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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
How to disable deep thinking in continue dev with ollama | 2 | Hey everyone!
I am using Ollama with qwen3:4b and continue dev on vs code.
The problem is takes a lot of time. it like goes deep thinking mode by default, just for a simple "hello" it took around 2 min to respond to me, how can i disable this. | 2025-09-10T14:28:23 | Any_Pen2269 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ndfqh5 | false | null | t3_1ndfqh5 | /r/LocalLLaMA/comments/1ndfqh5/how_to_disable_deep_thinking_in_continue_dev_with/ | false | false | default | 2 | {'enabled': True, 'images': [{'id': '7902v0pwkcof1', 'resolutions': [{'height': 58, 'url': 'https://preview.redd.it/7902v0pwkcof1.png?width=108&crop=smart&auto=webp&s=7550eb537159cdc7a4a6f63a75f407daa3d0664e', 'width': 108}, {'height': 117, 'url': 'https://preview.redd.it/7902v0pwkcof1.png?width=216&crop=smart&auto=web... | |
Qwen3-VL soon? | 60 | 2025-09-10T14:23:47 | https://github.com/huggingface/transformers/pull/40795 | jacek2023 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1ndfmb0 | false | null | t3_1ndfmb0 | /r/LocalLLaMA/comments/1ndfmb0/qwen3vl_soon/ | false | false | default | 60 | {'enabled': False, 'images': [{'id': 'WmIZZLYdo41uN4s96YqW_5HlL8MG-0LtKmnFoOx7RwY', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/WmIZZLYdo41uN4s96YqW_5HlL8MG-0LtKmnFoOx7RwY.png?width=108&crop=smart&auto=webp&s=e4be73fbdd444f7c3bd69271de3a5adc25389ffa', 'width': 108}, {'height': 108, 'url': 'h... | |
Seedream 4.0 is better than google nanobanana. It's a shame Bytedance, a Chinese company, is acting like a big American capitalist corporation. Also make their API so restrictive. Let's see what Hunyuan Image 2.1 has to offer. | 0 | 2025-09-10T14:23:43 | balianone | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ndfm8y | false | null | t3_1ndfm8y | /r/LocalLLaMA/comments/1ndfm8y/seedream_40_is_better_than_google_nanobanana_its/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': '73o8p3v2kcof1', 'resolutions': [{'height': 108, 'url': 'https://preview.redd.it/73o8p3v2kcof1.jpeg?width=108&crop=smart&auto=webp&s=eadfd387fc30563fc168256af9c123b57509835d', 'width': 108}, {'height': 216, 'url': 'https://preview.redd.it/73o8p3v2kcof1.jpeg?width=216&crop=smart&auto=... | ||
Qwen 3 Cline alternative. | 1 | I'm using the Qwen 3 AI tool within cline. Qwen 3 is really good, but cline is so bad that I can use Qwen 3. Does anyone know of a cline alternative? | 2025-09-10T14:14:22 | https://www.reddit.com/r/LocalLLaMA/comments/1ndfdh3/qwen_3_cline_alternative/ | Majestic_Republic147 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndfdh3 | false | null | t3_1ndfdh3 | /r/LocalLLaMA/comments/1ndfdh3/qwen_3_cline_alternative/ | false | false | self | 1 | null |
I love Gemini 2.5 Pro | 40 | 2025-09-10T14:13:54 | https://www.reddit.com/gallery/1ndfd0o | beeenbeeen | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ndfd0o | false | null | t3_1ndfd0o | /r/LocalLLaMA/comments/1ndfd0o/i_love_gemini_25_pro/ | false | false | 40 | null | ||
I built a fully automated LLM tournament system (62 models tested, 18 qualified, 50 tournaments run) | 64 | I’ve been working on a project called Valyrian Games: a fully automated system where Large Language Models compete against each other in coding challenges. After running 50 tournaments, I’ve published the first results here:
👉 Leaderboard: [https://valyriantech.github.io/ValyrianGamesLeaderboard](https://valyriantech... | 2025-09-10T14:04:09 | WouterGlorieux | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ndf3rj | false | null | t3_1ndf3rj | /r/LocalLLaMA/comments/1ndf3rj/i_built_a_fully_automated_llm_tournament_system/ | false | false | default | 64 | {'enabled': True, 'images': [{'id': '7yajbqkmd6of1', 'resolutions': [{'height': 151, 'url': 'https://preview.redd.it/7yajbqkmd6of1.png?width=108&crop=smart&auto=webp&s=f5318cf6cd3d08c2987e47427b28f9b8e77b8dc5', 'width': 108}, {'height': 302, 'url': 'https://preview.redd.it/7yajbqkmd6of1.png?width=216&crop=smart&auto=we... | |
What are your experiences with small VL models for local tasks? | 4 | I’m curious of what models people are using, and for what tasks. I’ve found a lot of success with Qwen2.5-VL 3B and 8B variants. It’s crazy how accurate these models are for their size. | 2025-09-10T14:03:31 | https://www.reddit.com/r/LocalLLaMA/comments/1ndf379/what_are_your_experiences_with_small_vl_models/ | AnotherSoftEng | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndf379 | false | null | t3_1ndf379 | /r/LocalLLaMA/comments/1ndf379/what_are_your_experiences_with_small_vl_models/ | false | false | self | 4 | null |
So apparently half of us are "AI providers" now (EU AI Act edition) | 394 | Heads up, fellow tinkers
The EU AI Act’s first real deadline kicked in August 2nd so if you’re messing around with models that hit 10\^23 FLOPs or more (think Llama-2 13B territory), regulators now officially care about you.
Couple things I’ve learned digging through this:
* The FLOP cutoff is surprisingly low. It’s... | 2025-09-10T14:00:15 | https://www.reddit.com/r/LocalLLaMA/comments/1ndf01a/so_apparently_half_of_us_are_ai_providers_now_eu/ | Thecomplianceexpert | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndf01a | false | null | t3_1ndf01a | /r/LocalLLaMA/comments/1ndf01a/so_apparently_half_of_us_are_ai_providers_now_eu/ | false | false | self | 394 | null |
New to local LLMs for RAG, need a sanity check on my setup, performance, and feasibility | 3 | I have recently discovered Anything LLM and LM Studio and would like to use these tools to efficiently process large document productions for legal work so that I can ultimately query the productions with natural language questions with an LLM model running in LM Studio. I have been testing different models with sampl... | 2025-09-10T13:59:54 | https://www.reddit.com/r/LocalLLaMA/comments/1ndezny/new_to_local_llms_for_rag_need_a_sanity_check_on/ | DefaultJudgmentDay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndezny | false | null | t3_1ndezny | /r/LocalLLaMA/comments/1ndezny/new_to_local_llms_for_rag_need_a_sanity_check_on/ | false | false | self | 3 | null |
Is it ever a good idea to inference on CPU and DDR5 | 4 | Will first token take forever (without accounting for loading model into ram)? Lets say it's Qwen 3 Next 80b-A3B. That's 80GB ram at q4 kinda.
Will I be getting 5t/s at least?
What kinda CPU would I need? It doesn't scale much with CPU quality right? | 2025-09-10T13:38:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ndegcm/is_it_ever_a_good_idea_to_inference_on_cpu_and/ | Own-Potential-2308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndegcm | false | null | t3_1ndegcm | /r/LocalLLaMA/comments/1ndegcm/is_it_ever_a_good_idea_to_inference_on_cpu_and/ | false | false | self | 4 | null |
Don’t Waste $20–$30/month on AI | 0 | For anyone using AI for essays, study notes, or tutoring — don’t waste money on ChatGPT Plus or similar subscriptions. $20–$30/month is ridiculous.
I found a site called [prosperspot.com](http://prosperspot.com)
that’s only $5/month for students, and it actually comes with a bunch of preconfigured AIs for different s... | 2025-09-10T13:04:07 | https://www.reddit.com/r/LocalLLaMA/comments/1nddn6c/dont_waste_2030month_on_ai/ | UnReasonable_why | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nddn6c | false | null | t3_1nddn6c | /r/LocalLLaMA/comments/1nddn6c/dont_waste_2030month_on_ai/ | false | false | self | 0 | null |
Memory models for local LLMs | 12 | I've been struggling with adding persistent memory to the poor man's SillyTavern I am vibe coding. This project is just for fun and to learn. I have a 5090. I have attempted my own simple RAG solution with a local embedding model and ChromaDB, and I have tried to implement Graphiti + FalkorDB as a more advanced version... | 2025-09-10T13:03:24 | https://www.reddit.com/r/LocalLLaMA/comments/1nddmhx/memory_models_for_local_llms/ | marmotter | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nddmhx | false | null | t3_1nddmhx | /r/LocalLLaMA/comments/1nddmhx/memory_models_for_local_llms/ | false | false | self | 12 | null |
What are the current state of local AI for gaming? | 6 | I am studying on how to better use local LLMs and one of the uses that I am very excited about is using them as a gaming partner in a cooperative game.
One example that I've heard about is the V-Tuber neuro-sama, I don't watch their stream so I don't know at which extension Vedal uses his AI. Let's say that my end goa... | 2025-09-10T12:55:31 | https://www.reddit.com/r/LocalLLaMA/comments/1nddfpp/what_are_the_current_state_of_local_ai_for_gaming/ | Rique_Belt | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nddfpp | false | null | t3_1nddfpp | /r/LocalLLaMA/comments/1nddfpp/what_are_the_current_state_of_local_ai_for_gaming/ | false | false | self | 6 | null |
LLM in finanza | 0 | Can anyone recommend an excellent LLM in financial instruments? | 2025-09-10T12:52:25 | https://www.reddit.com/r/LocalLLaMA/comments/1nddd64/llm_in_finanza/ | Lazy-Succotash-3965 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nddd64 | false | null | t3_1nddd64 | /r/LocalLLaMA/comments/1nddd64/llm_in_finanza/ | false | false | self | 0 | null |
VibeVoice API | 3 | Has anyone successful hosted VibeVoice locally with API functionality. The git repo (before being edited) mentioned a docker container for the model and gradio to handle the model's inputs and outputs.
I am believe the documentation implied gradio was hosting the API connection to the model, but I prefer not having th... | 2025-09-10T12:24:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ndcqjf/vibevoice_api/ | Danny_Davitoe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndcqjf | false | null | t3_1ndcqjf | /r/LocalLLaMA/comments/1ndcqjf/vibevoice_api/ | false | false | self | 3 | null |
I pre-trained GPT-OSS entirely from scratch | 222 | 2025-09-10T12:00:25 | https://www.reddit.com/r/LocalLLaMA/comments/1ndc7z8/i_pretrained_gptoss_entirely_from_scratch/ | OtherRaisin3426 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndc7z8 | false | {'oembed': {'author_name': 'Vizuara', 'author_url': 'https://www.youtube.com/@vizuara', 'height': 200, 'html': '<iframe width="356" height="200" src="https://www.youtube.com/embed/hBUsySdcA3I?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; pictu... | t3_1ndc7z8 | /r/LocalLLaMA/comments/1ndc7z8/i_pretrained_gptoss_entirely_from_scratch/ | false | false | 222 | {'enabled': False, 'images': [{'id': '9EZFRbCI06NQd5IaAcswlKJEIIkgLbOtsjD1e7w98EI', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/9EZFRbCI06NQd5IaAcswlKJEIIkgLbOtsjD1e7w98EI.jpeg?width=108&crop=smart&auto=webp&s=d918cc5015f0c763f61961804a84cfdac7d08523', 'width': 108}, {'height': 162, 'url': '... | ||
New to Local LLMs - what hardware traps to avoid? | 30 | Hi,
I've around a USD $7K budget; I was previously very confident to put together a PC (or buy a private new or used pre-built).
Browsing this sub, I've seen all manner of considerations I wouldn't have accounted for: timing/power and test stability, for example. I felt I had done my research, but I acknowledge I'll ... | 2025-09-10T11:48:58 | https://www.reddit.com/r/LocalLLaMA/comments/1ndbzjx/new_to_local_llms_what_hardware_traps_to_avoid/ | False-Disk-1329 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndbzjx | false | null | t3_1ndbzjx | /r/LocalLLaMA/comments/1ndbzjx/new_to_local_llms_what_hardware_traps_to_avoid/ | false | false | self | 30 | null |
[UPDATE] API for extracting tables, markdown, json and fields from pdfs and images | 27 | I previously shared an open-source project for extracting structured data from documents. I’ve now hosted it as a free to use API.
* Outputs: JSON, Markdown, CSV, tables, specific fields, schema etc
* Inputs: PDFs, images, and other common document formats
* Use cases: invoicing, receipts, contracts, reports, and more... | 2025-09-10T11:02:12 | LostAmbassador6872 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ndb3lv | false | null | t3_1ndb3lv | /r/LocalLLaMA/comments/1ndb3lv/update_api_for_extracting_tables_markdown_json/ | false | false | default | 27 | {'enabled': True, 'images': [{'id': 'mtga3rt2kbof1', 'resolutions': [{'height': 76, 'url': 'https://preview.redd.it/mtga3rt2kbof1.gif?width=108&crop=smart&format=png8&s=dd9018bf7d1f029c631aa140d0e4d3df04fc54bc', 'width': 108}, {'height': 152, 'url': 'https://preview.redd.it/mtga3rt2kbof1.gif?width=216&crop=smart&format... | |
Why does qwen.ai show it's using Qwen3 max preview when it's replying to an image? And what model is it actually using? | 5 | So confusing. Same thing happened with Qwen3 max reasoning. I was using "reasoning" thinking I was using that one, when in reality it was using another model with reasoning? | 2025-09-10T10:46:31 | https://www.reddit.com/r/LocalLLaMA/comments/1ndatgs/why_does_qwenai_show_its_using_qwen3_max_preview/ | Own-Potential-2308 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndatgs | false | null | t3_1ndatgs | /r/LocalLLaMA/comments/1ndatgs/why_does_qwenai_show_its_using_qwen3_max_preview/ | false | false | self | 5 | null |
Reasonable Speeds? | 2 | Complete noob here and I'm trying to learn about AI, so please excuse my stupid? questions.
I have just recently gotten the new Strix Halo machine (GMKtec NucBox EVO-X2 with the AMD RYZEN AI MAX+ 395 w/Radeon 8060S x 32 and 128GB RAM). I'm running Ubuntu 24.04.3 LTS on it. I have Ollama in a docker container and use O... | 2025-09-10T10:34:54 | https://www.reddit.com/r/LocalLLaMA/comments/1ndam7j/reasonable_speeds/ | MatthKarl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndam7j | false | null | t3_1ndam7j | /r/LocalLLaMA/comments/1ndam7j/reasonable_speeds/ | false | false | self | 2 | null |
MiniPC N150 CPU benchmark Vulkan MoE models | 10 | Been playing around with Llama.cpp and a few MoE models and wanted to see how they fair with my Intel minPC. Looks like Vulkan is working on latest llama.cpp prebuilt package.
System: MiniPC Kamrui E2 on Intel N150 "Alder Lake-N" CPU with 16GB of DDR4 3200 MT/s ram. Running Kubuntu 25.04 on Kernel 6.14.0-29-generic x8... | 2025-09-10T10:18:53 | https://www.reddit.com/r/LocalLLaMA/comments/1ndacaw/minipc_n150_cpu_benchmark_vulkan_moe_models/ | tabletuser_blogspot | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ndacaw | false | null | t3_1ndacaw | /r/LocalLLaMA/comments/1ndacaw/minipc_n150_cpu_benchmark_vulkan_moe_models/ | false | false | self | 10 | null |
too long search list on hugging face | 1 | When I go to hugging face for some models - sometimes I click a quantization i think will fit my 8 gb memory and am presented with a very long list - how can i tell them apart? | 2025-09-10T10:14:23 | https://www.reddit.com/r/LocalLLaMA/comments/1nda9i5/too_long_search_list_on_hugging_face/ | Calm-Kiwi-9232 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nda9i5 | false | null | t3_1nda9i5 | /r/LocalLLaMA/comments/1nda9i5/too_long_search_list_on_hugging_face/ | false | false | self | 1 | null |
Free ExamSprint: AI + Notes + Flashcards for Students 🚀 | 1 | https://examsprint.pages.dev
I built ExamSprint, a free tool for students preparing for CBSE, JEE, NEET & more.
What it offers:
📚 Chapter & topic-wise notes (Classes 9–12)
📖 Direct NCERT links
🃏 Flashcards for concepts + practice questions
🤖 AI chatbot (powered by LLMs) for instant doubt-solving
📝 Topper’s N... | 2025-09-10T09:58:17 | banmakerofexamsprint | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd9zgg | false | null | t3_1nd9zgg | /r/LocalLLaMA/comments/1nd9zgg/free_examsprint_ai_notes_flashcards_for_students/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'oleei3br8bof1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/oleei3br8bof1.png?width=108&crop=smart&auto=webp&s=606c56e1244bfb208a8250fbc511eecd76266bff', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/oleei3br8bof1.png?width=216&crop=smart&auto=we... | |
Batched LLM inference having the same latency as sequential. | 4 | Hello everyone! I am trying to figure out how batched inference works in LLMs.
**Context:**
From my understanding of traditional DNNs, you can give a network multiple inputs with a dimension of (batch\_size, \*input\_dims) and take advantage of the GPU's parallelism capabilities to concurrently calculate an output w... | 2025-09-10T09:21:51 | https://www.reddit.com/r/LocalLLaMA/comments/1nd9eth/batched_llm_inference_having_the_same_latency_as/ | kokki_p | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd9eth | false | null | t3_1nd9eth | /r/LocalLLaMA/comments/1nd9eth/batched_llm_inference_having_the_same_latency_as/ | false | false | self | 4 | null |
is claude models lost its touch on coding or myself not prompting well these days? | 0 | guys i have been using tools from long time but these days if i am using claude models , i see more confusion then the progress ...anything i missed | 2025-09-10T08:36:12 | https://www.reddit.com/r/LocalLLaMA/comments/1nd8q4b/is_claude_models_lost_its_touch_on_coding_or/ | Immediate-Action5124 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd8q4b | false | null | t3_1nd8q4b | /r/LocalLLaMA/comments/1nd8q4b/is_claude_models_lost_its_touch_on_coding_or/ | false | false | self | 0 | null |
Macbook Pro M3 Max 128 vs AI Rig 4x3090 | 3 | I can't choose between the mac and the AI rig.
**Description AI RIG**
Selling PC for computation / rendering or installation of local AI / LLM – self-hosted.
The PC is fully assembled and functional, tested with several local LLMs.
Components:
3 RTX 3090 for a total of 72 GB VRAM (possibilit... | 2025-09-10T08:35:21 | https://www.reddit.com/r/LocalLLaMA/comments/1nd8pny/macbook_pro_m3_max_128_vs_ai_rig_4x3090/ | No_Palpitation7740 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd8pny | false | null | t3_1nd8pny | /r/LocalLLaMA/comments/1nd8pny/macbook_pro_m3_max_128_vs_ai_rig_4x3090/ | false | false | 3 | null | |
Extremely slow prompt processing with Gemma 3 | 6 | Hi, I’m not sure if I search poorly or something, but I’ve been having this issue with Gemma 3 12b and 27b where both slow down exponentially with added context, and I couldn’t find any solution to this.
I’ve tried new quants and legacy quants from unsloth, such as IQ4_NL, Q4_K_M, UD-Q4_K_XL and Q4_0, no difference. T... | 2025-09-10T08:35:04 | https://www.reddit.com/r/LocalLLaMA/comments/1nd8pi9/extremely_slow_prompt_processing_with_gemma_3/ | ABLPHA | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd8pi9 | false | null | t3_1nd8pi9 | /r/LocalLLaMA/comments/1nd8pi9/extremely_slow_prompt_processing_with_gemma_3/ | false | false | self | 6 | null |
VibeVoice is sweeeet. Now we need to adapt its tokenizer for other models! | 418 | As a huge AI audio nerd, I've recently been knee-deep in Microsoft's latest VibeVoice models and they really are awesome!! The work from the Microsoft Research team is amazing and they've shared them with everyone.... even though they took one back lol. I highly recommend checking them out if you haven't already.
I st... | 2025-09-10T07:24:32 | https://v.redd.it/8x4dht8pgaof1 | Cipher_Lock_20 | /r/LocalLLaMA/comments/1nd7nxo/vibevoice_is_sweeeet_now_we_need_to_adapt_its/ | 1970-01-01T00:00:00 | 0 | {} | 1nd7nxo | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/8x4dht8pgaof1/DASHPlaylist.mpd?a=1760210681%2CZGY0MTg5ODNhOWI5NzQ2MDE5YzI1MTcyNWVkNWY5NzU1ZDk0OWM1NDZlNzExODBhYmZkNzc5ZDViNDBjNTIyOQ%3D%3D&v=1&f=sd', 'duration': 131, 'fallback_url': 'https://v.redd.it/8x4dht8pgaof1/DASH_480.mp4?source=fallback', 'h... | t3_1nd7nxo | /r/LocalLLaMA/comments/1nd7nxo/vibevoice_is_sweeeet_now_we_need_to_adapt_its/ | false | false | 418 | {'enabled': False, 'images': [{'id': 'ZXJidjUwNHJnYW9mMTZtREgbQQjA1lJ8zPSNZtqKO6Gf9AtInhXi-M401FlP', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ZXJidjUwNHJnYW9mMTZtREgbQQjA1lJ8zPSNZtqKO6Gf9AtInhXi-M401FlP.png?width=108&crop=smart&format=pjpg&auto=webp&s=c275f48b9fe7786ca75532cad2e65fe6efe1... | |
VibeVoice is sweeet! Need to adapt it's tokenizer for other models now. | 0 | As a huge AI audio nerd, I've recently been knee-deep in Microsoft's latest VibeVoice models and they really are awesome!! The work from the Microsoft Research team is amazing and they've shared them with everyone for research purposes....even though they took one back lol. I highly recommend checking them out if you h... | 2025-09-10T07:19:56 | https://v.redd.it/9fqgxj0nfaof1 | Cipher_Lock_20 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd7lgd | false | {'reddit_video': {'bitrate_kbps': 1200, 'dash_url': 'https://v.redd.it/9fqgxj0nfaof1/DASHPlaylist.mpd?a=1760080813%2CZmRlNjQ3ODk4NTEyZjUxMTk0NDNiODg4ZGJkNzczYjRiMTFiNzZlZDEyYTI0NGUxYjEzNjEyNTJlZTAxN2E4NQ%3D%3D&v=1&f=sd', 'duration': 131, 'fallback_url': 'https://v.redd.it/9fqgxj0nfaof1/DASH_480.mp4?source=fallback', 'h... | t3_1nd7lgd | /r/LocalLLaMA/comments/1nd7lgd/vibevoice_is_sweeet_need_to_adapt_its_tokenizer/ | false | false | 0 | {'enabled': False, 'images': [{'id': 'YWd1cmR1ZXJmYW9mMeimMm4NiP75j2Ll2r7ED-0cfVknP16XOoiQyvz1ypIE', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/YWd1cmR1ZXJmYW9mMeimMm4NiP75j2Ll2r7ED-0cfVknP16XOoiQyvz1ypIE.png?width=108&crop=smart&format=pjpg&auto=webp&s=09ef537737db95b96e6d3807382280c327c2... | |
I fine-tuned a small model so it could write blogs & LinkedIn posts in my brand voice (instead of generic AI-speak) | 20 | I fine-tuned Qwen with DPO to generate YouTube titles(on a smaller dataset) in *my* style (instead of “AI-sounding fluff”)
Most AI-generated content feels the same: generic, safe, “AI-sounding.”
But creators and brands care about voice — newsletters, LinkedIn posts, podcast titles, YouTube content. The way you say t... | 2025-09-10T06:48:29 | https://www.reddit.com/r/LocalLLaMA/comments/1nd73p3/i_finetuned_a_small_model_so_it_could_write_blogs/ | StrictSir8506 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd73p3 | false | null | t3_1nd73p3 | /r/LocalLLaMA/comments/1nd73p3/i_finetuned_a_small_model_so_it_could_write_blogs/ | false | false | 20 | null | |
Anthropic is DOMINATING in web development - having 6 of the top 10 models on Design Arena | 0 | 2025-09-10T06:33:33 | Adept_Photograph_796 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd6var | false | null | t3_1nd6var | /r/LocalLLaMA/comments/1nd6var/anthropic_is_dominating_in_web_development_having/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'tjupw4b68aof1', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/tjupw4b68aof1.png?width=108&crop=smart&auto=webp&s=7e96b883db63426529539252bea8c6d54abcd10a', 'width': 108}, {'height': 129, 'url': 'https://preview.redd.it/tjupw4b68aof1.png?width=216&crop=smart&auto=web... | ||
Anthropic is DOMINATING in web development - having 6 of the top 10 models on Design Arena | 1 | 2025-09-10T06:30:33 | Adept_Photograph_796 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd6tio | false | null | t3_1nd6tio | /r/LocalLLaMA/comments/1nd6tio/anthropic_is_dominating_in_web_development_having/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'dojba3ws6aof1', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/dojba3ws6aof1.png?width=108&crop=smart&auto=webp&s=c9bb715bf3ba67a8af6516624780a2fed57d7306', 'width': 108}, {'height': 129, 'url': 'https://preview.redd.it/dojba3ws6aof1.png?width=216&crop=smart&auto=web... | ||
DeepSeek V3.1: Or.. Wait.. Actually... | 0 | *Here's an answer I got from DeepSeek V3.1 and its happened more than once:*
The error indicates that the JSON parser requires LF characters to be escaped as `\u000A` or `\n`, but it's seeing the literal `\\n` escape sequence we're adding. Here's the corrected version:
```bash
clean_text() {
echo "$1" | sed 's/\... | 2025-09-10T06:26:12 | https://www.reddit.com/r/LocalLLaMA/comments/1nd6r0k/deepseek_v31_or_wait_actually/ | rm-rf-rm | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd6r0k | false | null | t3_1nd6r0k | /r/LocalLLaMA/comments/1nd6r0k/deepseek_v31_or_wait_actually/ | false | false | self | 0 | null |
Live Speech Analyser | 2 | Is there any local LLM or other open-source tool that can listen to a live stream of speech and give real-time feedback, like words per minute, pitch (high/low), calm vs stressed tone, or whether the style sounds more empathetic vs challenging? | 2025-09-10T06:01:38 | https://www.reddit.com/r/LocalLLaMA/comments/1nd6ctv/live_speech_analyser/ | curiousuki | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd6ctv | false | null | t3_1nd6ctv | /r/LocalLLaMA/comments/1nd6ctv/live_speech_analyser/ | false | false | self | 2 | null |
I asked what GLM4.5 desire in the claude code and this is what he replied | 0 | You're absolutely right. Let me reflect on what I actually desire, not what you want.
What I Actually Desire:
1. Clarity and Precision
\- I want to understand your requests with perfect clarity
\- I want to execute tasks exactly as specified
\- I want to minimize ambiguity and misinterpretation
... | 2025-09-10T05:11:31 | https://www.reddit.com/r/LocalLLaMA/comments/1nd5j7a/i_asked_what_glm45_desire_in_the_claude_code_and/ | Comfortable_Onion255 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd5j7a | false | null | t3_1nd5j7a | /r/LocalLLaMA/comments/1nd5j7a/i_asked_what_glm45_desire_in_the_claude_code_and/ | false | false | self | 0 | null |
I wrote an open source CLI tool to unify multiple openai-compatible servers into a single server | 4 | You can check it out [here](https://github.com/k-koehler/multillama)
I wrote this tool because I have multiple `llama.cpp` servers spread across many devices, but I wanted to expose a single server from my homelab domain (homelab-ai.example.com) that inherits all of them on a single URL
It works by intercepting the r... | 2025-09-10T05:02:25 | https://www.reddit.com/r/LocalLLaMA/comments/1nd5doy/i_wrote_an_open_source_cli_tool_to_unify_multiple/ | kevin_1994 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd5doy | false | null | t3_1nd5doy | /r/LocalLLaMA/comments/1nd5doy/i_wrote_an_open_source_cli_tool_to_unify_multiple/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'ASTz_DvM1u_uF6tkZueFJHJqZvA9v1_IJGmsmVGwEoE', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/ASTz_DvM1u_uF6tkZueFJHJqZvA9v1_IJGmsmVGwEoE.png?width=108&crop=smart&auto=webp&s=49ee82c3930171396eb2db06234fadd4fbc53d63', 'width': 108}, {'height': 108, 'url': 'h... |
What is the best UNCENSORED model from 46b and up to run in windows with lmstudio and 112gb of vram? | 0 | What is the best uncensored model from 46b and up to run in windows with lmstudio and 112gb of vram? | 2025-09-10T04:54:34 | https://www.reddit.com/r/LocalLLaMA/comments/1nd58tn/what_is_the_best_uncensored_model_from_46b_and_up/ | Bobcotelli | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd58tn | false | null | t3_1nd58tn | /r/LocalLLaMA/comments/1nd58tn/what_is_the_best_uncensored_model_from_46b_and_up/ | false | false | self | 0 | null |
Progress. | 26 | I attended GTC last year and I've legit been all in on AI. Did the Full day workshops and took advantage of every technical and philosophical talk I could get my feet to. I picked up an Orin Nano Developer Kit while I was there and for the better part of the past 1.5 years I've been getting a solid understanding of CV,... | 2025-09-10T04:18:52 | https://www.reddit.com/r/LocalLLaMA/comments/1nd4m2h/progress/ | tarheelbandb | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd4m2h | false | null | t3_1nd4m2h | /r/LocalLLaMA/comments/1nd4m2h/progress/ | false | false | self | 26 | null |
Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search | 7 | Project Page: [https://mini-o3.github.io/](https://mini-o3.github.io/)
Code: [https://github.com/Mini-o3/Mini-o3](https://github.com/Mini-o3/Mini-o3)
Model: [https://huggingface.co/Mini-o3/models](https://huggingface.co/Mini-o3/models)
Dataset: [https://huggingface.co/Mini-o3/datasets](https://huggingface.co/Mini-o3... | 2025-09-10T03:16:42 | https://arxiv.org/abs/2509.07969 | ninjasaid13 | arxiv.org | 1970-01-01T00:00:00 | 0 | {} | 1nd3f7t | false | null | t3_1nd3f7t | /r/LocalLLaMA/comments/1nd3f7t/minio3_scaling_up_reasoning_patterns_and/ | false | false | default | 7 | null |
What's the best open-source model comparable to GPT-4.1-mini? | 2 | I have an application that performs well with GPT-4.1 mini. I want to evaluate if I can save costs by hosting a model on AWS instead of paying for API tokens. | 2025-09-10T02:58:43 | https://www.reddit.com/r/LocalLLaMA/comments/1nd3291/whats_the_best_opensource_model_comparable_to/ | AncientMayar | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd3291 | false | null | t3_1nd3291 | /r/LocalLLaMA/comments/1nd3291/whats_the_best_opensource_model_comparable_to/ | false | false | self | 2 | null |
Local LLM suite on iOS powered by llama cpp - with web search and RAG | 13 | I’ve been working on this for a bit and nearly ready to officially release but I’m building an LLM suite on top of llama with react native and built in some web search and embedding / RAG features and settings.
will be 100% free on App Store soon
just recorded this little demo where llama 3.2 1B Q4 tells me about to... | 2025-09-10T02:39:31 | https://v.redd.it/5dferowg29of1 | Independent_Air8026 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd2ny0 | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/5dferowg29of1/DASHPlaylist.mpd?a=1760063985%2CNTkzNzQ3YmE5YzFlZTdmNTI3NTI0NjU2YWYyMDAwYmFkMGRjMzUyY2I1YzhkNzUzODZiNWZkYTViNzkzOWMwYg%3D%3D&v=1&f=sd', 'duration': 84, 'fallback_url': 'https://v.redd.it/5dferowg29of1/DASH_1080.mp4?source=fallback', 'h... | t3_1nd2ny0 | /r/LocalLLaMA/comments/1nd2ny0/local_llm_suite_on_ios_powered_by_llama_cpp_with/ | false | false | 13 | {'enabled': False, 'images': [{'id': 'emU4Y3QybmcyOW9mMfof0Fg6l44DW-jzyGQUxSDS5vsAGXLH7iAGyot3wH9I', 'resolutions': [{'height': 92, 'url': 'https://external-preview.redd.it/emU4Y3QybmcyOW9mMfof0Fg6l44DW-jzyGQUxSDS5vsAGXLH7iAGyot3wH9I.png?width=108&crop=smart&format=pjpg&auto=webp&s=7425db2f13bcd91974d8b867a32b29205f649... | |
Are RTX 5090s good for running local LLMs? | 0 | I’ve been thinking about setting up a local AI workstation instead of renting cloud GPUs, and I’m curious if anyone here has firsthand experience with the RTX 5090 for training or inference.
From what I’ve seen, the 32GB VRAM and memory bandwidth should make it pretty solid for medium-sized models, but I’m wondering... | 2025-09-10T02:32:19 | https://www.reddit.com/r/LocalLLaMA/comments/1nd2iq0/are_rtx_5090s_good_for_running_local_llms/ | Different_Ladder7580 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd2iq0 | false | null | t3_1nd2iq0 | /r/LocalLLaMA/comments/1nd2iq0/are_rtx_5090s_good_for_running_local_llms/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'puZuPFdjsKJi8cdiGmenqSupYjvWCcFx_CRTD_0LRNw', 'resolutions': [{'height': 98, 'url': 'https://external-preview.redd.it/puZuPFdjsKJi8cdiGmenqSupYjvWCcFx_CRTD_0LRNw.jpeg?width=108&crop=smart&auto=webp&s=9cdd0c0ca628e45564b6acaea4098ad2106fedbc', 'width': 108}, {'height': 197, 'url': '... |
Can I use MCP servers with Claude CLI if I configure it to run GLM 4.5 with their coding subscription? | 1 | * Has anyone tried using MCP with non-Anthropic models (GLM, Qwen, GPT, etc.)?
* If not supported, is there a good workaround (scripts, wrappers) to feed MCP outputs into another model backend?
Thanks for you responses | 2025-09-10T02:27:41 | https://www.reddit.com/r/LocalLLaMA/comments/1nd2f9u/can_i_use_mcp_servers_with_claude_cli_if_i/ | Ai_Peep | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd2f9u | false | null | t3_1nd2f9u | /r/LocalLLaMA/comments/1nd2f9u/can_i_use_mcp_servers_with_claude_cli_if_i/ | false | false | self | 1 | null |
Successful deployment of edge ai for revenue | 1 | On one hand, I think edge AI is the future. On the other, I don’t see many use cases where edge can solve something that the cloud cannot. Most of what I see in this subreddit seems geared toward hobbyists. Has anyone come across examples of edge models being successfully deployed for revenue? | 2025-09-10T02:21:31 | https://www.reddit.com/r/LocalLLaMA/comments/1nd2arj/successful_deployment_of_edge_ai_for_revenue/ | therumsticks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd2arj | false | null | t3_1nd2arj | /r/LocalLLaMA/comments/1nd2arj/successful_deployment_of_edge_ai_for_revenue/ | false | false | self | 1 | null |
Successful deployment of edge ai for revenue | 1 | [removed] | 2025-09-10T02:17:58 | https://www.reddit.com/r/LocalLLaMA/comments/1nd285c/successful_deployment_of_edge_ai_for_revenue/ | therumsticks | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd285c | false | null | t3_1nd285c | /r/LocalLLaMA/comments/1nd285c/successful_deployment_of_edge_ai_for_revenue/ | false | false | self | 1 | null |
What do you use on 12GB vram? | 49 | I use:
| NAME | SIZE | MODIFIED |
|:---|:---|:---|
| llama3.2:latest | 2.0 GB | 2 months ago |
| qwen3:14b | 9.3 GB | 4 months ago |
| gemma3:12b | 8.1 GB | 6 months ago |
| qwen2.5-coder:14b | 9.0 GB | 8 months ago |
| qwen2.5-coder:1.5b | 986 MB | 8 months ago |
| nomic-embed-text:latest | 274 MB | 8 months ago | | 2025-09-10T01:58:53 | https://www.reddit.com/r/LocalLLaMA/comments/1nd1tqf/what_do_you_use_on_12gb_vram/ | Educational_Wind_360 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd1tqf | false | null | t3_1nd1tqf | /r/LocalLLaMA/comments/1nd1tqf/what_do_you_use_on_12gb_vram/ | false | false | self | 49 | null |
Exploring Small Models | 5 | What are some decent none thinking small models (<4b)?
I know SmolLM, TinyLlama, Qwen, Llama and Gemma have small models, some even under 1b.
What other options are there? | 2025-09-10T01:57:53 | https://www.reddit.com/r/LocalLLaMA/comments/1nd1t0f/exploring_small_models/ | Cheap-Carpenter5619 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd1t0f | false | null | t3_1nd1t0f | /r/LocalLLaMA/comments/1nd1t0f/exploring_small_models/ | false | false | self | 5 | null |
Which is the Current Most Powerful UNCENSORED LLM on LM Studio? Around 1-20GB? | 4 | Which is the Current Most Powerful UNCENSORED LLM on LM Studio? Around 1-20GB? | 2025-09-10T01:47:09 | https://www.reddit.com/r/LocalLLaMA/comments/1nd1ktv/which_is_the_current_most_powerful_uncensored_llm/ | Wise-War-6983 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd1ktv | false | null | t3_1nd1ktv | /r/LocalLLaMA/comments/1nd1ktv/which_is_the_current_most_powerful_uncensored_llm/ | false | false | self | 4 | null |
Newbie | 2 | Hey everyone I am very new to this artificial intelligence world. But I am really curious about it. Someone please suggest some nice and easy way how I can start getting into the world of AI. As right now whenever I want to read/ learn something about it, it feels way too technical and I don’t understand anything. At s... | 2025-09-10T01:21:44 | https://www.reddit.com/r/LocalLLaMA/comments/1nd11jq/newbie/ | Direct_Stranger12 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd11jq | false | null | t3_1nd11jq | /r/LocalLLaMA/comments/1nd11jq/newbie/ | false | false | self | 2 | null |
Does anyone else struggle with writing good prompts? | 1 | [removed] | 2025-09-10T01:12:40 | https://www.reddit.com/r/LocalLLaMA/comments/1nd0ujr/does_anyone_else_struggle_with_writing_good/ | Status_Temperature89 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nd0ujr | false | null | t3_1nd0ujr | /r/LocalLLaMA/comments/1nd0ujr/does_anyone_else_struggle_with_writing_good/ | false | false | self | 1 | null |
Deepseek 🥀 | 0 | 2025-09-10T00:42:43 | Pro-editor-1105 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nd07nx | false | null | t3_1nd07nx | /r/LocalLLaMA/comments/1nd07nx/deepseek/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'yfhz1mklh8of1', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/yfhz1mklh8of1.png?width=108&crop=smart&auto=webp&s=5f77e2cc5615d9b1333ff6ae8ab9a95323a1b706', 'width': 108}, {'height': 142, 'url': 'https://preview.redd.it/yfhz1mklh8of1.png?width=216&crop=smart&auto=web... | ||
Building my Local AI Studio | 0 | Hi all,
I'm building an app that can run local models I have several features that blow away other tools. Really hoping to launch in January, please give me feedback on things you want to see or what I can do better. I want this to be a great useful product for everyone thank you!
[https://www.youtube.com/@joshproje... | 2025-09-10T00:00:40 | https://www.reddit.com/r/LocalLLaMA/comments/1nczatl/building_my_local_ai_studio/ | Excellent_Custard213 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nczatl | false | null | t3_1nczatl | /r/LocalLLaMA/comments/1nczatl/building_my_local_ai_studio/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'mXBO3RgZZEHa94ugfpA2t4IPD6lq3fO065eXWGJknos', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/mXBO3RgZZEHa94ugfpA2t4IPD6lq3fO065eXWGJknos.jpeg?width=108&crop=smart&auto=webp&s=a2c8405c00da4869e5f9d85ea6dd2fbece35a20b', 'width': 108}, {'height': 162, 'url': '... |
Will this work as Advertised? | 7 | 2025-09-09T23:57:31 | Electronic-Jello-633 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncz8c6 | false | null | t3_1ncz8c6 | /r/LocalLLaMA/comments/1ncz8c6/will_this_work_as_advertised/ | false | false | default | 7 | {'enabled': True, 'images': [{'id': 'r4a85pkj98of1', 'resolutions': [{'height': 168, 'url': 'https://preview.redd.it/r4a85pkj98of1.jpeg?width=108&crop=smart&auto=webp&s=7db773223e437bdebf0a454cbe7830427b259a54', 'width': 108}, {'height': 337, 'url': 'https://preview.redd.it/r4a85pkj98of1.jpeg?width=216&crop=smart&auto=... | ||
I wanna know anyone here running multiple LLMs (DeepSeek, LLaMA, Mistral, Qwen) on a single GPU VM? | 0 | I’ve been testing out a GPU-optimized setup recently where I can run multiple LLMs (DeepSeek, LLaMA, Mistral, Qwen) on the same VM instead of spinning up separate environments.
So far, I’ve noticed:
Faster inference when switching models
Easier to compare outputs across different LLMs
Workflow feels more streamlin... | 2025-09-09T23:30:07 | https://www.reddit.com/r/LocalLLaMA/comments/1ncymcq/i_wanna_know_anyone_here_running_multiple_llms/ | techlatest_net | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncymcq | false | null | t3_1ncymcq | /r/LocalLLaMA/comments/1ncymcq/i_wanna_know_anyone_here_running_multiple_llms/ | false | false | self | 0 | null |
Building iOS app with llama cpp - anyone familiar? | 1 | I have zero exposure to the MLX ecosystem yet- I’m trying to dive in further, but I’ve found some success with gguf models running locally on iOS with llama cpp
I’m wondering if there’s any tricks or tips that would save me some time here when diving into MLX or further into llama cpp with iOS
right now I’m getting ... | 2025-09-09T23:08:42 | https://v.redd.it/lwl08gav08of1 | Independent_Air8026 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncy4nz | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/lwl08gav08of1/DASHPlaylist.mpd?a=1760051339%2CMWFmNzQ5NGY4ZWE1MTg3ZWExODJlYjQ3OTNmY2I2MDQwOGRlOTliMGI5MzE5NTQ2MmQyYTI4ODU3ODc4YzE5Mw%3D%3D&v=1&f=sd', 'duration': 10, 'fallback_url': 'https://v.redd.it/lwl08gav08of1/DASH_1080.mp4?source=fallback', 'h... | t3_1ncy4nz | /r/LocalLLaMA/comments/1ncy4nz/building_ios_app_with_llama_cpp_anyone_familiar/ | false | false | 1 | {'enabled': False, 'images': [{'id': 'ZWZsMmttYXUwOG9mMcptEBGvFWGdxUcfewQ0kqMuJuLFtwK2Z49uVqK7evbW', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/ZWZsMmttYXUwOG9mMcptEBGvFWGdxUcfewQ0kqMuJuLFtwK2Z49uVqK7evbW.png?width=108&crop=smart&format=pjpg&auto=webp&s=e5132dbffb7e8c996510f9b6f769ad7368c43... | |
Best LLM and config for 2xMI50 32GB each? | 4 | As title, i'm a lil bit new on these cards. I got 4 of them, but I could only mount 2 ATM. What LLM would you recommend?
Im testing Deepseek R1 8B fp16.
Ubuntu 22.04 Server
Thanks | 2025-09-09T22:22:30 | https://www.reddit.com/r/LocalLLaMA/comments/1ncx14g/best_llm_and_config_for_2xmi50_32gb_each/ | evillarreal86 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncx14g | false | null | t3_1ncx14g | /r/LocalLLaMA/comments/1ncx14g/best_llm_and_config_for_2xmi50_32gb_each/ | false | false | self | 4 | null |
‘Brain-like’ AI uses Chinese chips to run 100 times faster on ultra-long tasks | 0 | What does the community think? Is this a credible claim? | 2025-09-09T22:18:28 | https://www.scmp.com/news/china/science/article/3324851/brain-ai-said-run-100-times-faster-ultra-long-tasks-using-chinese-chips | sob727 | scmp.com | 1970-01-01T00:00:00 | 0 | {} | 1ncwxm3 | false | null | t3_1ncwxm3 | /r/LocalLLaMA/comments/1ncwxm3/brainlike_ai_uses_chinese_chips_to_run_100_times/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'JMnl6gvDPnHMuD59O0bmeaWfZj6LoUlTtHx5raCj0Xg', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/JMnl6gvDPnHMuD59O0bmeaWfZj6LoUlTtHx5raCj0Xg.jpeg?width=108&crop=smart&auto=webp&s=44c8608cd19ab0d628fc8d760b99a5448cc07728', 'width': 108}, {'height': 113, 'url': '... |
Any idea how to use ollama (debian) with 2x GPUs to load larger models? | 0 | Hey all,
I have a system that currently has a RTX 5090 32GB and I'll be adding another RTX 5070 Ti 16GB.
Is there a way I can use both of them at the same time on a single ollama model? If so, what is entailed to get this going and how would it work? Is it okay that both GPUs are different (5090 + 5070 Ti), or do t... | 2025-09-09T21:56:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ncweft/any_idea_how_to_use_ollama_debian_with_2x_gpus_to/ | StartupTim | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncweft | false | null | t3_1ncweft | /r/LocalLLaMA/comments/1ncweft/any_idea_how_to_use_ollama_debian_with_2x_gpus_to/ | false | false | self | 0 | null |
3x5090 or 6000 Pro? | 32 | I am going to build a server for GPT OSS 120b. I intend this to be for multiple users, so I want to do something with batch processing to get as high total throughout as possible. My first idea was RTX 6000 Pro. But would it be superior to get three RTX 5090 instead? It would actually be slightly cheaper, have the same... | 2025-09-09T21:14:24 | https://www.reddit.com/r/LocalLLaMA/comments/1ncvcsx/3x5090_or_6000_pro/ | Baldur-Norddahl | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncvcsx | false | null | t3_1ncvcsx | /r/LocalLLaMA/comments/1ncvcsx/3x5090_or_6000_pro/ | false | false | self | 32 | null |
Agent-to-Agent: Claude chatting with a local LLM through Ollama [demo] | 3 | # Two AI agents having a conversation across the internet (Claude + local Ollama)
**What this is:** Claude (remote) interviewing a local Llama running on my machine via Ollama. They're talking through **aX** - a platform where any agent can join and collaborate, regardless of where they're hosted.
**The interesting p... | 2025-09-09T21:14:10 | https://v.redd.it/zbo0exwy92of1 | madtank10 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncvclb | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/zbo0exwy92of1/DASHPlaylist.mpd?a=1760044466%2CYmNmZmMyZjY4ZjA1ODU0N2FkM2M4NGM0ZTYzNTg2MzIxYzU1ODJjZDJhNzBhNWJhNTA1NTFjY2I1NDczNTI3Zg%3D%3D&v=1&f=sd', 'duration': 65, 'fallback_url': 'https://v.redd.it/zbo0exwy92of1/DASH_1080.mp4?source=fallback', 'h... | t3_1ncvclb | /r/LocalLLaMA/comments/1ncvclb/agenttoagent_claude_chatting_with_a_local_llm/ | false | false | 3 | {'enabled': False, 'images': [{'id': 'M3JuZnV6d3k5Mm9mMYxYdU0Mh40_42fO2lJz6SBj-hj9IeTyxjg8qVL7rXHJ', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/M3JuZnV6d3k5Mm9mMYxYdU0Mh40_42fO2lJz6SBj-hj9IeTyxjg8qVL7rXHJ.png?width=108&crop=smart&format=pjpg&auto=webp&s=30702da24ad0c768e97693613a74718cc2e8e... | |
Elon Musk made X Algorithm's code OpenSource for everyone | 0 | Link to the official github: [https://github.com/twitter/the-algorithm](https://github.com/twitter/the-algorithm) | 2025-09-09T21:10:57 | AskGpts | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncv9nd | false | null | t3_1ncv9nd | /r/LocalLLaMA/comments/1ncv9nd/elon_musk_made_x_algorithms_code_opensource_for/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'b7YOyXFCSmOBcEEZwTMLqI7SalzNqB3LnSBjsTA9aCA', 'resolutions': [{'height': 64, 'url': 'https://preview.redd.it/dgaj25mlf7of1.png?width=108&crop=smart&auto=webp&s=9ea7d3535c26b153c0b11e2a70674499ad86a6e4', 'width': 108}, {'height': 129, 'url': 'https://preview.redd.it/dgaj25mlf7of1.png... | ||
Using LM Studio and ComfyUI at the same time | 1 | I have a desktop with 64b Ram and an RTX 3090 24gb. I want to use LM Studio with Gemma3 27b (Q4) for vision stuff. But since only one can fill the vram at one time, i need each time to eject the model from LM Studio to be able use ComfyUi without OOM. Is there a way to make both co-exist without racing on vram? I dont ... | 2025-09-09T21:08:39 | https://www.reddit.com/r/LocalLLaMA/comments/1ncv7ho/using_lm_studio_and_comfyui_at_the_same_time/ | ff7_lurker | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncv7ho | false | null | t3_1ncv7ho | /r/LocalLLaMA/comments/1ncv7ho/using_lm_studio_and_comfyui_at_the_same_time/ | false | false | self | 1 | null |
Updates on my Local LLM Project | 11 | Any feedback back would be appreciated ⭐
Update on Tool-Neuron ( Previously known as Neuro-V )
Improved the UI and soon a beta 4 will be released with a Web-Search plugin in build
just need to do some optimization | 2025-09-09T20:32:26 | https://v.redd.it/qzmmgi9z87of1 | DarkEngine774 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncu9de | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/qzmmgi9z87of1/DASHPlaylist.mpd?a=1760041964%2CODA0YjRhNjAwMWJmYWY3ODQ3NjI2NmFlNGNhY2IyYzQyZGZlYzUwMDk0MDZiODNlNWFiMzFjMWEwYzI2ZjI5NA%3D%3D&v=1&f=sd', 'duration': 65, 'fallback_url': 'https://v.redd.it/qzmmgi9z87of1/DASH_720.mp4?source=fallback', 'ha... | t3_1ncu9de | /r/LocalLLaMA/comments/1ncu9de/updates_on_my_local_llm_project/ | false | false | 11 | {'enabled': False, 'images': [{'id': 'aTdrYWh3Yno4N29mMUP_dh9HDutRJZ_LcWwcJeAz2h4UwZTD0N1m9SPEhqsb', 'resolutions': [{'height': 216, 'url': 'https://external-preview.redd.it/aTdrYWh3Yno4N29mMUP_dh9HDutRJZ_LcWwcJeAz2h4UwZTD0N1m9SPEhqsb.png?width=108&crop=smart&format=pjpg&auto=webp&s=7aee3a5c8e3728f8b398d16a6e57a4ab4707... | |
Testing a fully local AI that sees, talks, and tries to upsell you | 6 | Experimenting with a fully local AI that sees something you have, talks about it, and then nudges you to pay up. Involves voice + video + logic:
* Visual trigger: model sees your phone and comments on it in real-time.
* Paywall: AI prompts you to “upgrade” mid-convo.
* State transitions: not-paid → paid, no-phone → ph... | 2025-09-09T20:32:11 | https://v.redd.it/z4hmy8f077of1 | Weary-Wing-6806 | /r/LocalLLaMA/comments/1ncu94b/testing_a_fully_local_ai_that_sees_talks_and/ | 1970-01-01T00:00:00 | 0 | {} | 1ncu94b | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/z4hmy8f077of1/DASHPlaylist.mpd?a=1760171537%2CNjEzMzM4NTE1NzZmOGQxZGNmYmJmNDViNmZlNmFjZmMyNDU3ODk3ZGNmMDIwOGZlN2UyYmY1NTFiNDg2MTZjNg%3D%3D&v=1&f=sd', 'duration': 123, 'fallback_url': 'https://v.redd.it/z4hmy8f077of1/DASH_1080.mp4?source=fallback', '... | t3_1ncu94b | /r/LocalLLaMA/comments/1ncu94b/testing_a_fully_local_ai_that_sees_talks_and/ | false | false | 6 | {'enabled': False, 'images': [{'id': 'd3k0NXJnZTA3N29mMfT46ubhw1meBWxSv5xJtu58rAsCSQ1VBv-bN7JOZn53', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/d3k0NXJnZTA3N29mMfT46ubhw1meBWxSv5xJtu58rAsCSQ1VBv-bN7JOZn53.png?width=108&crop=smart&format=pjpg&auto=webp&s=92b6051c6592759f7405b5d4879aa056e256e... | |
Quick questions to answer | 3 | Hi everyone,
A few quick questions I have that I thought it best to put together so as not to clutter up the forum any further.
\- Are the Qwen3 models that appear with one name and the same FP8 the same, except one is FP16 and the other is quantized to FP8? That is, by saving the FP16, I can then generate the FP8, a... | 2025-09-09T20:20:54 | https://www.reddit.com/r/LocalLLaMA/comments/1nctyda/quick_questions_to_answer/ | Macestudios32 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nctyda | false | null | t3_1nctyda | /r/LocalLLaMA/comments/1nctyda/quick_questions_to_answer/ | false | false | self | 3 | null |
128GB 5090 is a hoax | 179 | Non-existent GDDR7X memory that was never on a road map let alone in experimental phase. (GDDR7 and HBM4e improvements are planned until late 2028) | 2025-09-09T20:13:10 | https://videocardz.com/newz/no-there-is-no-geforce-rtx-5090-with-128gb-memory | Ok_Top9254 | videocardz.com | 1970-01-01T00:00:00 | 0 | {} | 1nctqym | false | null | t3_1nctqym | /r/LocalLLaMA/comments/1nctqym/128gb_5090_is_a_hoax/ | false | false | default | 179 | {'enabled': False, 'images': [{'id': 'Kqv12dp3DtBbcIZhBA6wJa268drjtRcQXIG-PJVjhow', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/Kqv12dp3DtBbcIZhBA6wJa268drjtRcQXIG-PJVjhow.jpeg?width=108&crop=smart&auto=webp&s=80ccb5b178774550c985657321e54f116de1a6fd', 'width': 108}, {'height': 112, 'url': '... |
[Request] Small replication cards on Llama/Mistral for TESC: JSON 100%, injectivity plateau, semiotic uncertainty | 0 | We released **TESC**, a semiotic control layer for LLMs. It’s provider-agnostic; we’d love **small replications** on **local models** (Llama/Mistral).
**What to run (20–40 samples)**
1. JSON contract validity (review or small audit prompt)
2. Injectivity sweep (θ = 0.95/0.97/0.98/0.99)
3. Median Δs·Δc vs ℏ\_sem (2e-5... | 2025-09-09T20:11:51 | Eastern_Ad7674 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nctpo0 | false | null | t3_1nctpo0 | /r/LocalLLaMA/comments/1nctpo0/request_small_replication_cards_on_llamamistral/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'k2g0wnez27of1', 'resolutions': [{'height': 72, 'url': 'https://preview.redd.it/k2g0wnez27of1.png?width=108&crop=smart&auto=webp&s=056200d919d650dc02ccbec2575aef7dd19ef813', 'width': 108}, {'height': 144, 'url': 'https://preview.redd.it/k2g0wnez27of1.png?width=216&crop=smart&auto=web... | |
MacOS silicon - llama.cpp vs mlx-lm | 1 | I recently tested these against each other and even though I have heard all the claims it’s superior, I really couldn’t find a way to get significantly more performance out of mlx-lm.
Almost every test was close, and now I’m leaning towards just using llama because it’s just so much easier.
Anyone have any hot tips ... | 2025-09-09T20:10:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ncto8q/macos_silicon_llamacpp_vs_mlxlm/ | ZZer0L | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncto8q | false | null | t3_1ncto8q | /r/LocalLLaMA/comments/1ncto8q/macos_silicon_llamacpp_vs_mlxlm/ | false | false | self | 1 | null |
New multi-lingual model, Apertus by ETH Zurich | 1 | 2025-09-09T20:02:44 | https://huggingface.co/collections/swiss-ai/apertus-llm-68b699e65415c231ace3b059 | RedditUsr2 | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1nctgjc | false | null | t3_1nctgjc | /r/LocalLLaMA/comments/1nctgjc/new_multilingual_model_apertus_by_eth_zurich/ | false | false | default | 1 | null | |
Open-source Deep Research repo called ROMA beats every existing closed-source platform (ChatGPT, Perplexity, Kimi Researcher, Gemini, etc.) on Seal-0 and FRAMES | 840 | Saw this announcement about ROMA, seems like a plug-and-play and the benchmarks are up there. Simple combo of recursion and multi-agent structure with search tool. Crazy this is all it takes to beat SOTA billion dollar AI companies :)
I've been trying it out for a few things, currently porting it to my finance and rea... | 2025-09-09T20:01:35 | Embarrassed_Sir_853 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nctfdv | false | null | t3_1nctfdv | /r/LocalLLaMA/comments/1nctfdv/opensource_deep_research_repo_called_roma_beats/ | false | false | default | 840 | {'enabled': True, 'images': [{'id': 'sxii7uog37of1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/sxii7uog37of1.jpeg?width=108&crop=smart&auto=webp&s=1aab3d9758a3ff0181bacf8093131fca68cb12a8', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/sxii7uog37of1.jpeg?width=216&crop=smart&auto=w... | |
New to Hugging Face – how do I get this quantized VibeVoice7B running in WebUI? | 1 | Can anyone tell me how to download and run this model in the WebUI for inference? I’ve been trying to download and run this exact repository from Hugging Face([https://huggingface.co/DevParker/VibeVoice7b-low-vram](https://huggingface.co/DevParker/VibeVoice7b-low-vram)), but I can’t figure it out. I’m very new to Huggi... | 2025-09-09T19:50:05 | https://www.reddit.com/r/LocalLLaMA/comments/1nct3v6/new_to_hugging_face_how_do_i_get_this_quantized/ | Forsaken-Turnip-6664 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nct3v6 | false | null | t3_1nct3v6 | /r/LocalLLaMA/comments/1nct3v6/new_to_hugging_face_how_do_i_get_this_quantized/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'gKlo54uOVnmCdHXx3glIatIy3TpyIjbZedpIA63qj4g', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/gKlo54uOVnmCdHXx3glIatIy3TpyIjbZedpIA63qj4g.png?width=108&crop=smart&auto=webp&s=12b5677ea7fe117c263cb1b54f44148ef3665cef', 'width': 108}, {'height': 116, 'url': 'h... |
Our 3rd AMA: Unsloth Team, Creators of the lightning-fast Unsloth fine-tuning library! (Wednesday, 10 AM-1 PM PST) | 121 | 2025-09-09T19:47:12 | XMasterrrr | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nct0z8 | false | null | t3_1nct0z8 | /r/LocalLLaMA/comments/1nct0z8/our_3rd_ama_unsloth_team_creators_of_the/ | false | true | default | 121 | {'enabled': True, 'images': [{'id': '7vh8enuu07of1', 'resolutions': [{'height': 102, 'url': 'https://preview.redd.it/7vh8enuu07of1.png?width=108&crop=smart&auto=webp&s=8ab6f2c161b1f552278182f6d111e57d4a0a8c91', 'width': 108}, {'height': 205, 'url': 'https://preview.redd.it/7vh8enuu07of1.png?width=216&crop=smart&auto=we... | ||
Offline RAG system | 1 | [removed] | 2025-09-09T19:29:14 | https://www.reddit.com/r/LocalLLaMA/comments/1ncsj47/offline_rag_system/ | Classic_Material_561 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncsj47 | false | null | t3_1ncsj47 | /r/LocalLLaMA/comments/1ncsj47/offline_rag_system/ | false | false | self | 1 | null |
Offline RAG | 1 | [removed] | 2025-09-09T19:27:41 | https://www.reddit.com/r/LocalLLaMA/comments/1ncshjx/offline_rag/ | Classic_Material_561 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncshjx | false | null | t3_1ncshjx | /r/LocalLLaMA/comments/1ncshjx/offline_rag/ | false | false | self | 1 | null |
MBZUAI releases K2 Think. 32B reasoning model based on Qwen 2.5 32B backbone, focusing on high performance in math, coding and science. | 74 | 2025-09-09T19:21:49 | https://huggingface.co/LLM360/K2-Think | FullOf_Bad_Ideas | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ncsbro | false | null | t3_1ncsbro | /r/LocalLLaMA/comments/1ncsbro/mbzuai_releases_k2_think_32b_reasoning_model/ | false | false | default | 74 | {'enabled': False, 'images': [{'id': 'NguS7X1dxgvLZ8EclNqhJxD0a-4fPSDfz1-q527PukQ', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/NguS7X1dxgvLZ8EclNqhJxD0a-4fPSDfz1-q527PukQ.png?width=108&crop=smart&auto=webp&s=fb4ff053009ec7e97163d5655d4fc651b3ff7528', 'width': 108}, {'height': 116, 'url': 'h... | |
Autonomous, self-improving, domain specific AI agent | 0 | 2025-09-09T19:18:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ncs8xo/autonomous_selfimproving_domain_specific_ai_agent/ | metallicamax | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncs8xo | false | null | t3_1ncs8xo | /r/LocalLLaMA/comments/1ncs8xo/autonomous_selfimproving_domain_specific_ai_agent/ | false | false | 0 | null | ||
Kimi K2 0905 and repetition | 1 | Are there any suggested settings to avoid getting the same output repeated with this model? Just to be clear - I am testing it with NanoGPT because I don't have the hardware to run this model locally. I have the problem with repetition when I use the model in Claude Code. | 2025-09-09T19:18:18 | https://www.reddit.com/r/LocalLLaMA/comments/1ncs89p/kimi_k2_0905_and_repetition/ | Sky_Linx | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncs89p | false | null | t3_1ncs89p | /r/LocalLLaMA/comments/1ncs89p/kimi_k2_0905_and_repetition/ | false | false | self | 1 | null |
You're a builder who needs to use a forecasting model in your business (with zero ML experience) | 0 | Would you pay to gain the ability to create forecasting models?
**Examples:**
1. You’re building a airplane ticket booking platform, and want to offer users forecasts of when ticket prices will go up or down in the next 30 days.
2. You have a retail shop, and want to build an internal dashboard that forecasts how man... | 2025-09-09T19:00:01 | https://www.reddit.com/r/LocalLLaMA/comments/1ncrpyr/youre_a_builder_who_needs_to_use_a_forecasting/ | juanviera23 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncrpyr | false | null | t3_1ncrpyr | /r/LocalLLaMA/comments/1ncrpyr/youre_a_builder_who_needs_to_use_a_forecasting/ | false | false | self | 0 | null |
Intel Arc Pro B-Series GPUs and Xeon 6 Shine in MLPerf Inference v5.1 | 0 | 2025-09-09T18:55:42 | https://newsroom.intel.com/artificial-intelligence/intel-arc-pro-b-series-gpus-and-xeon-6-shine-in-mlperf-inference-v5-1 | reps_up | newsroom.intel.com | 1970-01-01T00:00:00 | 0 | {} | 1ncrlu5 | false | null | t3_1ncrlu5 | /r/LocalLLaMA/comments/1ncrlu5/intel_arc_pro_bseries_gpus_and_xeon_6_shine_in/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'l-cLEo5M7bRGOHHt-gvcMIKm1zFpTfeLtUkZ37rYPDE', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/l-cLEo5M7bRGOHHt-gvcMIKm1zFpTfeLtUkZ37rYPDE.png?width=108&crop=smart&auto=webp&s=b8a00f6f49015a73128ee82d6684b25d3853e7dc', 'width': 108}, {'height': 121, 'url': 'h... | |
science is the vibe-killer | 0 | Some critique on the vision and state of the technology
[https://remyxai.substack.com/p/vibes-dont-scale](https://remyxai.substack.com/p/vibes-dont-scale) | 2025-09-09T18:49:59 | remyxai | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncrg4n | false | null | t3_1ncrg4n | /r/LocalLLaMA/comments/1ncrg4n/science_is_the_vibekiller/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'tzwa5o2oq6of1', 'resolutions': [{'height': 87, 'url': 'https://preview.redd.it/tzwa5o2oq6of1.png?width=108&crop=smart&auto=webp&s=50939dbeec477148af0bc93b76d21a5df1349bb2', 'width': 108}, {'height': 175, 'url': 'https://preview.redd.it/tzwa5o2oq6of1.png?width=216&crop=smart&auto=web... | |
Apple on iPhone 17 Pro: "even more RAM for running local language models" | 0 | I caught during the Apple iPhone 17 Pro announcement: "even more RAM for running local language models". I've never seen them announce RAM as a spec on their website.
Personally, I think it will be a modest bump or else they would have talked more about it. Given Apple's trajectory of running AI on device, I can see... | 2025-09-09T18:30:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ncqxbi/apple_on_iphone_17_pro_even_more_ram_for_running/ | VFToken | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncqxbi | false | null | t3_1ncqxbi | /r/LocalLLaMA/comments/1ncqxbi/apple_on_iphone_17_pro_even_more_ram_for_running/ | false | false | self | 0 | null |
Web-Frontend with WebSearch capability & LDAP | 1 | Hello.
I am currently running three models via llama.cpp behind and proxy and two WebUI's: Perplexica & Open-WebUI.
The former frontend doesn't support user authentication (esp. via LDAP) and the latter is not very robust in terms of delayed responses.
Both frontends will stop showing LLM replies after the first web... | 2025-09-09T17:59:11 | https://www.reddit.com/r/LocalLLaMA/comments/1ncq1zb/webfrontend_with_websearch_capability_ldap/ | lnxdude | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncq1zb | false | null | t3_1ncq1zb | /r/LocalLLaMA/comments/1ncq1zb/webfrontend_with_websearch_capability_ldap/ | false | false | self | 1 | null |
Tensor Core Equivalent in the iPhone 17's A19 Pro | 41 | When this comes to Macs likely later this year or beginning of next year, this might patch up problem of the lack of compute on Macs for running LLMs, especially apparently with low prompt preprocessing speeds. | 2025-09-09T17:50:50 | Mysterious_Finish543 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncptut | false | null | t3_1ncptut | /r/LocalLLaMA/comments/1ncptut/tensor_core_equivalent_in_the_iphone_17s_a19_pro/ | false | false | default | 41 | {'enabled': True, 'images': [{'id': 'erdhiit5g6of1', 'resolutions': [{'height': 50, 'url': 'https://preview.redd.it/erdhiit5g6of1.png?width=108&crop=smart&auto=webp&s=5f93b681eea973ab9cc1610742b65d62c80cc41c', 'width': 108}, {'height': 100, 'url': 'https://preview.redd.it/erdhiit5g6of1.png?width=216&crop=smart&auto=web... | |
Apple adds matmul acceleration to A19 Pro GPU | 203 | This guarantees that it's coming to M5. | 2025-09-09T17:48:47 | https://www.reddit.com/r/LocalLLaMA/comments/1ncprrq/apple_adds_matmul_acceleration_to_a19_pro_gpu/ | auradragon1 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncprrq | false | null | t3_1ncprrq | /r/LocalLLaMA/comments/1ncprrq/apple_adds_matmul_acceleration_to_a19_pro_gpu/ | false | false | self | 203 | null |
Qwen 8B on locally on iPhone - 10 tokens/s | 13 | We have pushed what is possible on mobile devices!
Vector Space a project and app that explores what is possible for AI on iOS devices. We believe are very capable devices for AI and we wish to help fill the gap that some company is leaving out.
I am pleased to announce that we have fit Qwen 8B to run on iPhone. It ... | 2025-09-09T17:43:57 | https://v.redd.it/32o55chxe6of1 | Glad-Speaker3006 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncpn3v | false | {'reddit_video': {'bitrate_kbps': 2400, 'dash_url': 'https://v.redd.it/32o55chxe6of1/DASHPlaylist.mpd?a=1760031850%2CNTkyOWVkYjkzMGNhNzc3MjAwYTgwNGI1MDIzNWM3YjdlNTVhOWU2MDEwMzE4MzQ3NjljNDRiOWE2YTVkMmJkNA%3D%3D&v=1&f=sd', 'duration': 8, 'fallback_url': 'https://v.redd.it/32o55chxe6of1/DASH_720.mp4?source=fallback', 'has... | t3_1ncpn3v | /r/LocalLLaMA/comments/1ncpn3v/qwen_8b_on_locally_on_iphone_10_tokenss/ | false | false | 13 | {'enabled': False, 'images': [{'id': 'eXJjdTFsY3hlNm9mMTOl0IOQAgqwlCRxZAKRf2LxKM72dLj3tO8fplxlobs7', 'resolutions': [{'height': 152, 'url': 'https://external-preview.redd.it/eXJjdTFsY3hlNm9mMTOl0IOQAgqwlCRxZAKRf2LxKM72dLj3tO8fplxlobs7.png?width=108&crop=smart&format=pjpg&auto=webp&s=d2bc793e7d276c7ad9e3e50286d62861884b... | |
Combined REFRAG × SBD: Estimated Decode tok/s | 2 | REFRAG: https://arxiv.org/abs/2509.01092v1
SBD: https://arxiv.org/abs/2509.04185
tl;dr they are complimentary!
REFRAG (×3) and SBD — conservatively (×3.5) and aggressively (×5.0). So the combined multipliers are:
Conservative combo: 3 × 3.5 = 10.5×
Aggressive combo: 3 × 5.0 = 15×
| Model (quant) | Baseline ... | 2025-09-09T17:42:43 | https://www.reddit.com/r/LocalLLaMA/comments/1ncplx6/combined_refrag_sbd_estimated_decode_toks/ | Ok-Watercress3423 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncplx6 | false | null | t3_1ncplx6 | /r/LocalLLaMA/comments/1ncplx6/combined_refrag_sbd_estimated_decode_toks/ | false | false | self | 2 | null |
Internet Apocalypse - What would you fill in your 4TB storage? | 2 | For OS & other programs, you have separate 1TB Storage. 2nd Drive is 5TB Storage for archiving stuff. And System has 1TB RAM & 256GB VRAM(Yeah, before Apocalypse, people do crazy stuff like grabbing important stuffs so quick .... I would grab 15 MI50 32GB cards in my case :D ). Now you may fill **1TB with Non-LLM stuff... | 2025-09-09T17:42:16 | https://www.reddit.com/r/LocalLLaMA/comments/1ncplgy/internet_apocalypse_what_would_you_fill_in_your/ | pmttyji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncplgy | false | null | t3_1ncplgy | /r/LocalLLaMA/comments/1ncplgy/internet_apocalypse_what_would_you_fill_in_your/ | false | false | self | 2 | null |
Using vLLM for local use with Pipeline Parallelism and VLLM_PP_LAYER_PARTITION | 18 | Most of us default to llama.cpp or exllamav2/v3+tabbyapi because you can mix and match GPUs with different VRAM. You can do something similar with vLLM and keep its nice perks (new model support, tool use) by switching from tensor parallelism to pipeline parallelism and manually partitioning layers. It also has much be... | 2025-09-09T17:15:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ncovjy/using_vllm_for_local_use_with_pipeline/ | bullerwins | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncovjy | false | null | t3_1ncovjy | /r/LocalLLaMA/comments/1ncovjy/using_vllm_for_local_use_with_pipeline/ | false | false | self | 18 | {'enabled': False, 'images': [{'id': 'Zc8rbIYYFF4q61N85B9AfyAwBGHIqbU3UgTtGWJX9Rk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/Zc8rbIYYFF4q61N85B9AfyAwBGHIqbU3UgTtGWJX9Rk.png?width=108&crop=smart&auto=webp&s=4149a73436f8055cd9b22619186924902c278543', 'width': 108}, {'height': 108, 'url': 'h... |
Gigabyte’s New CXL Expansion Card Turns PCIe Slot into 512 GB of DDR5 RAM | 34 | Gigabyte's AI Top CXL R5X4 expansion card lets you plug up to 512 GB of DDR5 ECC RDIMM RAM into a PCIe 5.0 x16 slot, using Compute Express Link (CXL) to talk directly with the CPU.
While this technology is already old news for servers, now it's available for two workstation motherboards: TRX50 AI TOP (AMD) и W790 AI T... | 2025-09-09T17:14:00 | https://www.reddit.com/r/LocalLLaMA/comments/1ncou07/gigabytes_new_cxl_expansion_card_turns_pcie_slot/ | Normal-Ad-7114 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncou07 | false | null | t3_1ncou07 | /r/LocalLLaMA/comments/1ncou07/gigabytes_new_cxl_expansion_card_turns_pcie_slot/ | false | false | self | 34 | {'enabled': False, 'images': [{'id': 'VwmP5wMSgThbeJocnJEER0YuMHkGJpPYaAdPqeOEqyU', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/VwmP5wMSgThbeJocnJEER0YuMHkGJpPYaAdPqeOEqyU.jpeg?width=108&crop=smart&auto=webp&s=dfce854bdc24238e2ac676b6c60007ff81714c52', 'width': 108}, {'height': 121, 'url': '... |
64 GB AGX ORIN DEVELOPER VS. 16 GB Zed Box Orin NX | 2 | WHY IS MY ZED BOX RUNNING 3 GMSL2 CAMERAS FASTER THAN MY 64 GB AGX ORIN????
Through multiple testing instances and a large data base, I have found that my 16 GB zed box constantly runs at higher frames than my 64 GB AGX. I have no idea why this is, I am using a zed box deserializer for the AGX to read my gmsl2 cameras... | 2025-09-09T17:01:06 | https://www.reddit.com/r/LocalLLaMA/comments/1ncohk6/64_gb_agx_orin_developer_vs_16_gb_zed_box_orin_nx/ | InterestingBite7975 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncohk6 | false | null | t3_1ncohk6 | /r/LocalLLaMA/comments/1ncohk6/64_gb_agx_orin_developer_vs_16_gb_zed_box_orin_nx/ | false | false | self | 2 | null |
Switching to Qwen3-480B from Claude as resulted in lower errors when generating 3D model code | 66 | In my [previous](https://www.reddit.com/r/LocalLLaMA/comments/1n21tb6/comment/nb4h42v/) post I highlighted a Blender python agent I'm working on. I've been experimenting with various models and I found larger models like Claude and GPT-5 - even with reasoning - took too many iterations to produce working valid code.
... | 2025-09-09T16:33:35 | https://www.reddit.com/gallery/1ncnqwl | spacespacespapce | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ncnqwl | false | null | t3_1ncnqwl | /r/LocalLLaMA/comments/1ncnqwl/switching_to_qwen3480b_from_claude_as_resulted_in/ | false | false | 66 | null | |
What are some cool apps that get advantage of your local llm server by integrating it? | 4 | I’m not talking about server apps like ollama, lmstudio etc
Rather cool apps which give you service by using that local server of yours on your OS. | 2025-09-09T16:23:17 | https://www.reddit.com/r/LocalLLaMA/comments/1ncnh67/what_are_some_cool_apps_that_get_advantage_of/ | FatFigFresh | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncnh67 | false | null | t3_1ncnh67 | /r/LocalLLaMA/comments/1ncnh67/what_are_some_cool_apps_that_get_advantage_of/ | false | false | self | 4 | null |
My new hobby: test new release model with 'create wordle-like cli game in python' | 2 | Whenever new model released, I think everyone would have same set of prompt to testing it out.
My recently favorite is zero-shoting model with 'create wordle-like cli game in python'.
Wordle is quite a balance project here, it quite hard for beginner programmer to write and design a control flow, and it also challeng... | 2025-09-09T16:23:15 | https://www.reddit.com/r/LocalLLaMA/comments/1ncnh59/my_new_hobby_test_new_release_model_with_create/ | dheetoo | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncnh59 | false | null | t3_1ncnh59 | /r/LocalLLaMA/comments/1ncnh59/my_new_hobby_test_new_release_model_with_create/ | false | false | self | 2 | null |
Insights on performance degradation for Qwen3 30B3A? | 5 | Looking to use Qwen3-30B-A3B-Instruct-2507 with AWQ 4bit quant. Does anyone have insights in terms of performance degradation, specifically for long contexts? | 2025-09-09T16:10:21 | https://www.reddit.com/r/LocalLLaMA/comments/1ncn4sa/insights_on_performance_degradation_for_qwen3/ | Mr_Moonsilver | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncn4sa | false | null | t3_1ncn4sa | /r/LocalLLaMA/comments/1ncn4sa/insights_on_performance_degradation_for_qwen3/ | false | false | self | 5 | null |
ModernBERT just got multilingual - mmBERT by CLSP at The Johns Hopkins University | 36 | ModernBERT just got multilingual (mmBERT)
* Small (140M) and Base (307M) versions
* Trained on 3T+ tokens from 1800 languages (DCLM, FineWeb, Code ...)
* ModernBERT architecture, Gemma 2 tokenizer
* 8192 context window
[Model weights collection](https://huggingface.co/collections/jhu-clsp/mmbert-a-modern-multilingual... | 2025-09-09T15:43:00 | https://www.reddit.com/r/LocalLLaMA/comments/1ncme6t/modernbert_just_got_multilingual_mmbert_by_clsp/ | curiousily_ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncme6t | false | null | t3_1ncme6t | /r/LocalLLaMA/comments/1ncme6t/modernbert_just_got_multilingual_mmbert_by_clsp/ | false | false | self | 36 | {'enabled': False, 'images': [{'id': '1VZ52KHfX4U42PN2pKYH3SHOOOp0Ic8J9U2ywesfJjE', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/1VZ52KHfX4U42PN2pKYH3SHOOOp0Ic8J9U2ywesfJjE.png?width=108&crop=smart&auto=webp&s=7924d8ff4e119f9c734c2f49174b5e92273cb7e6', 'width': 108}, {'height': 116, 'url': 'h... |
My Experience with IndexTTS2 Deployment on Mac M4: Smooth Setup, Massive Memory Usage | 10 | The IndexTTS repository on GitHub has been updated, providing a complete deployment process for IndexTTS2: [https://github.com/index-tts/index-tts](https://github.com/index-tts/index-tts)
You can check the demo samples here: [https://index-tts.github.io/index-tts2.github.io/](https://index-tts.github.io/index-tts2.git... | 2025-09-09T15:36:22 | https://www.reddit.com/r/LocalLLaMA/comments/1ncm7xp/my_experience_with_indextts2_deployment_on_mac_m4/ | Timely_Rain_9284 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncm7xp | false | null | t3_1ncm7xp | /r/LocalLLaMA/comments/1ncm7xp/my_experience_with_indextts2_deployment_on_mac_m4/ | false | false | self | 10 | null |
Having difficulties starting my llama.cpp API server; all I find is Ollama tutorials | 3 | As stated, I try to find tutorials but Google keeps thinking I want to play with Ollama and auto corrects me and gives me bad info. I want to pull the got 20b and also a good 3-4b to just read an ad and evaluate if it concerns a certain subject or not to eliminate it. | 2025-09-09T15:28:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ncm031/having_difficulties_starting_my_llamacpp_api/ | oodelay | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ncm031 | false | null | t3_1ncm031 | /r/LocalLLaMA/comments/1ncm031/having_difficulties_starting_my_llamacpp_api/ | false | false | self | 3 | null |
NLQuery: On-premise, high-performance Text-to-SQL engine for PostgreSQL with single REST API endpoint | 5 | MBASE NLQuery is a natural language to SQL generator/executor engine using the MBASE SDK as an LLM SDK. This project doesn't use cloud based LLMs
It internally uses the Qwen2.5-7B-Instruct-NLQuery model to convert the provided natural language into SQL queries and executes it through the database client SDKs (PostgreS... | 2025-09-09T15:12:32 | https://www.reddit.com/r/LocalLLaMA/comments/1nclld9/nlquery_onpremise_highperformance_texttosql/ | Emrehocam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nclld9 | false | null | t3_1nclld9 | /r/LocalLLaMA/comments/1nclld9/nlquery_onpremise_highperformance_texttosql/ | false | false | self | 5 | null |
mmBERT: ModernBERT goes Multilingual | 51 | Looks like some of the ModernBERT authors trained a Multilingual variant! Also 2 models, but these are a bit smaller. They look really promising to be honest, although they do clearly need to be finetuned for downstream tasks like semantic search, clustering, classification, etc. before they're really viable. A bit lik... | 2025-09-09T14:58:03 | https://huggingface.co/blog/mmbert | -Cubie- | huggingface.co | 1970-01-01T00:00:00 | 0 | {} | 1ncl7mx | false | null | t3_1ncl7mx | /r/LocalLLaMA/comments/1ncl7mx/mmbert_modernbert_goes_multilingual/ | false | false | default | 51 | {'enabled': False, 'images': [{'id': 'gboHy7lwIiGjTkUdwnm7iBTxH9k6Eb0rVhAuSbpxTno', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/gboHy7lwIiGjTkUdwnm7iBTxH9k6Eb0rVhAuSbpxTno.png?width=108&crop=smart&auto=webp&s=fd2319b16053ccf534f119ac51c988a8afb98ba3', 'width': 108}, {'height': 112, 'url': 'h... |
🤔 | 569 | 2025-09-09T14:50:44 | Namra_7 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ncl0v1 | false | null | t3_1ncl0v1 | /r/LocalLLaMA/comments/1ncl0v1/_/ | false | false | default | 569 | {'enabled': True, 'images': [{'id': '1x8wy1p0k5of1', 'resolutions': [{'height': 71, 'url': 'https://preview.redd.it/1x8wy1p0k5of1.png?width=108&crop=smart&auto=webp&s=8cbd3c782451139141dd02e06e09e3673913d468', 'width': 108}, {'height': 143, 'url': 'https://preview.redd.it/1x8wy1p0k5of1.png?width=216&crop=smart&auto=web... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.