | null | ||
Local LLM in Github Copilot, Agent mode | 4 | I am pretty new to this whole Local LLM world, Thought id give it a bash with ollama, Got it all up and running in Docker on Ubuntu 25.04 with a 4070ti
Ive nipped into VSCode github copilot extension, Selected the models, Gone into agent mode and I can get the models to respond (mostly) but none of them seem to be abl... | 2025-09-18T20:39:49 | https://www.reddit.com/r/LocalLLaMA/comments/1nkjp1y/local_llm_in_github_copilot_agent_mode/ | SuspiciousParsnip5 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkjp1y | false | null | t3_1nkjp1y | /r/LocalLLaMA/comments/1nkjp1y/local_llm_in_github_copilot_agent_mode/ | false | false | 4 | null | |
With Meta's Fail, I wanted to test a couple 4Bs | 0 | Throwaway because I'm a lurker, not a poster.... but I thought this was interesting...
First I took a screenshot of the man asking for the AI questions, and I asked Gemma-3-4B what it saw:
Okay, let's break down this image in as much detail as possible. Here’s a comprehensive analysis, focusing on what I observe:... | 2025-09-18T20:29:34 | https://www.reddit.com/r/LocalLLaMA/comments/1nkjfiq/with_metas_fail_i_wanted_to_test_a_couple_4bs/ | Single_Power4777 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkjfiq | false | null | t3_1nkjfiq | /r/LocalLLaMA/comments/1nkjfiq/with_metas_fail_i_wanted_to_test_a_couple_4bs/ | false | false | self | 0 | null |
Want to split a big model among two 5090's - what's my best case for single query response speed improvement? | 2 | So.. i have a single 5090 here and i'm looking to buy another. I also need to get another motherboard in the process.
What i'm trying to figure out is..
When splitting a model between two GPUs ( GLM 4.5 air in this case ), what is the best case speedup, in terms of tokens/sec, either literally or a percentage... | 2025-09-18T20:18:16 | https://www.reddit.com/r/LocalLLaMA/comments/1nkj4wo/want_to_split_a_big_model_among_two_5090s_whats/ | mr_zerolith | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkj4wo | false | null | t3_1nkj4wo | /r/LocalLLaMA/comments/1nkj4wo/want_to_split_a_big_model_among_two_5090s_whats/ | false | false | self | 2 | null |
New stealth model Golden Capybara? | 12 | 2025-09-18T19:52:29 | https://www.reddit.com/r/LocalLLaMA/comments/1nkigg6/new_stealth_model_golden_capybara/ | Adept_Photograph_796 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkigg6 | false | null | t3_1nkigg6 | /r/LocalLLaMA/comments/1nkigg6/new_stealth_model_golden_capybara/ | false | false | 12 | null | ||
PSA it costs authors $12,690 to make a Nature article Open Access | 648 | And the DeepSeek folks paid up so we can read their work without hitting a paywall. Massive respect for absorbing the costs so the public benefits. | 2025-09-18T19:50:42 | entsnack | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkieo3 | false | null | t3_1nkieo3 | /r/LocalLLaMA/comments/1nkieo3/psa_it_costs_authors_12690_to_make_a_nature/ | false | false | default | 648 | {'enabled': True, 'images': [{'id': 'xkcal9zq9zpf1', 'resolutions': [{'height': 93, 'url': 'https://preview.redd.it/xkcal9zq9zpf1.jpeg?width=108&crop=smart&auto=webp&s=c1a5f51b1b9633285101e029621c74f1a8ea04de', 'width': 108}, {'height': 186, 'url': 'https://preview.redd.it/xkcal9zq9zpf1.jpeg?width=216&crop=smart&auto=w... | |
gpt-oss-20b TTFT very slow with llama.cpp? | 5 | Hey friends,
I'm running llama.cpp with llama-swap, and getting really poor performance with gsp-oss-20b on dual RTX 3060s with tensor split. I'm trying to switch over from ollama (for obvious reasons), but I'm finding that TTFT gets longer and longer as context grows, sometimes waiting 30 seconds to even minutes befo... | 2025-09-18T19:46:30 | https://www.reddit.com/r/LocalLLaMA/comments/1nkiaov/gptoss20b_ttft_very_slow_with_llamacpp/ | No_Information9314 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkiaov | false | null | t3_1nkiaov | /r/LocalLLaMA/comments/1nkiaov/gptoss20b_ttft_very_slow_with_llamacpp/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'VDsaRKB6MF1zC72W3rEBeZYiTeSy-Leo3mzF4pSf7-0', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/VDsaRKB6MF1zC72W3rEBeZYiTeSy-Leo3mzF4pSf7-0.png?width=108&crop=smart&auto=webp&s=f6dc2e77da193dc9923ee611963dc30f62c22e3e', 'width': 108}, {'height': 108, 'url': 'h... |
Problem with glm air in LMStudio | 5 |
Hi. I have tried to get glm 4.5 air to work with opencode. Works great when I use it via openrouter, but when I run same model locally (LMStudio) all tool call fails. Have tried different quants, but so far nothing works.
Anyone who have a clue? Would really appreciate suggestions.
| 2025-09-18T19:21:33 | Magnus114 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkhn3t | false | null | t3_1nkhn3t | /r/LocalLLaMA/comments/1nkhn3t/problem_with_glm_air_in_lmstudio/ | false | false | default | 5 | {'enabled': True, 'images': [{'id': 'xvt021tj4zpf1', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/xvt021tj4zpf1.jpeg?width=108&crop=smart&auto=webp&s=94b965f12dfed39ac6cd79d26e2a4a7789059ad0', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/xvt021tj4zpf1.jpeg?width=216&crop=smart&auto=w... | |
Can you guess what model you're talking to in 5 prompts? | 52 | I made a [web version](whichllama.com) of the WhichLlama? bot in our Discord server (you should join!) to share here. I think my own "LLM palate" isn't refined enough to tell models apart (drawing an analogy to coffee and wine tasting). | 2025-09-18T19:05:38 | https://v.redd.it/y7dajeso1zpf1 | entsnack | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkh88k | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/y7dajeso1zpf1/DASHPlaylist.mpd?a=1760814352%2CMWYzYzhhMDJhYjBhMDk2MTM4ZTZjYWIyMTBiZGYyYzZhZmE4NmNkMjkzYzkyYzg2YzQ0ODQyZWNjY2JiZGRlMA%3D%3D&v=1&f=sd', 'duration': 42, 'fallback_url': 'https://v.redd.it/y7dajeso1zpf1/DASH_480.mp4?source=fallback', 'ha... | t3_1nkh88k | /r/LocalLLaMA/comments/1nkh88k/can_you_guess_what_model_youre_talking_to_in_5/ | false | false | 52 | {'enabled': False, 'images': [{'id': 'NTh4aG80cW8xenBmMfQ6ULqGkcZNtZeiwHOodBaY1uWCovO-Ocod72xeRKh_', 'resolutions': [{'height': 78, 'url': 'https://external-preview.redd.it/NTh4aG80cW8xenBmMfQ6ULqGkcZNtZeiwHOodBaY1uWCovO-Ocod72xeRKh_.png?width=108&crop=smart&format=pjpg&auto=webp&s=b06676b1b14b3a38abd0a0c10466aa243480f... | |
Problem with glm air in LMStudio | 1 | Hi. I have tried to get glm 4.5 air to work with opencode. Works great when I use it via openrouter, but when I run same model locally (LMStudio) all tool call fails. Have tried different quants, but so far nothing works.
Anyone who have a clue? Would really appreciate suggestions.
| 2025-09-18T19:00:59 | Magnus114 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkh3qv | false | null | t3_1nkh3qv | /r/LocalLLaMA/comments/1nkh3qv/problem_with_glm_air_in_lmstudio/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'vrksb8pv0zpf1', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/vrksb8pv0zpf1.jpeg?width=108&crop=smart&auto=webp&s=e113d608d23348dd35fbe2eb95cad402a8e58f10', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/vrksb8pv0zpf1.jpeg?width=216&crop=smart&auto=w... | |
Beginner Question: How do I use quantised VisionLLMs available on Hugging Face? | 3 | I want to run the VLLM on Jetson Orin Nano (8GBs RAM) and so I've been looking for quantized VLLMs. But, when I tried to run
"EZCon/Qwen2-VL-2B-Instruct-abliterated-4bit-mlx" on PyTorch
It gave me this error: The model's quantization config from the arguments has no \`quant\_method\` attribute. Make sure that the ... | 2025-09-18T18:52:02 | https://www.reddit.com/r/LocalLLaMA/comments/1nkgvcb/beginner_question_how_do_i_use_quantised/ | dead_shroom | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkgvcb | false | null | t3_1nkgvcb | /r/LocalLLaMA/comments/1nkgvcb/beginner_question_how_do_i_use_quantised/ | false | false | self | 3 | {'enabled': False, 'images': [{'id': 'flDa7d4uxAqmQLZxAO_rdAJNBdbzF-nMCH8sZ7QYVJI', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/flDa7d4uxAqmQLZxAO_rdAJNBdbzF-nMCH8sZ7QYVJI.png?width=108&crop=smart&auto=webp&s=d7e6b660624062e5513c36bd831f94637032b3b3', 'width': 108}, {'height': 116, 'url': 'h... |
RX 7700 launched with 2560 cores (relatively few) and 16GB memory with 624 GB/s bandwidth (relatively high) | 26 | This seems like an LLM GPU. Lot’s of bandwidth compared to compute.
See https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7700.html for the full specs | 2025-09-18T18:37:07 | https://videocardz.com/newz/amd-launches-radeon-rx-7700-with-2560-cores-and-16gb-memory | Balance- | videocardz.com | 1970-01-01T00:00:00 | 0 | {} | 1nkgh1u | false | null | t3_1nkgh1u | /r/LocalLLaMA/comments/1nkgh1u/rx_7700_launched_with_2560_cores_relatively_few/ | false | false | default | 26 | {'enabled': False, 'images': [{'id': 'ZtmeYdNQChVt_XKulmUOe_WPIvyPIS1JhHlC4A0Lp38', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/ZtmeYdNQChVt_XKulmUOe_WPIvyPIS1JhHlC4A0Lp38.jpeg?width=108&crop=smart&auto=webp&s=2f266b69025a9d4f631bd6e151d37dbe9b6bed83', 'width': 108}, {'height': 112, 'url': '... |
Local LLM Coding Stack (24GB minimum, ideal 36GB) | 323 | Perhaps this could be useful to someone trying to get his/her own local AI coding stack. I do scientific coding stuff, not web or application development related stuff, so the needs might be different.
Deployed on a 48gb Mac, but this should work on 32GB, and maybe even 24GB setups:
General Tasks, used 90% of the... | 2025-09-18T18:14:56 | JLeonsarmiento | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkfvrl | false | null | t3_1nkfvrl | /r/LocalLLaMA/comments/1nkfvrl/local_llm_coding_stack_24gb_minimum_ideal_36gb/ | false | false | default | 323 | {'enabled': True, 'images': [{'id': 'ia5muohupypf1', 'resolutions': [{'height': 70, 'url': 'https://preview.redd.it/ia5muohupypf1.png?width=108&crop=smart&auto=webp&s=843fd78c870da3099d1531a990d26820a222a1af', 'width': 108}, {'height': 140, 'url': 'https://preview.redd.it/ia5muohupypf1.png?width=216&crop=smart&auto=web... | |
AMA with the LM Studio team | 178 | Hello r/LocalLLaMA! We're excited for this AMA. Thank you for having us here today. We got a full house from the LM Studio team:
\- Yags [https://reddit.com/user/yags-lms/](https://t.co/ERfA4NrR96) (founder)
\- Neil [https://reddit.com/user/neilmehta24/](https://t.co/KyiHVfv0QG) (LLM engines and runtime)
\- Wi... | 2025-09-18T18:12:24 | https://www.reddit.com/r/LocalLLaMA/comments/1nkft9l/ama_with_the_lm_studio_team/ | yags-lms | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkft9l | false | null | t3_1nkft9l | /r/LocalLLaMA/comments/1nkft9l/ama_with_the_lm_studio_team/ | false | true | self | 178 | null |
ꓚоսꓲd ꓲосаꓲ ꓡꓡꓟѕ bесоmе tһе rеаꓲ аꓲꓲ-іո-оոе аꓲtеrոаtіνе tо сꓲоսd ꓮꓲ? | 0 | ꓲ’νе bееո ехреrіmеոtіոց ԝіtһ dіffеrеոt ꓲосаꓲ ѕеtսрѕ fоr ꓡꓡаꓟꓮ-bаѕеd mоdеꓲѕ, аոd іt ցоt mе tһіոkіոց, аrе ԝе mоνіոց сꓲоѕеr tо а fսtսrе ԝһеrе ꓲосаꓲ ꓡꓡꓟѕ саո ѕеrνе аѕ а trսе аꓲꓲ-іո-оոе һսb?
ꓣіցһt ոоԝ, реорꓲе tеոd tо mіх аոd mаtсһ: оոе tооꓲ fоr ոоtе-tаkіոց, аոоtһеr fоr аսtоmаtіоո, аոоtһеr fоr сһаt, еtс. ꓐսt іf ꓲосаꓲ ꓡꓡꓟѕ... | 2025-09-18T17:40:54 | https://www.reddit.com/r/LocalLLaMA/comments/1nkeykh/ꓚоսꓲd_ꓲосаꓲ_ꓡꓡꓟѕ_bесоmе_tһе_rеаꓲ_аꓲꓲіոоոе/ | Objective-Box7188 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkeykh | false | null | t3_1nkeykh | /r/LocalLLaMA/comments/1nkeykh/ꓚоսꓲd_ꓲосаꓲ_ꓡꓡꓟѕ_bесоmе_tһе_rеаꓲ_аꓲꓲіոоոе/ | false | false | self | 0 | null |
DnD AI DM : Stable SillyTavern + Vicuna 13B setup for lore-heavy D&D (RTX 3070 / 8GB VRAM) | 1 | [removed] | 2025-09-18T17:35:31 | https://www.reddit.com/r/LocalLLaMA/comments/1nketbi/dnd_ai_dm_stable_sillytavern_vicuna_13b_setup_for/ | Additional_Ad2545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nketbi | false | null | t3_1nketbi | /r/LocalLLaMA/comments/1nketbi/dnd_ai_dm_stable_sillytavern_vicuna_13b_setup_for/ | false | false | self | 1 | null |
[Guide] Stable SillyTavern + Vicuna 13B setup for lore-heavy D&D (RTX 3070 / 8GB VRAM) | 1 | [removed] | 2025-09-18T17:34:03 | https://www.reddit.com/r/LocalLLaMA/comments/1nkes06/guide_stable_sillytavern_vicuna_13b_setup_for/ | Additional_Ad2545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkes06 | false | null | t3_1nkes06 | /r/LocalLLaMA/comments/1nkes06/guide_stable_sillytavern_vicuna_13b_setup_for/ | false | false | self | 1 | null |
DnD AI DM: Stable SillyTavern + Vicuna 13B Setup for Lore-Heavy D&D (RTX 3070/8GB VRAM) | 1 | [removed] | 2025-09-18T17:30:37 | https://www.reddit.com/r/LocalLLaMA/comments/1nkeoqg/dnd_ai_dm_stable_sillytavern_vicuna_13b_setup_for/ | Additional_Ad2545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkeoqg | false | null | t3_1nkeoqg | /r/LocalLLaMA/comments/1nkeoqg/dnd_ai_dm_stable_sillytavern_vicuna_13b_setup_for/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'JXD7apj8aB4GZzBm_M46ukkHvkv5ubcKkAZboniqkrY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/JXD7apj8aB4GZzBm_M46ukkHvkv5ubcKkAZboniqkrY.png?width=108&crop=smart&auto=webp&s=50459b106c03fc3b98949b8b4c193cb05d80eada', 'width': 108}, {'height': 108, 'url': 'h... |
Can I run local opensource models like Wan2.1, Hunyuan Video, CogVideoX & Chatterbox on a RTX 3060 build? | 1 | [removed] | 2025-09-18T17:30:21 | https://www.reddit.com/r/LocalLLaMA/comments/1nkeogq/can_i_run_local_opensource_models_like_wan21/ | Educational-Bite325 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkeogq | false | null | t3_1nkeogq | /r/LocalLLaMA/comments/1nkeogq/can_i_run_local_opensource_models_like_wan21/ | false | false | self | 1 | null |
DnD AI DM, lore-heavy. [Guide] Stable SillyTavern + Vicuna 13B Setup for Lore-Heavy D&D (RTX 3070/8GB VRAM) | 1 | [removed] | 2025-09-18T17:11:47 | https://www.reddit.com/r/LocalLLaMA/comments/1nke6o0/dnd_ai_dm_loreheavy_guide_stable_sillytavern/ | Additional_Ad2545 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nke6o0 | false | null | t3_1nke6o0 | /r/LocalLLaMA/comments/1nke6o0/dnd_ai_dm_loreheavy_guide_stable_sillytavern/ | false | false | self | 1 | null |
Can someone explain | 0 | I am lost and looking for resources are making me more lost. What do these terms mean
1. Safetensors
2. GGUF
3. Instruct
4. MoE - I know it is mixture of experts but how is it different
And more are there | 2025-09-18T17:04:52 | https://www.reddit.com/r/LocalLLaMA/comments/1nkdzu0/can_someone_explain/ | r00tdr1v3 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkdzu0 | false | null | t3_1nkdzu0 | /r/LocalLLaMA/comments/1nkdzu0/can_someone_explain/ | false | false | self | 0 | null |
How to locally test ICPC 2025 World Finals questions with open-source models. | 1 | The questions put to all these teams and their hardware and programs at this event that just concluded in Baku - where all the big models get ranked in performance - are available online in PDF format exactly as presented in competition.
Now I can solve all of them in my head mind you, but just for giggles, how would ... | 2025-09-18T16:59:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nkdu8u/how_to_locally_test_icpc_2025_world_finals/ | PaulDallas72 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkdu8u | false | null | t3_1nkdu8u | /r/LocalLLaMA/comments/1nkdu8u/how_to_locally_test_icpc_2025_world_finals/ | false | false | self | 1 | null |
A dialogue where god tries (and fails) to prove to satan that humans can reason | 77 | [Full article here](https://www.astralcodexten.com/p/what-is-man-that-thou-art-mindful). | 2025-09-18T16:52:06 | FinnFarrow | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkdnf2 | false | null | t3_1nkdnf2 | /r/LocalLLaMA/comments/1nkdnf2/a_dialogue_where_god_tries_and_fails_to_prove_to/ | false | false | default | 77 | {'enabled': True, 'images': [{'id': 'fqm6nmw8dypf1', 'resolutions': [{'height': 150, 'url': 'https://preview.redd.it/fqm6nmw8dypf1.png?width=108&crop=smart&auto=webp&s=c9132c2b2434b185bf9747080b6a5329e2213db1', 'width': 108}, {'height': 300, 'url': 'https://preview.redd.it/fqm6nmw8dypf1.png?width=216&crop=smart&auto=we... | |
Vibevoice Comfy Distributed? | 1 | Could vibevoice be run on across distributed GPUs in ComfyUI? Any ideas if this is possible? | 2025-09-18T16:31:37 | https://www.reddit.com/r/LocalLLaMA/comments/1nkd3fa/vibevoice_comfy_distributed/ | Eastern_Rock7947 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkd3fa | false | null | t3_1nkd3fa | /r/LocalLLaMA/comments/1nkd3fa/vibevoice_comfy_distributed/ | false | false | self | 1 | null |
Running Nvidia CUDA Pytorch/vLLM projects and pipelines on AMD with no modifications | 2 | Hi, I wanted to share some information on this cool feature we built in WoolyAI GPU hypervisor, which enables users to run their existing Nvidia CUDA pytorch/vLLM projects and pipelines without any modifications on AMD GPUs. ML researchers can transparently consume GPUs from a heterogeneous cluster of Nvidia and AMD GP... | 2025-09-18T16:25:38 | https://www.reddit.com/r/LocalLLaMA/comments/1nkcxlj/running_nvidia_cuda_pytorchvllm_projects_and/ | Chachachaudhary123 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkcxlj | false | null | t3_1nkcxlj | /r/LocalLLaMA/comments/1nkcxlj/running_nvidia_cuda_pytorchvllm_projects_and/ | false | false | self | 2 | {'enabled': False, 'images': [{'id': 'vbTKGbEN-i6KoDED_b9j5Og-2ZY5W-amfiS9hRDeZjE', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/vbTKGbEN-i6KoDED_b9j5Og-2ZY5W-amfiS9hRDeZjE.jpeg?width=108&crop=smart&auto=webp&s=51e56875612b1cac16959f9d217b5fbceed6b736', 'width': 108}, {'height': 162, 'url': '... |
how do i best use my hardware | 0 | Hi folks:
I have been hosting LLM's on my hardware a bit (taking a break right now from all ai -- personal reasons, dont ask), but eventually i'll be getting back into it. I have a Ryzen 9 9950x with 64gb of ddr5 memory, about 12 tb of drive space, and a 3060 (12gb) GPU -- it works great, but, unfortunately, the gpu ... | 2025-09-18T16:12:36 | https://www.reddit.com/r/LocalLLaMA/comments/1nkckw6/how_do_i_best_use_my_hardware/ | slrg1968 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkckw6 | false | null | t3_1nkckw6 | /r/LocalLLaMA/comments/1nkckw6/how_do_i_best_use_my_hardware/ | false | false | self | 0 | null |
GLM 4.5 Air - Jinja Template Modification (Based on Unsloth's) - No thinking by default - straight quick answers, need thinking? simple activation with "/think" command anywhere in the system prompt. | 58 | 2025-09-18T16:03:16 | https://www.reddit.com/gallery/1nkcbwp | -Ellary- | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nkcbwp | false | null | t3_1nkcbwp | /r/LocalLLaMA/comments/1nkcbwp/glm_45_air_jinja_template_modification_based_on/ | false | false | 58 | null | ||
I open-sourced a text2SQL RAG for all your databases and local models | 21 | Hey r/LocalLLama 👋
I’ve spent most of my career working with databases, and one thing that’s always bugged me is how hard it is for AI agents to work with them. Whenever I ask Claude, GPT, or Llama about my data, it either invents schemas or hallucinates details. To fix that, I built [ToolFront](https://docs.toolfro... | 2025-09-18T16:02:36 | Durovilla | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nkcb7n | false | null | t3_1nkcb7n | /r/LocalLLaMA/comments/1nkcb7n/i_opensourced_a_text2sql_rag_for_all_your/ | false | false | default | 21 | {'enabled': True, 'images': [{'id': 'kolx2nwb3ypf1', 'resolutions': [{'height': 35, 'url': 'https://preview.redd.it/kolx2nwb3ypf1.png?width=108&crop=smart&auto=webp&s=149df8c389bf0e27509937c2677254f7f2720af9', 'width': 108}, {'height': 71, 'url': 'https://preview.redd.it/kolx2nwb3ypf1.png?width=216&crop=smart&auto=webp... | |
Qwen3 Next - Behind the Curtain | 7 | 2025-09-18T15:59:55 | https://www.youtube.com/watch?v=DfPKk-8fOGA | Confident-Honeydew66 | youtube.com | 1970-01-01T00:00:00 | 0 | {} | 1nkc8gm | false | {'oembed': {'author_name': 'Sam Witteveen', 'author_url': 'https://www.youtube.com/@samwitteveenai', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/DfPKk-8fOGA?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyr... | t3_1nkc8gm | /r/LocalLLaMA/comments/1nkc8gm/qwen3_next_behind_the_curtain/ | false | false | default | 7 | {'enabled': False, 'images': [{'id': 'atPe_ZcLh-b1MmmRXwqyrOtH9cMsKeTF2v_fDKIB1JE', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/atPe_ZcLh-b1MmmRXwqyrOtH9cMsKeTF2v_fDKIB1JE.jpeg?width=108&crop=smart&auto=webp&s=4e9a85451b145d09453eb66848e9c1cc81accfaa', 'width': 108}, {'height': 162, 'url': '... | |
How are you using computer-use agents? | 7 | I'm trying to understand how people are using computer-use agents in practice. If you are using computer-use agents today, what's your use-case?
To clarify, I'm not looking for folks building these agents. I'd love to hear from you if you are / know of individuals, teams, or companies actually using them in their work... | 2025-09-18T15:58:15 | https://www.reddit.com/r/LocalLLaMA/comments/1nkc6tx/how_are_you_using_computeruse_agents/ | New-Strain-7472 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkc6tx | false | null | t3_1nkc6tx | /r/LocalLLaMA/comments/1nkc6tx/how_are_you_using_computeruse_agents/ | false | false | self | 7 | null |
The one who knows how 2 5090 on same server can run vLLM in tp 2 | 0 | The one who knows how 2x 5090 on same server can run vLLM in tensor parallel 2, I will transfer 100 euro worth of coins.
Currently my 2x AMD 7900 XTX can do that, they run fine vLLM in tensor parallel 2,
but latest Nvidia cards cant :)
How come the tables have turned. So currently Nvidia sucks, and AMD just w... | 2025-09-18T15:53:54 | https://www.reddit.com/r/LocalLLaMA/comments/1nkc2o6/the_one_who_knows_how_2_5090_on_same_server_can/ | somealusta | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkc2o6 | false | null | t3_1nkc2o6 | /r/LocalLLaMA/comments/1nkc2o6/the_one_who_knows_how_2_5090_on_same_server_can/ | false | false | self | 0 | null |
Using gpt-oss:120b with Ollama on a Ryzen Max 395+ via Continue.dev | 5 | I have a Bosgame M5 AI Mini PC running Ubuntu 24.04. On said machine, I have Ollama 0.11.11. I have the memory configured with 96GB dedicated for GPU with the remaining 32GB for system use. Using gpt-oss:120b via Open Web UI works without issue from a browser. In fact, it is quite responsive. In trying to get the ... | 2025-09-18T15:48:13 | https://www.reddit.com/r/LocalLLaMA/comments/1nkbx6w/using_gptoss120b_with_ollama_on_a_ryzen_max_395/ | tinycomputing | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkbx6w | false | null | t3_1nkbx6w | /r/LocalLLaMA/comments/1nkbx6w/using_gptoss120b_with_ollama_on_a_ryzen_max_395/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': '7FTmwKM4TuCvaIMSlask76mRn8liFawdPuHJFSqPl9U', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/7FTmwKM4TuCvaIMSlask76mRn8liFawdPuHJFSqPl9U.png?width=108&crop=smart&auto=webp&s=efe307f51ff2874b18960bc89ca5a18a1b551442', 'width': 108}, {'height': 113, 'url': 'h... |
Good mining frame for server motherboards and large GPUs? | 2 | I am putting together a system with an SSI-EEB board as well as chonky 4090s that are 360mm in length.
Most mining frames are targeted for bitcoin mining with ATX motherboards and a bunch of smaller GPUs and they don't necessarily support the SSI-EEB screw pattern or GPUs that long.
I'm open to other ideas too, but ... | 2025-09-18T15:44:25 | https://www.reddit.com/r/LocalLLaMA/comments/1nkbthf/good_mining_frame_for_server_motherboards_and/ | abnormal_human | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkbthf | false | null | t3_1nkbthf | /r/LocalLLaMA/comments/1nkbthf/good_mining_frame_for_server_motherboards_and/ | false | false | self | 2 | null |
Local Suno just dropped | 474 | [https://huggingface.co/fredconex/SongBloom-Safetensors](https://huggingface.co/fredconex/SongBloom-Safetensors)
[https://github.com/fredconex/ComfyUI-SongBloom](https://github.com/fredconex/ComfyUI-SongBloom)
Examples:
[https://files.catbox.moe/i0iple.flac](https://files.catbox.moe/i0iple.flac)
[https://files.ca... | 2025-09-18T15:42:25 | https://www.reddit.com/r/LocalLLaMA/comments/1nkbrk1/local_suno_just_dropped/ | Different_Fix_2217 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkbrk1 | false | null | t3_1nkbrk1 | /r/LocalLLaMA/comments/1nkbrk1/local_suno_just_dropped/ | false | false | self | 474 | {'enabled': False, 'images': [{'id': '0madv9n-jRmSA4yqmlaooVPTBKjVWGBP05OrZ3jpZho', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/0madv9n-jRmSA4yqmlaooVPTBKjVWGBP05OrZ3jpZho.png?width=108&crop=smart&auto=webp&s=898f505c9bcb7b44da27d0dfa4696d360b00d8f0', 'width': 108}, {'height': 116, 'url': 'h... |
Anyone here tried NVIDIA’s LLM-optimized VM setups for faster workflows? | 1 | Lately I’ve been looking into ways to speed up LLM workflows (training, inference, prototyping) without spending hours setting up CUDA, PyTorch, and all the dependencies manually.
From what I see, there are preconfigured GPU-accelerated VM images out there that already bundle the common libraries (PyTorch, TensorFlow,... | 2025-09-18T15:30:07 | https://www.reddit.com/r/LocalLLaMA/comments/1nkbfp5/anyone_here_tried_nvidias_llmoptimized_vm_setups/ | techlatest_net | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nkbfp5 | false | null | t3_1nkbfp5 | /r/LocalLLaMA/comments/1nkbfp5/anyone_here_tried_nvidias_llmoptimized_vm_setups/ | false | false | self | 1 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.