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 ⌀ |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Decent local models that run with 32 GB VRAM (5090) with 64 GB RAM at a good speed? | 4 | Been messing around local models since I am annoyed with the rate limits of claude code, any good models which run decently? Tried gpt-oss 20B but it was getting stuck into an endless loop when the code repo complexity was getting larger. Currently running everything with a llama.cpp server with Cline.
Haven't tried ... | 2025-10-04T23:52:32 | https://www.reddit.com/r/LocalLLaMA/comments/1ny9ds3/decent_local_models_that_run_with_32_gb_vram_5090/ | rulerofthehell | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny9ds3 | false | null | t3_1ny9ds3 | /r/LocalLLaMA/comments/1ny9ds3/decent_local_models_that_run_with_32_gb_vram_5090/ | false | false | self | 4 | null |
Running Qwen3-VL-30B locally with 48GB VRAM: 90 t/s | 1 | [removed] | 2025-10-04T23:49:59 | https://www.reddit.com/r/LocalLLaMA/comments/1ny9bup/running_qwen3vl30b_locally_with_48gb_vram_90_ts/ | slavik-dev | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny9bup | false | null | t3_1ny9bup | /r/LocalLLaMA/comments/1ny9bup/running_qwen3vl30b_locally_with_48gb_vram_90_ts/ | false | false | self | 1 | null |
Qwen3-VL-30B-A3B-Instruct ~= Qwen2.5-VL-72B | 13 | qwen3-vl-30b is obviously smaller and should be faster. there's no gguf model yet, so for me it's taking 60+GB of vram. I'm running the 72b gguf Q8 and having to use transformers to run qwen3 and qwen3 feels/runs slower. Running the 30b-a3b on quad 3090s and 72b on mix of P40/P100/3060 and yet 72b is faster. 72b ... | 2025-10-04T23:24:27 | https://www.reddit.com/r/LocalLLaMA/comments/1ny8s1r/qwen3vl30ba3binstruct_qwen25vl72b/ | segmond | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny8s1r | false | null | t3_1ny8s1r | /r/LocalLLaMA/comments/1ny8s1r/qwen3vl30ba3binstruct_qwen25vl72b/ | false | false | self | 13 | null |
Testing some language models on NPU | 4 | I got my hand on a (kinda) -china exclusive- sbc the OPI ai pro 20T
it can give 20 TOPS @ int8 precision (i have the 24g ram)
and this board actually has an NPU (Ascend310) i was able to run Qwen 2.5 & 3 (3B half precision was kinda slow but acceptable)
my ultimate goal is to deploy some quantized models + whisper ti... | 2025-10-04T22:45:53 | overflow74 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ny7wwz | false | null | t3_1ny7wwz | /r/LocalLLaMA/comments/1ny7wwz/testing_some_language_models_on_npu/ | false | false | default | 4 | {'enabled': True, 'images': [{'id': 'e0wxt77lb6tf1', 'resolutions': [{'height': 37, 'url': 'https://preview.redd.it/e0wxt77lb6tf1.jpeg?width=108&crop=smart&auto=webp&s=ec6f7348d7c52e6260be8dabe49e1d73badb2fa1', 'width': 108}, {'height': 74, 'url': 'https://preview.redd.it/e0wxt77lb6tf1.jpeg?width=216&crop=smart&auto=we... | |
Desktop app for running local LLMs | 1 | Hi everyone — I’m the developer of this project and wanted to share.
It can:
* Run any LLM locally through **Ollama**
* Perform **multi-step Deep Research** with citations
* **Auto-organize folders** and manage files in seconds
* **Open and close applications** directly from the interface
* Customize **reasoning mode... | 2025-10-04T22:29:24 | https://www.reddit.com/r/LocalLLaMA/comments/1ny7j8g/desktop_app_for_running_local_llms/ | KatAssistant | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny7j8g | false | null | t3_1ny7j8g | /r/LocalLLaMA/comments/1ny7j8g/desktop_app_for_running_local_llms/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': '0FY5uCTKTIpROi6ujHnKcj_DWkkQc_-Hu_NmzgGvcdU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/0FY5uCTKTIpROi6ujHnKcj_DWkkQc_-Hu_NmzgGvcdU.png?width=108&crop=smart&auto=webp&s=a51ab12d8e8862d3817141081110be0be9c699db', 'width': 108}, {'height': 108, 'url': 'h... |
Working on an academic AI project for CV screening — looking for advice | 0 | Hey everyone,
I’m doing an academic project around **AI for recruitment**, and I’d love some feedback or ideas for improvement.
The goal is to build a project that can **analyze CVs (PDFs)**, extract key info (skills, experience, education), and **match them with a job description** to give a simple, **explainable ra... | 2025-10-04T22:19:47 | https://www.reddit.com/r/LocalLLaMA/comments/1ny7b4a/working_on_an_academic_ai_project_for_cv/ | Particular_Cake4359 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny7b4a | false | null | t3_1ny7b4a | /r/LocalLLaMA/comments/1ny7b4a/working_on_an_academic_ai_project_for_cv/ | false | false | self | 0 | null |
is the DGX Spark a valid option? | 0 | Just curious.. given the $3K "alleged" price tag of OEMs (not founders).. 144GB HBM3e unified ram, tiny size and power use.. is it a viable solution to run (infer) GLM4.6, DeepSeekR2, etc? Thinkin 2 of them (since it supprots NV Link) for $6K or so would be a pretty powerful setup with 250+GB or VRAM between them. Port... | 2025-10-04T22:03:50 | https://www.reddit.com/r/LocalLLaMA/comments/1ny6xio/is_the_dgx_spark_a_valid_option/ | Conscious-Fee7844 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny6xio | false | null | t3_1ny6xio | /r/LocalLLaMA/comments/1ny6xio/is_the_dgx_spark_a_valid_option/ | false | false | self | 0 | null |
Someone said janky? | 54 | Longtime lurker here. Seems to be posts of janky rigs today. Please enjoy. | 2025-10-04T21:40:18 | https://www.reddit.com/gallery/1ny6dep | omg__itsFullOfStars | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1ny6dep | false | null | t3_1ny6dep | /r/LocalLLaMA/comments/1ny6dep/someone_said_janky/ | false | false | 54 | null | |
need help getting one file in order to install an ai image generator | 1 | to make comfyui work i need a specific file that i can't find a download of; does anyone with a working installation have a filed named "clip-vit-l-14.safetensors" if you do please upload it; i can't find the thing anywhere; and i've checked in a lot of places; my installation of it needs this file badly | 2025-10-04T21:39:09 | https://www.reddit.com/r/LocalLLaMA/comments/1ny6cfc/need_help_getting_one_file_in_order_to_install_an/ | GanacheConfident6576 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny6cfc | false | null | t3_1ny6cfc | /r/LocalLLaMA/comments/1ny6cfc/need_help_getting_one_file_in_order_to_install_an/ | false | false | self | 1 | null |
Tutorial: Matrix Core Programming on AMD GPUs | 1 | Hi all,
I wanted to share my new tutorial on programming Matrix Cores in HIP. The blog post is very educational and contains necessary knowledge to start programming Matrix Cores, covering modern low-precision floating-point types, the Matrix Core compiler intrinsics, and the data layouts required by the Matrix Core i... | 2025-10-04T21:20:49 | salykova_ | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ny5wj2 | false | null | t3_1ny5wj2 | /r/LocalLLaMA/comments/1ny5wj2/tutorial_matrix_core_programming_on_amd_gpus/ | false | false | default | 1 | {'enabled': True, 'images': [{'id': 'gid62c0ew5tf1', 'resolutions': [{'height': 92, 'url': 'https://preview.redd.it/gid62c0ew5tf1.jpeg?width=108&crop=smart&auto=webp&s=8cc67af331f30a5b0e11374aa37a7820542b53ec', 'width': 108}, {'height': 184, 'url': 'https://preview.redd.it/gid62c0ew5tf1.jpeg?width=216&crop=smart&auto=w... | |
Tutorial: Matrix Core Programming on AMD GPUs | 1 | [deleted] | 2025-10-04T21:19:48 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1ny5vkh | false | null | t3_1ny5vkh | /r/LocalLLaMA/comments/1ny5vkh/tutorial_matrix_core_programming_on_amd_gpus/ | false | false | default | 1 | null | ||
What happens if AI agents start trusting everything they read? (I ran a test.) | 0 | I ran a controlled experiment where an AI agent followed hidden instructions inside a doc and made destructive repo changes. Don’t worry — it was a lab test and I’m not sharing how to do it. My question: who should be responsible — the AI vendor, the company deploying agents, or security teams? Why? | 2025-10-04T20:48:00 | https://www.reddit.com/r/LocalLLaMA/comments/1ny5345/what_happens_if_ai_agents_start_trusting/ | AIMadeMeDoIt__ | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny5345 | false | null | t3_1ny5345 | /r/LocalLLaMA/comments/1ny5345/what_happens_if_ai_agents_start_trusting/ | false | false | self | 0 | null |
Replacing my need for Anthropic and OpenAI with my current hardware possible? | 0 | I just bought what I thought was beast hardware: rtx 5090, ultra 9 285k and 128 gb of ram. To my disappointment, I can't run the best models out there without quantization. If I had known earlier, I would have waited more for the hardware to catch up. I guess my goal is to replace my dependency of ChatGPT, Claude Code,... | 2025-10-04T20:44:03 | https://www.reddit.com/r/LocalLLaMA/comments/1ny4zi9/replacing_my_need_for_anthropic_and_openai_with/ | alienz225 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny4zi9 | false | null | t3_1ny4zi9 | /r/LocalLLaMA/comments/1ny4zi9/replacing_my_need_for_anthropic_and_openai_with/ | false | false | self | 0 | null |
Windows App/GUI for MLX, vLLM models? | 2 | For GGUF, we have so many Open source GUIs to run models great. I'm looking for Windows App/GUI for MLX & vLLM models. Even WebUI fine. Command line also fine(Recently started learning llama.cpp). Non-Docker would be great. I'm fine if it's not pure Open source in worst case.
The reason for this is I heard that MLX, v... | 2025-10-04T20:09:14 | https://www.reddit.com/r/LocalLLaMA/comments/1ny447i/windows_appgui_for_mlx_vllm_models/ | pmttyji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny447i | false | null | t3_1ny447i | /r/LocalLLaMA/comments/1ny447i/windows_appgui_for_mlx_vllm_models/ | false | false | self | 2 | null |
Alternatives to Ollama? | 0 | I'm a little tired of Ollama's management. I've read that they've stopped supporting some AMD GPUs that recently received a power-up from Llama.cpp, and I'd like to prepare for a future change.
I don't know if there is some kind of wrapper on top of Llama.cpp that offers the same ease of use as Ollama, with the same e... | 2025-10-04T20:04:45 | https://www.reddit.com/r/LocalLLaMA/comments/1ny408v/alternatives_to_ollama/ | vk3r | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny408v | false | null | t3_1ny408v | /r/LocalLLaMA/comments/1ny408v/alternatives_to_ollama/ | false | false | self | 0 | null |
Best model for NSFW creative writing? | 0 | What is the best LLM for NSFW creative writing? | 2025-10-04T19:49:12 | https://www.reddit.com/r/LocalLLaMA/comments/1ny3mg1/best_model_for_nsfw_creative_writing/ | Time-Teaching1926 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny3mg1 | false | null | t3_1ny3mg1 | /r/LocalLLaMA/comments/1ny3mg1/best_model_for_nsfw_creative_writing/ | false | false | nsfw | 0 | null |
GLM-4.6 Tip: How to Control Output Quality via Thinking | 39 | You can control the output quality of GLM-4.6 by influencing the thinking process through your prompt.
You can suppress the thinking process by appending `</think>` at the end of your prompt. GLM-4.6 will then respond directly, but with the lowest output quality.
Conversely, you can ramp up the thinking process and s... | 2025-10-04T19:42:22 | https://www.reddit.com/r/LocalLLaMA/comments/1ny3gfb/glm46_tip_how_to_control_output_quality_via/ | Snail_Inference | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny3gfb | false | null | t3_1ny3gfb | /r/LocalLLaMA/comments/1ny3gfb/glm46_tip_how_to_control_output_quality_via/ | false | false | self | 39 | null |
Gemini 3.0 & Deepseek R2 | 12 | I think the last big 2 models to come out this year or early next year will be the king of closed source LLM's Gemini 3.0 and the king of open sourced LLM's Deepseek R2.
Are you all excited? | 2025-10-04T19:28:38 | https://www.reddit.com/r/LocalLLaMA/comments/1ny33x8/gemini_30_deepseek_r2/ | Time-Teaching1926 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny33x8 | false | null | t3_1ny33x8 | /r/LocalLLaMA/comments/1ny33x8/gemini_30_deepseek_r2/ | false | false | self | 12 | null |
New Build for local LLM | 187 | Mac Studio M3 Ultra 512GB RAM 4TB HDD desktop
96core threadripper, 512GB RAM, 4x RTX Pro 6000 Max Q (all at 5.0x16), 16TB 60GBps Raid 0 NVMe
Thanks for all the help getting parts selected, getting it booted, and built! It's finally together thanks to the help of the community (here and discord!)
Check out my cozy lit... | 2025-10-04T19:20:06 | chisleu | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ny2w2d | false | null | t3_1ny2w2d | /r/LocalLLaMA/comments/1ny2w2d/new_build_for_local_llm/ | false | false | default | 187 | {'enabled': True, 'images': [{'id': '3xz2zcko95tf1', 'resolutions': [{'height': 144, 'url': 'https://preview.redd.it/3xz2zcko95tf1.png?width=108&crop=smart&auto=webp&s=dc54bb3abe3a1606b69c16d5661c5221721a9da1', 'width': 108}, {'height': 288, 'url': 'https://preview.redd.it/3xz2zcko95tf1.png?width=216&crop=smart&auto=we... | |
Any good local alternatives to Claude? | 1 | Disclaimer: I understand some programming but I am not a programmer.
Note: I have a 5090 & 64GB Ram.
Never used Claude until last night. I was fighting ChatGPT for hours on some simple Python code (specifically RenPy). You know the typical, try this same thing over-and-over loop.
Claude solved my problem in about... | 2025-10-04T19:12:18 | https://www.reddit.com/r/LocalLLaMA/comments/1ny2ot3/any_good_local_alternatives_to_claude/ | BenefitOfTheDoubt_01 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny2ot3 | false | null | t3_1ny2ot3 | /r/LocalLLaMA/comments/1ny2ot3/any_good_local_alternatives_to_claude/ | false | false | self | 1 | null |
Any resources on how to prepare data for fine tuning? | 6 | Dear tech wizards of LocalLLama,
I own a M3 Max 36 gb and have experience running inference on local models using OpenwebUI and Ollama. I want to get some hands in experience with fine tuning And am looking for resources for fine tuning data prep.
For the tech stack, i decided to use MLX since I want to do everything... | 2025-10-04T18:44:25 | https://www.reddit.com/r/LocalLLaMA/comments/1ny1z91/any_resources_on_how_to_prepare_data_for_fine/ | SoggyClue | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny1z91 | false | null | t3_1ny1z91 | /r/LocalLLaMA/comments/1ny1z91/any_resources_on_how_to_prepare_data_for_fine/ | false | false | self | 6 | null |
What are some repetitive text patterns you see a lot from your AI? | 0 | Just curious what comes up the most from you, if anything. | 2025-10-04T18:41:53 | https://www.reddit.com/r/LocalLLaMA/comments/1ny1wzr/what_are_some_repetitive_text_patterns_you_see_a/ | XiRw | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny1wzr | false | null | t3_1ny1wzr | /r/LocalLLaMA/comments/1ny1wzr/what_are_some_repetitive_text_patterns_you_see_a/ | false | false | self | 0 | null |
Qwen3-VL-30B-A3B-Instruct & Thinking are here! | 182 | Also releasing an FP8 version, plus the FP8 of the massive Qwen3-VL-235B-A22B! | 2025-10-04T18:40:35 | Full_Piano_3448 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ny1vrt | false | null | t3_1ny1vrt | /r/LocalLLaMA/comments/1ny1vrt/qwen3vl30ba3binstruct_thinking_are_here/ | false | false | 182 | {'enabled': True, 'images': [{'id': 'NQdxBGNuYRDrUfBYGgIpi1zlCloNSwZod_Gaw5T6gCM', 'resolutions': [{'height': 147, 'url': 'https://preview.redd.it/bx7mh9pr35tf1.png?width=108&crop=smart&auto=webp&s=12c40a1dee688277334c34b2cd742c6c8f730eeb', 'width': 108}, {'height': 295, 'url': 'https://preview.redd.it/bx7mh9pr35tf1.pn... | ||
Need help and resources to learn on how to run LLMs locally on PC and phones and build AI Apps | 1 | I could not find any proper resources to learn on how to run llms locally ( youtube medium and github ) if someone knows or has any links that could help me i can also start my journey in this sub. | 2025-10-04T18:36:34 | https://www.reddit.com/r/LocalLLaMA/comments/1ny1s4g/need_help_and_resources_to_learn_on_how_to_run/ | Mysterious_Local9395 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny1s4g | false | null | t3_1ny1s4g | /r/LocalLLaMA/comments/1ny1s4g/need_help_and_resources_to_learn_on_how_to_run/ | false | false | self | 1 | null |
Any quality ios chat with custom models? | 0 | Does anyone know if such a thing exists? I would happily pay one-time fee for it and use my home api. | 2025-10-04T18:22:13 | https://www.reddit.com/r/LocalLLaMA/comments/1ny1ess/any_quality_ios_chat_with_custom_models/ | shaman-warrior | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny1ess | false | null | t3_1ny1ess | /r/LocalLLaMA/comments/1ny1ess/any_quality_ios_chat_with_custom_models/ | false | false | self | 0 | null |
Launch Your SaaS Faster: The Founderflow Next.js Boilerplate is Here! | 0 | [removed] | 2025-10-04T17:54:04 | https://www.reddit.com/r/LocalLLaMA/comments/1ny0of2/launch_your_saas_faster_the_founderflow_nextjs/ | Old-Baker-2300 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny0of2 | false | null | t3_1ny0of2 | /r/LocalLLaMA/comments/1ny0of2/launch_your_saas_faster_the_founderflow_nextjs/ | false | false | self | 0 | null |
Launch Your SaaS Faster: The Founderflow Next.js Boilerplate is Here! | 1 | [removed] | 2025-10-04T17:53:16 | [deleted] | 1970-01-01T00:00:00 | 0 | {} | 1ny0no6 | false | null | t3_1ny0no6 | /r/LocalLLaMA/comments/1ny0no6/launch_your_saas_faster_the_founderflow_nextjs/ | true | false | default | 1 | null | ||
Launch Your SaaS Faster: The Founderflow Next.js Boilerplate is Here! | 1 | [removed] | 2025-10-04T17:52:27 | https://www.reddit.com/r/LocalLLaMA/comments/1ny0myj/launch_your_saas_faster_the_founderflow_nextjs/ | Old-Baker-2300 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1ny0myj | false | null | t3_1ny0myj | /r/LocalLLaMA/comments/1ny0myj/launch_your_saas_faster_the_founderflow_nextjs/ | false | false | 1 | null | |
Open source text-to-image Hunyuan 3.0 by Tencent is now #1 in LMArena, Beating proprietary models like Nano Banana and SeeDream 4 for the first time | 125 | 2025-10-04T17:29:59 | abdouhlili | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1ny022j | false | null | t3_1ny022j | /r/LocalLLaMA/comments/1ny022j/open_source_texttoimage_hunyuan_30_by_tencent_is/ | false | false | default | 125 | {'enabled': True, 'images': [{'id': 'whxcmf68r4tf1', 'resolutions': [{'height': 86, 'url': 'https://preview.redd.it/whxcmf68r4tf1.jpeg?width=108&crop=smart&auto=webp&s=6a67317a3db99b7b5f8fe32c3ed04534aaf685a7', 'width': 108}, {'height': 172, 'url': 'https://preview.redd.it/whxcmf68r4tf1.jpeg?width=216&crop=smart&auto=w... | ||
GPT-1 Thinking 2.6m coming soon | 665 | Took my GPT-1 from past posts, gave it roughly 600 million tokens from Nemotron's pretraining dataset.
Then finetuned it on my own private thinking dataset, used sonnet 4.5 to help me come up with it, essentially to help the model 'see' the pattern of the thinking rather than just random q/a with thinking in it. ... | 2025-10-04T17:24:39 | Creative-Ad-2112 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxzx6t | false | null | t3_1nxzx6t | /r/LocalLLaMA/comments/1nxzx6t/gpt1_thinking_26m_coming_soon/ | false | false | default | 665 | {'enabled': True, 'images': [{'id': '2ln0mw87m4tf1', 'resolutions': [{'height': 81, 'url': 'https://preview.redd.it/2ln0mw87m4tf1.png?width=108&crop=smart&auto=webp&s=f958b76416630742973c69f65c8e32b911bd9ae5', 'width': 108}, {'height': 162, 'url': 'https://preview.redd.it/2ln0mw87m4tf1.png?width=216&crop=smart&auto=web... | |
gpt-oss 120B is running at 20t/s with $500 AMD M780 iGPU mini PC and 96GB DDR5 RAM | 340 | Everyone here is talking about how great AMD Ryzen AI MAX+ 395 128GB is. But mini PCs with those specs cost almost $2k. I agree the specs are amazing but the price is way high for most local LLM users. I wondered if there was any alternative. My primary purpose was to run gpt-oss 120B at readable speeds.
I searched f... | 2025-10-04T17:20:52 | https://www.reddit.com/r/LocalLLaMA/comments/1nxztlx/gptoss_120b_is_running_at_20ts_with_500_amd_m780/ | MLDataScientist | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxztlx | false | null | t3_1nxztlx | /r/LocalLLaMA/comments/1nxztlx/gptoss_120b_is_running_at_20ts_with_500_amd_m780/ | false | false | self | 340 | null |
Belly dance | 0 | A 26-year-old Arabian belly dancer with a bold and confident personality performs mesmerizing belly dance moves in the middle of a golden desert at sunset. She wears flowing, colorful clothing with shimmering fabrics that are slightly transparent, accentuating her beauty and grace. Her costume sparkles with golden orna... | 2025-10-04T17:02:24 | Alert-Afternoon-2894 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxzcsu | false | null | t3_1nxzcsu | /r/LocalLLaMA/comments/1nxzcsu/belly_dance/ | true | false | nsfw | 0 | {'enabled': True, 'images': [{'id': 'fm1wm79yl4tf1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/fm1wm79yl4tf1.jpeg?width=108&crop=smart&auto=webp&s=e0b4713d9054eca177f6c02a21363c5191d2bb69', 'width': 108}, {'height': 120, 'url': 'https://preview.redd.it/fm1wm79yl4tf1.jpeg?width=216&crop=smart&auto=w... | |
What model do you think this website uses? | 3 | Hello.
I've found this website [suno-ai.me](http://suno-ai.me/) and it generates really good sounds.
But i doubt they trained their own model, based on how the website looks, it's a free model from huggingface that they charge money for. In the footer they have a backlink to "Incredibox Sprunki Music Games" that says... | 2025-10-04T17:00:28 | https://www.reddit.com/r/LocalLLaMA/comments/1nxzaw4/what_model_do_you_think_this_website_uses/ | MrPulifrici | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxzaw4 | false | null | t3_1nxzaw4 | /r/LocalLLaMA/comments/1nxzaw4/what_model_do_you_think_this_website_uses/ | false | false | self | 3 | null |
My janky way of getting 2 GPUs into my rig | 19 | I had forgotten I had a second power supply from when I upgraded my rig, and realized that I had a second GPU that I had upgraded from. RX 6800 16GB. so I bought a tool to make it possible to use both power supplies, and it’s working fine in LM Studio. Now to try it in Ollama. And if I have to, cool is next | 2025-10-04T16:43:54 | https://www.reddit.com/gallery/1nxyw0a | Savantskie1 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nxyw0a | false | null | t3_1nxyw0a | /r/LocalLLaMA/comments/1nxyw0a/my_janky_way_of_getting_2_gpus_into_my_rig/ | false | false | 19 | null | |
Hi there , is anyone know a opensource GUI github that is like chatgpt with login and payment system with vector database , means a GUI in which we can connect our own pdfs , also in tool and mcp ! | 0 | Hi there , is anyone know a opensource GUI github that is like chatgpt with login and payment system with vector database , means a GUI in which we can connect our own pdfs , also in tool and mcp !
as we are thinking to launch a SaaS same like chatgpt but for a specific purpose so need a GUI in which we can just ad... | 2025-10-04T16:35:23 | https://www.reddit.com/r/LocalLLaMA/comments/1nxyo81/hi_there_is_anyone_know_a_opensource_gui_github/ | ZealousidealRide7425 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxyo81 | false | null | t3_1nxyo81 | /r/LocalLLaMA/comments/1nxyo81/hi_there_is_anyone_know_a_opensource_gui_github/ | false | false | self | 0 | null |
What are the best models for legal work in Oct 2025? | 5 | TLDR: I've been experimenting with models from the 20b-120b range recently and I found that if you can reliably get past the censorship issues, the gpt-oss models do seem to be the best for (English language) legal work. Would be great to hear some thoughts.
By "legal work' I mean
- instruction following in focused ... | 2025-10-04T16:26:12 | https://www.reddit.com/r/LocalLLaMA/comments/1nxyfwr/what_are_the_best_models_for_legal_work_in_oct/ | yuch85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxyfwr | false | null | t3_1nxyfwr | /r/LocalLLaMA/comments/1nxyfwr/what_are_the_best_models_for_legal_work_in_oct/ | false | false | self | 5 | null |
HP Launches ZGX Nano G1n AI Workstation, Powered By NVIDIA's GB10 Superchip | 9 | 2025-10-04T16:03:17 | https://wccftech.com/hp-launches-zgx-nano-g1n-ai-workstation-powered-by-nvidias-gb10-superchip/ | _SYSTEM_ADMIN_MOD_ | wccftech.com | 1970-01-01T00:00:00 | 0 | {} | 1nxxvcz | false | null | t3_1nxxvcz | /r/LocalLLaMA/comments/1nxxvcz/hp_launches_zgx_nano_g1n_ai_workstation_powered/ | false | false | default | 9 | {'enabled': False, 'images': [{'id': 'nYf-wHbI5uSDELNJEC2OhUyjUThzYznosmkFXGXT1PQ', 'resolutions': [{'height': 65, 'url': 'https://external-preview.redd.it/nYf-wHbI5uSDELNJEC2OhUyjUThzYznosmkFXGXT1PQ.jpeg?width=108&crop=smart&auto=webp&s=8c8ba1994f6eee1480be1b27639b1120bcd01537', 'width': 108}, {'height': 130, 'url': '... | |
Why are AI labs in China not focused on creating new search engines? | 536 | 2025-10-04T15:45:31 | balianone | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxxeu1 | false | null | t3_1nxxeu1 | /r/LocalLLaMA/comments/1nxxeu1/why_are_ai_labs_in_china_not_focused_on_creating/ | false | false | default | 536 | {'enabled': True, 'images': [{'id': '4glawt4k84tf1', 'resolutions': [{'height': 186, 'url': 'https://preview.redd.it/4glawt4k84tf1.jpeg?width=108&crop=smart&auto=webp&s=fbba2c5925ef9b58bd929331a9141f9180a5e2ca', 'width': 108}, {'height': 372, 'url': 'https://preview.redd.it/4glawt4k84tf1.jpeg?width=216&crop=smart&auto=... | ||
My mildly janky setup | 74 | 2025-10-04T15:39:59 | https://www.reddit.com/gallery/1nxx9r9 | sergeysi | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nxx9r9 | false | null | t3_1nxx9r9 | /r/LocalLLaMA/comments/1nxx9r9/my_mildly_janky_setup/ | false | false | 74 | null | ||
Which Open-Source / Local LLMs work best for Offensive Security? + What Hardware Setup Is Realistic? | 3 | >Hey folks I’m looking to build a **local offensive security / red teaming assistant** using LLMs.
>I want it to help me with things like:
>• Recon / enumeration / vuln search
>• Generating exploit ideas or testing code
>• Post-exploitation scripts, privilege escalation, etc.
>• Ideally some chaining of tasks + me... | 2025-10-04T15:27:40 | https://www.reddit.com/r/LocalLLaMA/comments/1nxwykv/which_opensource_local_llms_work_best_for/ | NoobMaster048 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxwykv | false | null | t3_1nxwykv | /r/LocalLLaMA/comments/1nxwykv/which_opensource_local_llms_work_best_for/ | false | false | self | 3 | null |
How to enable powerful RAG, caching powers, full swe styled loops to my agent? And what llm it should back by ? Oss120b/20b or any other i personally liked nemotron 9b v2 but consider me a noob in this particular field | 0 | Please answer me with your real expertise and upvote or share this to get me great answers, i want Ai agent in my laptop that will do too much great coding uses internet via multiple MCPs. | 2025-10-04T15:22:22 | https://www.reddit.com/r/LocalLLaMA/comments/1nxwtt1/how_to_enable_powerful_rag_caching_powers_full/ | AccomplishedBoss7738 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxwtt1 | false | null | t3_1nxwtt1 | /r/LocalLLaMA/comments/1nxwtt1/how_to_enable_powerful_rag_caching_powers_full/ | false | false | self | 0 | null |
Quite accurate | 992 | 2025-10-04T14:50:10 | Komarov_d | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxw08b | false | null | t3_1nxw08b | /r/LocalLLaMA/comments/1nxw08b/quite_accurate/ | false | false | default | 992 | {'enabled': True, 'images': [{'id': '9lms1idpy3tf1', 'resolutions': [{'height': 39, 'url': 'https://preview.redd.it/9lms1idpy3tf1.jpeg?width=108&crop=smart&auto=webp&s=1078e346423894eb1627c81b91d2cc98732d8d5f', 'width': 108}, {'height': 79, 'url': 'https://preview.redd.it/9lms1idpy3tf1.jpeg?width=216&crop=smart&auto=we... | ||
Comparison between Qwen-Image, HunyuanImage 2.1, HunyuanImage 3.0 | 31 | Couple of days ago i asked about the difference between the archticture in HunyuanImage 2.1 and HunyuanImage 3.0 and which is better and as you may have geussed nobody helped me. so, i decided to compare between the three myself and this is the results i got.
https://preview.redd.it/1w6bgzguu3tf1.png?width=1355&format... | 2025-10-04T14:33:52 | https://www.reddit.com/r/LocalLLaMA/comments/1nxvlm8/comparison_between_qwenimage_hunyuanimage_21/ | Severe-Awareness829 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxvlm8 | false | null | t3_1nxvlm8 | /r/LocalLLaMA/comments/1nxvlm8/comparison_between_qwenimage_hunyuanimage_21/ | false | false | 31 | null | |
Performance of GLM 4.6 Q3_K_S on 6x MI50 | 45 | Last night I downloaded the latest GLM 4.6 GGUFs from [unsloth/GLM-4.6-GGUF · Hugging Face](https://huggingface.co/unsloth/GLM-4.6-GGUF). I chose Q3\_K\_S since it was the best size allowing for full context on six AMD Instinct MI50 32gb (192gb). I also took the opportunity to download and rebuild the latest llama.cpp.... | 2025-10-04T14:18:58 | https://www.reddit.com/r/LocalLLaMA/comments/1nxv7x6/performance_of_glm_46_q3_k_s_on_6x_mi50/ | MachineZer0 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxv7x6 | false | null | t3_1nxv7x6 | /r/LocalLLaMA/comments/1nxv7x6/performance_of_glm_46_q3_k_s_on_6x_mi50/ | false | false | 45 | {'enabled': False, 'images': [{'id': 'JsfroVEhCwDAyGkCRZ2-n87DtLempLcI758DM9LAUaU', 'resolutions': [{'height': 58, 'url': 'https://external-preview.redd.it/JsfroVEhCwDAyGkCRZ2-n87DtLempLcI758DM9LAUaU.png?width=108&crop=smart&auto=webp&s=cd157f4ac67e6bed610d457c087e3d0d7d301af9', 'width': 108}, {'height': 116, 'url': 'h... | |
I accidentally built an AI agent that's better than GPT-4 and it's 100% deterministic. This changes everything | 0 | **TL;DR:**
Built an AI agent that beat GPT-4, got **100% accuracy** on customer service tasks, and is **completely deterministic** (same input = same output, always).
This might be the first AI you can actually trust in production.
---
## The Problem Everyone Ignores
AI agents today are like quantum particles — ... | 2025-10-04T14:16:15 | https://gist.github.com/alokranjan-agp/541243473ea2bc31a7ddfe617e5a7d2c | Secure_Echo_971 | gist.github.com | 1970-01-01T00:00:00 | 0 | {} | 1nxv5hw | false | null | t3_1nxv5hw | /r/LocalLLaMA/comments/1nxv5hw/i_accidentally_built_an_ai_agent_thats_better/ | false | false | default | 0 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg.png?width=108&crop=smart&auto=webp&s=796041decb8c1250cbc2f301331b72f7385b477d', 'width': 108}, {'height': 108, 'url': 'h... |
It's alive! | 41 | The H in Granite 4.0-h stands for hilarious!
https://preview.redd.it/7y03utomr3tf1.png?width=1138&format=png&auto=webp&s=3aaaf875911e3a123e0651758a1d1a077225178e
| 2025-10-04T14:14:11 | https://www.reddit.com/r/LocalLLaMA/comments/1nxv3ke/its_alive/ | Illustrious-Dot-6888 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxv3ke | false | null | t3_1nxv3ke | /r/LocalLLaMA/comments/1nxv3ke/its_alive/ | false | false | 41 | null | |
Question about Qwen3-30B | 0 | Is there a way to turn off or filter out the thinking commentary on the responses?
"Okay, let me analyze this...", "First, I need to understand...", etc. ?
| 2025-10-04T13:53:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nxulci/question_about_qwen330b/ | seoulsrvr | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxulci | false | null | t3_1nxulci | /r/LocalLLaMA/comments/1nxulci/question_about_qwen330b/ | false | false | self | 0 | null |
Is MLX in itself somehow making the models a little bit different / more "stupid"? | 18 | I have an MBP M4 128GB RAM.
I run LLMs using LMStudio.
I (nearly) always let LMStudio decide on the temp and other params.
I simply load models and use the chat interface or use them directly from code via the local API.
As a Mac user, I tend to go for the MLX versions of models since they are generally faster th... | 2025-10-04T13:21:20 | https://www.reddit.com/r/LocalLLaMA/comments/1nxtuiy/is_mlx_in_itself_somehow_making_the_models_a/ | CBW1255 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxtuiy | false | null | t3_1nxtuiy | /r/LocalLLaMA/comments/1nxtuiy/is_mlx_in_itself_somehow_making_the_models_a/ | false | false | self | 18 | null |
Looking for hardware recommendations for my first home/hobby machine | 4 | Hi,
I've been searching Marketplace for a while.
Two different machines have come up and I would like some recommendations from the community.
First, for $1950 CAD
- Mother Board: ASROCK Z490 TAICHI
- GPU: Nvidia GeForce RTX 3090 Founders Edition
- CPU: Intel Core i9-10900K 10-Core 3.7GHz
- PSU: Seasonic FOCUS GM-8... | 2025-10-04T13:10:18 | https://www.reddit.com/r/LocalLLaMA/comments/1nxtldo/looking_for_hardware_recommendations_for_my_first/ | mrfocus22 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxtldo | false | null | t3_1nxtldo | /r/LocalLLaMA/comments/1nxtldo/looking_for_hardware_recommendations_for_my_first/ | false | false | self | 4 | null |
Replicating Anthropic's Agentic Misalignment with open models? | 4 | A few months ago Anthropic published an [article](https://www.anthropic.com/research/agentic-misalignment) and [repo](https://github.com/anthropic-experimental/agentic-misalignment) where they run some experiments and, from what I understand, they show that models resort to murder and blackmail (with different rates) i... | 2025-10-04T13:08:57 | https://www.reddit.com/r/LocalLLaMA/comments/1nxtk7j/replicating_anthropics_agentic_misalignment_with/ | MitsotakiShogun | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxtk7j | false | null | t3_1nxtk7j | /r/LocalLLaMA/comments/1nxtk7j/replicating_anthropics_agentic_misalignment_with/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'YqpkFbtVl5x_nWeH4WDeyrnRsjmO_TkNaHzW8-LXmr4', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/YqpkFbtVl5x_nWeH4WDeyrnRsjmO_TkNaHzW8-LXmr4.png?width=108&crop=smart&auto=webp&s=3858f721a29547fa04b2e0baa4c1d0e9bf05205b', 'width': 108}, {'height': 113, 'url': 'h... |
Effective context engineering for AI agents by Anthropic | 0 | 2025-10-04T12:47:27 | https://www.reddit.com/gallery/1nxt2r2 | Vast_Comedian_9370 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nxt2r2 | false | null | t3_1nxt2r2 | /r/LocalLLaMA/comments/1nxt2r2/effective_context_engineering_for_ai_agents_by/ | false | false | 0 | null | ||
IBM granite 4.0-h-tiny leads the way for extra small MoEs | 139 | I hope the trend for those MoEs carries on. Normies with laverage laptops will soon be able to use decent models with little ressources. | 2025-10-04T12:20:23 | GreenTreeAndBlueSky | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxshw2 | false | null | t3_1nxshw2 | /r/LocalLLaMA/comments/1nxshw2/ibm_granite_40htiny_leads_the_way_for_extra_small/ | false | false | default | 139 | {'enabled': True, 'images': [{'id': 'nlkf3btz73tf1', 'resolutions': [{'height': 57, 'url': 'https://preview.redd.it/nlkf3btz73tf1.png?width=108&crop=smart&auto=webp&s=ff74d6667a7a1a2a11a30adcefa258e8e3c1b366', 'width': 108}, {'height': 115, 'url': 'https://preview.redd.it/nlkf3btz73tf1.png?width=216&crop=smart&auto=web... | |
GLM 4.6 Makes Incredible Front End Design with 2 prompts | 98 | So I've been playing with GLM 4.6, I've also implemented it inside Cloud Code, and I'll be doing a new video on how to set up GLM 4.6 in Cloud Code, but I really wanted to show everybody how great z ai is with front end design.
In this video I take a screenshot of a website and I do one simple prompt and it kicks out ... | 2025-10-04T12:08:05 | https://youtu.be/AvHsytH-K84 | dev_is_active | youtu.be | 1970-01-01T00:00:00 | 0 | {} | 1nxs8tr | false | {'oembed': {'author_name': 'eeko systems | ai & automation for business', 'author_url': 'https://www.youtube.com/@eeko_systems', 'height': 200, 'html': '<iframe width="267" height="200" src="https://www.youtube.com/embed/AvHsytH-K84?feature=oembed&enablejsapi=1" frameborder="0" allow="accelerometer; autoplay; clipboard... | t3_1nxs8tr | /r/LocalLLaMA/comments/1nxs8tr/glm_46_makes_incredible_front_end_design_with_2/ | false | false | 98 | {'enabled': False, 'images': [{'id': 'HRx3NTzzZMOIdtM0oRmpT2rIW9OnDaS9AE7D0C1FPSc', 'resolutions': [{'height': 81, 'url': 'https://external-preview.redd.it/HRx3NTzzZMOIdtM0oRmpT2rIW9OnDaS9AE7D0C1FPSc.jpeg?width=108&crop=smart&auto=webp&s=ea8ea76a6c4234e3fcec27721b999cff24946f33', 'width': 108}, {'height': 162, 'url': '... | |
Are there any LLM 'guardrails' that are ever built into the model training process? | 2 | Are there any LLM 'guardrails' that are ever built into the model training process? Trying to understand the set exclusivity of what is actually trained into the model and what is added on post-training
For example chatgpt would reject a request "how to make mustard gas" as it recognizes that mustard gas is specifical... | 2025-10-04T12:03:55 | https://www.reddit.com/r/LocalLLaMA/comments/1nxs5td/are_there_any_llm_guardrails_that_are_ever_built/ | MullingMulianto | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxs5td | false | null | t3_1nxs5td | /r/LocalLLaMA/comments/1nxs5td/are_there_any_llm_guardrails_that_are_ever_built/ | false | false | self | 2 | null |
Does anyone actually use Cratak? | 0 | I’ve been using it since only few days. It claims to be a community platform and give access to modified (uncensored) versions of some latest LLM models. The thing is expect a weird YouTube video and a guy who talked about it on r/privacy, this website looks to be appeared out of nowhere with zero reputation or histor... | 2025-10-04T11:58:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nxs1kl/does_anyone_actually_use_cratak/ | Planctonique | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxs1kl | false | null | t3_1nxs1kl | /r/LocalLLaMA/comments/1nxs1kl/does_anyone_actually_use_cratak/ | false | false | 0 | null | |
This is pretty cool | 69 | https://venturebeat.com/ai/huaweis-new-open-source-technique-shrinks-llms-to-make-them-run-on-less
https://github.com/huawei-csl/SINQ/blob/main/README.md
| 2025-10-04T11:45:15 | https://github.com/huawei-csl/SINQ/blob/main/README.md | wowsers7 | github.com | 1970-01-01T00:00:00 | 0 | {} | 1nxrssl | false | null | t3_1nxrssl | /r/LocalLLaMA/comments/1nxrssl/this_is_pretty_cool/ | false | false | 69 | {'enabled': False, 'images': [{'id': 'fWjpQVd5VjUiyz85oEUZ3MBMlQycdcPTlMPYbRWoE6A', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/fWjpQVd5VjUiyz85oEUZ3MBMlQycdcPTlMPYbRWoE6A.png?width=108&crop=smart&auto=webp&s=7dea2e3e0a59f656b89dde6c5e7b53ffb14046b9', 'width': 108}, {'height': 108, 'url': 'h... | |
Just saw the news of ban consideration on DeepSeek in US | 5 | Just read this https://www.axios.com/2025/10/03/ai-deepseek-alarm
Who will suffer in the end is an average consumer who will be overcharged by US Moguls. Remember llamers if DeepSeek wasn't announced openai pricing for o4 we all know was out of reach and closed sources. Just let the market play, same for gpus we want ... | 2025-10-04T11:32:01 | https://www.reddit.com/r/LocalLLaMA/comments/1nxrk0p/just_saw_the_news_of_ban_consideration_on/ | gpt872323 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxrk0p | false | null | t3_1nxrk0p | /r/LocalLLaMA/comments/1nxrk0p/just_saw_the_news_of_ban_consideration_on/ | false | false | self | 5 | {'enabled': False, 'images': [{'id': 'phWZbT_xplj7hhbivItDt26f7wYBEtxN4cPDxGiktek', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/phWZbT_xplj7hhbivItDt26f7wYBEtxN4cPDxGiktek.jpeg?width=108&crop=smart&auto=webp&s=f33157c50a793a5ad2b88dd04a7354092cb64180', 'width': 108}, {'height': 121, 'url': '... |
Most reliable vllm quant for Qwen3-next-80b-a3b? | 3 | As title suggests. I'm trying to find a int4 or awq version that can start up properly and reliably. Have tried cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit and Intel/Qwen3-Next-80B-A3B-Instruct-int4-mixed-AutoRound.
The latter gives me KeyError: 'layers.0.mlp.shared_expert.down_proj.weight'.
I am on the latest vLLM ... | 2025-10-04T11:27:48 | https://www.reddit.com/r/LocalLLaMA/comments/1nxrh9d/most_reliable_vllm_quant_for_qwen3next80ba3b/ | yuch85 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxrh9d | false | null | t3_1nxrh9d | /r/LocalLLaMA/comments/1nxrh9d/most_reliable_vllm_quant_for_qwen3next80ba3b/ | false | false | self | 3 | null |
Smartest model to run on 5090? | 18 | What’s the largest model I should run on 5090 for reasoning? E.g. GLM 4.6 - which version is ideal for one 5090?
Thanks. | 2025-10-04T11:08:10 | https://www.reddit.com/r/LocalLLaMA/comments/1nxr4gu/smartest_model_to_run_on_5090/ | eCityPlannerWannaBe | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxr4gu | false | null | t3_1nxr4gu | /r/LocalLLaMA/comments/1nxr4gu/smartest_model_to_run_on_5090/ | false | false | self | 18 | null |
Anyone running llm on their 16GB android phone? | 15 | My 8gb dual channel phone is dying, so I would like buy a 16gb quad channel android phone to run llm.
I am interested in running gemma3-12b-qat-q4\_0 on it.
If you have one, can you run it for me on pocketpal or chatterUI and report the performance (t/s for both prompt processing and inference)? Please also report y... | 2025-10-04T10:58:27 | https://www.reddit.com/r/LocalLLaMA/comments/1nxqxtl/anyone_running_llm_on_their_16gb_android_phone/ | Ok_Warning2146 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxqxtl | false | null | t3_1nxqxtl | /r/LocalLLaMA/comments/1nxqxtl/anyone_running_llm_on_their_16gb_android_phone/ | false | false | self | 15 | null |
Examsprint AI is the only study solution you need. | 0 | I am Aadarsh Pandey 13y/o from India. I am the developer and founder of Examsprint AI.
features of Examsprint AI are:
Chapters and topics list
Direct NCERT Links
Practice questions in form of Flashcards specialised for each chapter[For Class 11 and 12]
Personal AI chatbot to SOLVE any type of Questions regarding P... | 2025-10-04T10:54:07 | No_Golf_5566 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxqv89 | false | null | t3_1nxqv89 | /r/LocalLLaMA/comments/1nxqv89/examsprint_ai_is_the_only_study_solution_you_need/ | false | false | default | 0 | {'enabled': True, 'images': [{'id': 'rqicn4ehs2tf1', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/rqicn4ehs2tf1.png?width=108&crop=smart&auto=webp&s=4f5d8b1f4a5eb97eb29498082190e1612e28450e', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/rqicn4ehs2tf1.png?width=216&crop=smart&auto=we... | |
I was constantly getting rate limit/timeout errors from AI APIs, so I built a universal Python error handler and retry decorator to solve it. Here's the code (FOSS). | 1 | [removed] | 2025-10-04T10:40:40 | https://www.reddit.com/r/LocalLLaMA/comments/1nxqn59/i_was_constantly_getting_rate_limittimeout_errors/ | WeakPianist9445 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxqn59 | false | null | t3_1nxqn59 | /r/LocalLLaMA/comments/1nxqn59/i_was_constantly_getting_rate_limittimeout_errors/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/OAXSl8SY6T3JK9MGQyKxkoYbqZ71HQRYXLeB8CV0NXg.png?width=108&crop=smart&auto=webp&s=796041decb8c1250cbc2f301331b72f7385b477d', 'width': 108}, {'height': 108, 'url': 'h... |
Examsprint AI: The only one stop Study you need. | 0 | I am Aadarsh Pandey 13y/o from India. I am the developer and founder of Examsprint AI.
features of Examsprint AI are:
Chapters and topics list
Direct NCERT Links
Practice questions in form of Flashcards specialised for each chapter[For Class 11 and 12]
Personal AI chatbot to SOLVE any type of Questions regarding P... | 2025-10-04T10:39:14 | Organic_Kick6610 | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxqm81 | false | null | t3_1nxqm81 | /r/LocalLLaMA/comments/1nxqm81/examsprint_ai_the_only_one_stop_study_you_need/ | false | false | 0 | {'enabled': True, 'images': [{'id': 'PrtV4Au8xzyBwWrtwu7kdUupYR51vmMfQiwX9meRV8Y', 'resolutions': [{'height': 216, 'url': 'https://preview.redd.it/8wl1fpyxp2tf1.png?width=108&crop=smart&auto=webp&s=712ea8f32f903cb6c5d34704782227f0930bbb43', 'width': 108}, {'height': 432, 'url': 'https://preview.redd.it/8wl1fpyxp2tf1.pn... | ||
The easiest way for an Al to seize power is not by breaking out of Dr. Frankenstein's lab but by ingratiating itself with some paranoid Tiberius. | 0 | "If even just a few of the world's dictators choose to put their trust in Al, this could have far-reaching consequences for the whole of humanity.
Science fiction is full of scenarios of an Al getting out of control and enslaving or eliminating humankind.
Most sci-fi plots explore these scenarios in the context of de... | 2025-10-04T10:36:22 | https://www.reddit.com/r/LocalLLaMA/comments/1nxqki4/the_easiest_way_for_an_al_to_seize_power_is_not/ | katxwoods | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxqki4 | false | null | t3_1nxqki4 | /r/LocalLLaMA/comments/1nxqki4/the_easiest_way_for_an_al_to_seize_power_is_not/ | false | false | self | 0 | null |
Can't run GLM 4.6 in lmstudio! | 4 | Can I run GLM 4.6 in lmstudio at all? I keep getting this error: "\`\`\`
🥲 Failed to load the model
Failed to load model
error loading model: missing tensor 'blk.92.nextn.embed\_tokens.weight'
\`\`\`" | 2025-10-04T10:33:11 | https://www.reddit.com/r/LocalLLaMA/comments/1nxqion/cant_run_glm_46_in_lmstudio/ | Adventurous_Rise_683 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxqion | false | null | t3_1nxqion | /r/LocalLLaMA/comments/1nxqion/cant_run_glm_46_in_lmstudio/ | false | false | self | 4 | null |
Awesome Local LLM Speech-to-Speech Models & Frameworks | 26 | Did some digging into speech-to-speech models/frameworks for a project recently and ended up with a pretty comprehensive list. Figured I'd drop it here in case it helps anyone else avoid going down the same rabbit hole.
What made the cut:
* Has **LLM integration** (built-in or via modules)
* Does **full speech-to... | 2025-10-04T10:19:27 | https://github.com/tleyden/awesome-llm-speech-to-speech | tleyden | github.com | 1970-01-01T00:00:00 | 0 | {} | 1nxqabe | false | null | t3_1nxqabe | /r/LocalLLaMA/comments/1nxqabe/awesome_local_llm_speechtospeech_models_frameworks/ | false | false | 26 | {'enabled': False, 'images': [{'id': 'sv2a4YrAVR9g08yOa0AOrBrIqErmKKSQAYIjNTCx_eI', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/sv2a4YrAVR9g08yOa0AOrBrIqErmKKSQAYIjNTCx_eI.png?width=108&crop=smart&auto=webp&s=60f46e4e5af1ec77ab94075fd92923b4dd50687c', 'width': 108}, {'height': 108, 'url': 'h... | |
[Tool Release] ollama_server_manager: A Simple Web UI to Manage Models Across Multiple Local Ollama Servers | 1 | I was struggling to keep track of models across my **three local Ollama servers** using only the command line. It got tedious! 😥
To solve this, I created `ollama_server_manager`\- a simple tool that provides a **web-based dashboard** to overview which models are present on which server.
Since I only use this on my *... | 2025-10-04T10:18:03 | https://www.reddit.com/r/LocalLLaMA/comments/1nxq9gu/tool_release_ollama_server_manager_a_simple_web/ | GennadiiM | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxq9gu | false | null | t3_1nxq9gu | /r/LocalLLaMA/comments/1nxq9gu/tool_release_ollama_server_manager_a_simple_web/ | false | false | self | 1 | {'enabled': False, 'images': [{'id': 'EFL5nViDRcVoXOzP2ObIaPHFmE5ciabBzEB5hl1LYxM', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/EFL5nViDRcVoXOzP2ObIaPHFmE5ciabBzEB5hl1LYxM.png?width=108&crop=smart&auto=webp&s=196c3ba627a4755b8996801c9a8413b7c920cd6e', 'width': 108}, {'height': 108, 'url': 'h... |
Best lightweight low resources LLM. | 4 | Best lightweight low resources no GPU LLM model to run locally on a VM.
7b or less. RAM only 8GB , CPU 4 cores 2.5Ghz.
Working on project cloud environmen troubleshooting tool. Will be using it for low level coding, finding issues related to kubernetes, docker, kafka, database, linux systems.
Qwen2.5 coder 7b,
Codel... | 2025-10-04T10:01:59 | https://www.reddit.com/r/LocalLLaMA/comments/1nxq04a/best_lightweight_low_resources_llm/ | Full_University_7232 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxq04a | false | null | t3_1nxq04a | /r/LocalLLaMA/comments/1nxq04a/best_lightweight_low_resources_llm/ | false | false | self | 4 | null |
Can't get Granite 4 maximum context window size... | 3 | Hello,
I'm using ollama 0.12.3 and OpenWebui 0.6.32 and I have a rig with 3x 4060 TI 16GB. I can run 32b models with context size that allow to fill up to 48GB VRAM.
When I'm using granite4:tiny-h, I can put a context of 290000 tokens, which takes 12GB in the VRAM but I have a memory error for 300000 tokens.
With gr... | 2025-10-04T08:44:57 | https://www.reddit.com/r/LocalLLaMA/comments/1nxosfs/cant_get_granite_4_maximum_context_window_size/ | Fade78 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxosfs | false | null | t3_1nxosfs | /r/LocalLLaMA/comments/1nxosfs/cant_get_granite_4_maximum_context_window_size/ | false | false | self | 3 | null |
Best local model for open code? | 16 | Which LLM gives you satisfaction for tasks under open code with 12Go vram ? | 2025-10-04T08:00:16 | https://www.reddit.com/r/LocalLLaMA/comments/1nxo3ao/best_local_model_for_open_code/ | LastCulture3768 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxo3ao | false | null | t3_1nxo3ao | /r/LocalLLaMA/comments/1nxo3ao/best_local_model_for_open_code/ | false | false | self | 16 | null |
Whats your PC tech spec? | 2 | Hey guys.
I'm just wondering what is your PC/Laptop tech spec and what local LLM are you guys using?
How's the experience? | 2025-10-04T07:51:05 | https://www.reddit.com/r/LocalLLaMA/comments/1nxny65/whats_your_pc_tech_spec/ | luckypanda95 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxny65 | false | null | t3_1nxny65 | /r/LocalLLaMA/comments/1nxny65/whats_your_pc_tech_spec/ | false | false | self | 2 | null |
Dual DGX Spark for ~150 Users RAG? | 0 | Hey all,
with the official order options of the DGX Spark starting soon, I'd like to get some reflection by those actually running a larger scale system for many users.
Currently we only have a few OpenAI licenses in our company. We have about 10k Documents from our QM system we'd like to ingest into a RAG system to ... | 2025-10-04T07:42:06 | https://www.reddit.com/r/LocalLLaMA/comments/1nxnt4j/dual_dgx_spark_for_150_users_rag/ | streppelchen | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxnt4j | false | null | t3_1nxnt4j | /r/LocalLLaMA/comments/1nxnt4j/dual_dgx_spark_for_150_users_rag/ | false | false | self | 0 | null |
Where do you think we'll be at for home inference in 2 years? | 25 | I suppose we'll never see any big price reduction jumps? Especially with inflation rising globally?
I'd love to be able to have a home SOTA tier model for under $15k. Like GLM 4.6, etc. But wouldn't we all? | 2025-10-04T07:41:51 | https://www.reddit.com/r/LocalLLaMA/comments/1nxnszs/where_do_you_think_well_be_at_for_home_inference/ | TumbleweedDeep825 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxnszs | false | null | t3_1nxnszs | /r/LocalLLaMA/comments/1nxnszs/where_do_you_think_well_be_at_for_home_inference/ | false | false | self | 25 | null |
best coding model under 40b parameters? preferably moe | 8 | preferably moe | 2025-10-04T07:37:00 | https://www.reddit.com/r/LocalLLaMA/comments/1nxnq77/best_coding_model_under_40b_parameters_preferably/ | Odd-Ordinary-5922 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxnq77 | false | null | t3_1nxnq77 | /r/LocalLLaMA/comments/1nxnq77/best_coding_model_under_40b_parameters_preferably/ | false | false | self | 8 | null |
Multi-Agent RAG Workflows in RAGFlow, Slower, No Better Results? Looking for Guidance | 3 | Hey everyone,
I'm currently working on upgrading our RAG system at my company and could really use some input.
I’m restricted to using RAGFlow, and my original hypothesis was that implementing a multi-agent architecture would yield better performance and more accurate results. However, what I’ve observed is that:
*... | 2025-10-04T07:30:21 | https://www.reddit.com/r/LocalLLaMA/comments/1nxnmc2/multiagent_rag_workflows_in_ragflow_slower_no/ | void_brambora | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxnmc2 | false | null | t3_1nxnmc2 | /r/LocalLLaMA/comments/1nxnmc2/multiagent_rag_workflows_in_ragflow_slower_no/ | false | false | self | 3 | null |
I used llama 3.3 70b to build an AI tool | 0 | So I'm Arush, a 14 y/o from India. I recently built NexNotes Al. It has all the features needed for studying and research. Just upload any type of file and get:
question papers
Mindmaps and diagrams (custom)
Quizzes with customized difficulty
Vocab extraction
Humanized text
handwritten text
It can solve your que... | 2025-10-04T07:19:00 | https://www.reddit.com/r/LocalLLaMA/comments/1nxnfuy/i_used_llama_33_70b_to_build_an_ai_tool/ | Turbulent_Orchid2829 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxnfuy | false | null | t3_1nxnfuy | /r/LocalLLaMA/comments/1nxnfuy/i_used_llama_33_70b_to_build_an_ai_tool/ | false | false | self | 0 | null |
We’re doing community safety research on open models — 30 sec survey for users | 0 | Hey all! Have you ever explored or considered downloading open-weight models on Hugging Face? If yes, could you help us out by filling this quick 30 second survey? : [forms.gle/RETjXHvtqtLmMhPM7](http://forms.gle/RETjXHvtqtLmMhPM7)
Context : We're planning to run some safety research on top HuggingFace models and publ... | 2025-10-04T07:07:43 | https://www.reddit.com/r/LocalLLaMA/comments/1nxn9f5/were_doing_community_safety_research_on_open/ | whalefal | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxn9f5 | false | null | t3_1nxn9f5 | /r/LocalLLaMA/comments/1nxn9f5/were_doing_community_safety_research_on_open/ | false | false | self | 0 | {'enabled': False, 'images': [{'id': 'O7x0pJ3DB4MPKopPFw_3N6NQpgYS8aI9CVbqiCi8OZU', 'resolutions': [{'height': 56, 'url': 'https://external-preview.redd.it/O7x0pJ3DB4MPKopPFw_3N6NQpgYS8aI9CVbqiCi8OZU.png?width=108&crop=smart&auto=webp&s=e05c589f84900204fa3faa95b293f254d7ae2603', 'width': 108}, {'height': 113, 'url': 'h... |
how you configure the $3/mo GLM Coding Plan with Droid CLI | 1 | [removed] | 2025-10-04T07:02:42 | https://www.reddit.com/r/LocalLLaMA/comments/1nxn6gi/how_you_configure_the_3mo_glm_coding_plan_with/ | Impressive-Olive8372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxn6gi | false | null | t3_1nxn6gi | /r/LocalLLaMA/comments/1nxn6gi/how_you_configure_the_3mo_glm_coding_plan_with/ | false | false | self | 1 | null |
how you configure the $3/mo GLM Coding Plan with Droid CLI | 1 | [removed] | 2025-10-04T06:59:42 | https://www.reddit.com/r/LocalLLaMA/comments/1nxn4gy/how_you_configure_the_3mo_glm_coding_plan_with/ | Impressive-Olive8372 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxn4gy | false | null | t3_1nxn4gy | /r/LocalLLaMA/comments/1nxn4gy/how_you_configure_the_3mo_glm_coding_plan_with/ | false | false | self | 1 | null |
Help me build this monster, for- learning, experiments(text, image, video, audio), training and fine-tuning(small scale LoRA) | 0 | Im trying to finalize a configuration for a local stack for - check title.
Shortlisted so far below, I want to know your experiences, suggestions, tips etc.
CPU: AMD Threadripper Pro 9955WX 16-core
Chipset: WRX90, WRX90E SAGE SE - Asus Pro WS
Mem: 128GB ECC DDR5 5600Mhz/6000
GPU: RTX 6000 PRO Blackwell Workstatio... | 2025-10-04T06:58:10 | https://www.reddit.com/r/LocalLLaMA/comments/1nxn3jy/help_me_build_this_monster_for_learning/ | s2k4ever | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxn3jy | false | null | t3_1nxn3jy | /r/LocalLLaMA/comments/1nxn3jy/help_me_build_this_monster_for_learning/ | false | false | self | 0 | null |
The Missing Link between the Transformer and Models of the Brain | 9 | A group of scientists at Pathway claim to have found a missing link . 'The massively parallel post-Transformer reasoning architecture which opens the door to generalization over time'
Link to the paper : https://arxiv.org/abs/2509.26507 | 2025-10-04T06:35:16 | https://www.reddit.com/r/LocalLLaMA/comments/1nxmq9b/the_missing_link_between_the_transformer_and/ | ramzeez88 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxmq9b | false | null | t3_1nxmq9b | /r/LocalLLaMA/comments/1nxmq9b/the_missing_link_between_the_transformer_and/ | false | false | self | 9 | null |
Where can I find Sonnet 4.5 at a lower price? | 0 | I’m interested in using Sonnet 4.5 daily, but I’m not sure about Claude’s limits. Is it more cost-effective to purchase Cursor, pay as you go on OpenRouter, or buy the Claude subscription itself? Using OpenRouter give me the option to switch to GLM 4.6 for easier tasks
Has anyone attempted to determine the most ec... | 2025-10-04T06:31:19 | https://www.reddit.com/r/LocalLLaMA/comments/1nxmny6/where_can_i_find_sonnet_45_at_a_lower_price/ | farnoud | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxmny6 | false | null | t3_1nxmny6 | /r/LocalLLaMA/comments/1nxmny6/where_can_i_find_sonnet_45_at_a_lower_price/ | false | false | self | 0 | null |
Any concrete drawbacks from using Vercel's AI SDK? | 4 | I have started multiple projects using AI / Agent frameworks and have always been disappointed in the end. My current project I am implementing everything from scratch and I am much happier, I know where all the state exists and I do not have to spend hours trying to find how to extract some data from the agent loop wh... | 2025-10-04T06:18:17 | https://www.reddit.com/r/LocalLLaMA/comments/1nxmfz7/any_concrete_drawbacks_from_using_vercels_ai_sdk/ | Suspicious_Dress_350 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxmfz7 | false | null | t3_1nxmfz7 | /r/LocalLLaMA/comments/1nxmfz7/any_concrete_drawbacks_from_using_vercels_ai_sdk/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'D6shUXR7p16Sn_OlqzgZA1AwgNS_FrdvcuB9JbWIZck', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/D6shUXR7p16Sn_OlqzgZA1AwgNS_FrdvcuB9JbWIZck.png?width=108&crop=smart&auto=webp&s=36ed0b4002b1a2b49a655eeafa068505f04ce430', 'width': 108}, {'height': 108, 'url': 'h... |
Does anyone know how to fix this? | 5 | I just download LM studio, and I cannot click "get started" ?? | 2025-10-04T06:13:21 | Neck_Aware | i.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxmd1h | false | null | t3_1nxmd1h | /r/LocalLLaMA/comments/1nxmd1h/does_anyone_know_how_to_fix_this/ | false | false | default | 5 | {'enabled': True, 'images': [{'id': 'wyh4ilqce1tf1', 'resolutions': [{'height': 60, 'url': 'https://preview.redd.it/wyh4ilqce1tf1.png?width=108&crop=smart&auto=webp&s=0439ee74af7d920844b79ed5657612c0f24af063', 'width': 108}, {'height': 121, 'url': 'https://preview.redd.it/wyh4ilqce1tf1.png?width=216&crop=smart&auto=web... | |
Unsure which ollama model to use? Here's a tool I built to help | 4 | Hey everyone,
I’m fairly new to working with local LLMs, and like many, I wondered which model(s) I should use. To help answer that, I put together a tool that:
* Automates running multiple models on custom prompts
* Outputs everything into a clean, easy-to-read HTML report
* Lets you quickly compare results side by ... | 2025-10-04T05:36:03 | https://www.reddit.com/r/LocalLLaMA/comments/1nxlq7t/unsure_which_ollama_model_to_use_heres_a_tool_i/ | h3xzur7 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxlq7t | false | null | t3_1nxlq7t | /r/LocalLLaMA/comments/1nxlq7t/unsure_which_ollama_model_to_use_heres_a_tool_i/ | false | false | self | 4 | {'enabled': False, 'images': [{'id': 'PUdEn3C3OYW3pnzdzVV9G-ao4Q8h-K_s24CF_LxayCU', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/PUdEn3C3OYW3pnzdzVV9G-ao4Q8h-K_s24CF_LxayCU.png?width=108&crop=smart&auto=webp&s=38a0361ba6042272be3a54cc2e1849556ef61101', 'width': 108}, {'height': 108, 'url': 'h... |
Looking for CTO, I'm a content creator (750k+) I scaled apps to 1.5M downloads. VCs are now waiting for product + team | 0 | I’m a theology grad and content creator with 750K+ followers (30M likes, 14M views). I’ve also scaled and sold apps to 1.5M+ organic downloads before.
Right now, I’m building an AI-powered spiritual companion. Think Hallow (valued $400M+ for Catholics), but built for a massive, underserved segment of Christianity.
I’... | 2025-10-04T05:27:01 | https://www.reddit.com/r/LocalLLaMA/comments/1nxlksh/looking_for_cto_im_a_content_creator_750k_i/ | Samonji | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxlksh | false | null | t3_1nxlksh | /r/LocalLLaMA/comments/1nxlksh/looking_for_cto_im_a_content_creator_750k_i/ | false | false | self | 0 | null |
Best practices for building a context-aware chatbot with a small dataset and a custom context pipeline | 2 | I’m building a chatbot for my research project that helps participants understand charts. The chatbot runs on a React website.
My goal is to make the experience feel like ChatGPT in the browser: users upload a chart image and dataset file, then ask questions about it naturally in a conversational way. I want the chatb... | 2025-10-04T05:24:55 | https://www.reddit.com/r/LocalLLaMA/comments/1nxljg8/best_practices_for_building_a_contextaware/ | EnvironmentalWork812 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxljg8 | false | null | t3_1nxljg8 | /r/LocalLLaMA/comments/1nxljg8/best_practices_for_building_a_contextaware/ | false | false | self | 2 | null |
Regarding artificial intelligence, does llama have an online server free? | 0 | type to avoid overloading and damaging a laptop with only 8GB of RAM. I wanted one to use online that was uncensored and without limitations and that allowed me to create a data library as an online reference | 2025-10-04T05:20:22 | https://www.reddit.com/r/LocalLLaMA/comments/1nxlgmb/regarding_artificial_intelligence_does_llama_have/ | Godi22kam | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxlgmb | false | null | t3_1nxlgmb | /r/LocalLLaMA/comments/1nxlgmb/regarding_artificial_intelligence_does_llama_have/ | false | false | self | 0 | null |
Help with local LLM setup for vibe coding | 4 | Hi all, I'm interested to setup a local model to vibe code with cline in VS code and would like some recommendations for the most optimum setup.
I have 2 PCs:
1. Main rig - AMD 5700X3D + 32GB 3200MHz + AMD RX6750XT 12GB VRAM
2. Old rig - AMD 5600 + 64GB 2133MHz + GT710 for display only
I'm considering between upgradi... | 2025-10-04T05:11:58 | https://www.reddit.com/r/LocalLLaMA/comments/1nxlbgx/help_with_local_llm_setup_for_vibe_coding/ | Diligent-Cut-899 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxlbgx | false | null | t3_1nxlbgx | /r/LocalLLaMA/comments/1nxlbgx/help_with_local_llm_setup_for_vibe_coding/ | false | false | self | 4 | null |
5 second scraper you can use to make apis using Granite-4.0-micro unsloth 4bit | 4 | Ive tried making a web scraper in the past that rely on llms but have never really succeeded as the low parameter models would struggle with following instructions or would hallucinate and the larger parameter models would just be too large to run holding all the context. But today I decided to try the micro version of... | 2025-10-04T05:02:12 | https://v.redd.it/izb5dw5q01tf1 | Odd-Ordinary-5922 | v.redd.it | 1970-01-01T00:00:00 | 0 | {} | 1nxl5iw | false | {'reddit_video': {'bitrate_kbps': 5000, 'dash_url': 'https://v.redd.it/izb5dw5q01tf1/DASHPlaylist.mpd?a=1762146149%2CNGRlNzViYjNmZTM0NmE2ZjFlZGYzZDExN2JjMzA2OGFjOWI4NmEyOGNhMzQ3YzY0OWU3ZWQ3YzQyNTUxMDEwMg%3D%3D&v=1&f=sd', 'duration': 34, 'fallback_url': 'https://v.redd.it/izb5dw5q01tf1/DASH_1080.mp4?source=fallback', 'h... | t3_1nxl5iw | /r/LocalLLaMA/comments/1nxl5iw/5_second_scraper_you_can_use_to_make_apis_using/ | false | false | 4 | {'enabled': False, 'images': [{'id': 'eGJhZzZ3NXEwMXRmMc7wnKrW8YZJ1JZ6MUrOz6iXOJGd9J7VbFIb3kcWITYX', 'resolutions': [{'height': 60, 'url': 'https://external-preview.redd.it/eGJhZzZ3NXEwMXRmMc7wnKrW8YZJ1JZ6MUrOz6iXOJGd9J7VbFIb3kcWITYX.png?width=108&crop=smart&format=pjpg&auto=webp&s=795ccc2ea150ae6871907e6b5457a2ffe1779... | |
Everyone thinks theyre good at prompt engineering.. most arent. I learned that the hard way | 0 | I honestly thought I was good at writing prompts. like compared to my friends I felt I gave better instructions to llms and got better answers. but obviously they all thought they were better too.
so we made this dumb little competition.. everyone gets the same problem statement, 2 hours to write a prompt, then we run... | 2025-10-04T05:00:53 | https://www.reddit.com/r/LocalLLaMA/comments/1nxl4ll/everyone_thinks_theyre_good_at_prompt_engineering/ | Comfortable_Device50 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxl4ll | false | null | t3_1nxl4ll | /r/LocalLLaMA/comments/1nxl4ll/everyone_thinks_theyre_good_at_prompt_engineering/ | false | false | self | 0 | null |
Front end generation model recommendations | 3 | Looking for models that are capable of designing sites using vanilla js and html. React, svelte ,bootstrap even jquery is a plus. | 2025-10-04T04:51:47 | https://www.reddit.com/r/LocalLLaMA/comments/1nxkymy/front_end_generation_model_recommendations/ | AggravatingGiraffe46 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxkymy | false | null | t3_1nxkymy | /r/LocalLLaMA/comments/1nxkymy/front_end_generation_model_recommendations/ | false | false | self | 3 | null |
I was constantly getting rate limit errors from AI APIs, so I built a universal Python error handler and retry decorator to solve it. Sharing it for free. | 1 |
Like many of you, I've been building some complex projects that make a lot of calls to various AI APIs. One of the biggest frustrations has been the constant stream of RateLimitError, APITimeoutError, or random 502 Bad Gateway issues that would crash my entire workflow.
Writing try...except blocks for every single A... | 2025-10-04T04:48:51 | https://www.reddit.com/r/LocalLLaMA/comments/1nxkwsi/i_was_constantly_getting_rate_limit_errors_from/ | WeakPianist9445 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxkwsi | false | null | t3_1nxkwsi | /r/LocalLLaMA/comments/1nxkwsi/i_was_constantly_getting_rate_limit_errors_from/ | false | false | self | 1 | null |
Distributed Inference over wifi with 8x 3090 egpus performance | 136 | Hello,
I smoked some really good weed recently and decided it was a good idea to buy more 3090s.
Naturally I didn't want to use a real build with server parts, put 8 3090s in one build on home depot racks? No thanks I'm lazy.
I got 4 3090 egpus from a guy on facebook. He's cool, sold them to me for 650 each with the... | 2025-10-04T03:57:59 | https://www.reddit.com/r/LocalLLaMA/comments/1nxjzbn/distributed_inference_over_wifi_with_8x_3090/ | Only_Situation_4713 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxjzbn | false | null | t3_1nxjzbn | /r/LocalLLaMA/comments/1nxjzbn/distributed_inference_over_wifi_with_8x_3090/ | false | false | nsfw | 136 | {'enabled': False, 'images': [{'id': 'ys4iv7u_l2dMri4phpZy-9Px0-5rQm6yE7pFfmOqawQ', 'resolutions': [{'height': 108, 'url': 'https://external-preview.redd.it/ys4iv7u_l2dMri4phpZy-9Px0-5rQm6yE7pFfmOqawQ.png?width=108&crop=smart&auto=webp&s=0f61397cba0724be0a2d6320f914959224ff90ce', 'width': 108}, {'height': 216, 'url': '... |
Behold, the jankiest setup ever | 81 | I plan to get an open test bench, after I get my second P40 in a week or two (which will fit nicely on the other side of that fan)
Performance is as shown, Qwen 3 32B Q4 5.9T/sec
The fan is one of those stupidly powerful Delta electronics server fans that pushes out like 250cfm, so I needed to add a PWM controller t... | 2025-10-04T03:31:15 | https://www.reddit.com/gallery/1nxjhnj | T-VIRUS999 | reddit.com | 1970-01-01T00:00:00 | 0 | {} | 1nxjhnj | false | null | t3_1nxjhnj | /r/LocalLLaMA/comments/1nxjhnj/behold_the_jankiest_setup_ever/ | false | false | 81 | null | |
GitHub - huawei-csl/SINQ: Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method designed to make any Large Language Model smaller while preserving accuracy. | 66 | 2025-10-04T03:30:30 | https://github.com/huawei-csl/SINQ | Aiochedolor | github.com | 1970-01-01T00:00:00 | 0 | {} | 1nxjh4c | false | null | t3_1nxjh4c | /r/LocalLLaMA/comments/1nxjh4c/github_huaweicslsinq_welcome_to_the_official/ | false | false | default | 66 | {'enabled': False, 'images': [{'id': 'yP0CnjxBFJCXTVacHixSvy4H_F7MTnOAVtKcV29Lggk', 'resolutions': [{'height': 54, 'url': 'https://external-preview.redd.it/yP0CnjxBFJCXTVacHixSvy4H_F7MTnOAVtKcV29Lggk.png?width=108&crop=smart&auto=webp&s=70a7ffdefbd7cbdad2ea677cc3cb2be538382a9d', 'width': 108}, {'height': 108, 'url': 'h... | |
Help me fish... | 2 | There is a saying... give a man a fish feed him for a day... teach him to fish, feed him for life.
Anyone have a particularly clear and up-to-date guide on compiling llama.cpp for Nvidia in Ubuntu/Pop?
I found this so far: [https://truelogic.org/wordpress/2024/08/14/installing-llama-cpp-on-ubuntu-with-an-nvidia-gpu/... | 2025-10-04T03:24:18 | https://www.reddit.com/r/LocalLLaMA/comments/1nxjcqo/help_me_fish/ | silenceimpaired | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxjcqo | false | null | t3_1nxjcqo | /r/LocalLLaMA/comments/1nxjcqo/help_me_fish/ | false | false | self | 2 | null |
Where’s the lip reading ai? | 18 | I’m sure there are some projects out there making real progress on this, but given how quickly tech has advanced in recent years, I’m honestly surprised nothing has surfaced with strong accuracy in converting video to transcript purely through lip reading.
From what I’ve seen, personalized models trained on specific i... | 2025-10-04T02:31:46 | https://www.reddit.com/r/LocalLLaMA/comments/1nxibik/wheres_the_lip_reading_ai/ | Trustingmeerkat | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxibik | false | null | t3_1nxibik | /r/LocalLLaMA/comments/1nxibik/wheres_the_lip_reading_ai/ | false | false | self | 18 | null |
Why do private companies release open source models? | 136 | I love open source models. I feel they are an alternative for general knowledge, and since I started in this world, I stopped paying for subscriptions and started running models locally.
However, I don't understand the business model of companies like OpenAI launching an open source model.
How do they make money by ... | 2025-10-04T02:26:58 | https://www.reddit.com/r/LocalLLaMA/comments/1nxi82t/why_do_private_companies_release_open_source/ | desudesu15 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxi82t | false | null | t3_1nxi82t | /r/LocalLLaMA/comments/1nxi82t/why_do_private_companies_release_open_source/ | false | false | self | 136 | null |
Built an AI Trading Desk Quant - any thoughts? | 0 | [CILA chat](https://preview.redd.it/b05spx2s60tf1.png?width=1938&format=png&auto=webp&s=56e43f8108d46e853688580f2d93f57ab2b41e5b)
Hey everyone - we’ve been building an AI trading desk quant named **CILA-v1** (*Computational Intelligence for Low-frequency Assets*).
We launched on **Oct 1**, and the response blew us aw... | 2025-10-04T02:11:28 | https://www.reddit.com/r/LocalLLaMA/comments/1nxhx5t/built_an_ai_trading_desk_quant_any_thoughts/ | Significant-Town-457 | self.LocalLLaMA | 1970-01-01T00:00:00 | 0 | {} | 1nxhx5t | false | null | t3_1nxhx5t | /r/LocalLLaMA/comments/1nxhx5t/built_an_ai_trading_desk_quant_any_thoughts/ | false | false | 0 | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.