Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
- fine-tuning
- llama
- llms
- gemma
94,845 visible repositories in the index
1–14 of 14 · Most stars
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
For GGUF support, see KoboldCPP: https://github.com/LostRuins/koboldcpp
FastAPI + Playwright + Camoufox 中间层代理服务器,兼容OpenAI API且支持参数转发。项目通过浏览器自动化将API请求转发到 Google AI Studio Chat,并同样按照OpenAI标准格式返回的工具。内置调试WebUI面板。
Train LoRAs on Google Colab in one click: Illustrious/NoobAI, Anima and MOSS-Image, over kohya-ss/sd-scripts.
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.
Tika-Python is a Python binding to the Apache Tika™ REST services allowing Tika to be called natively in the Python community.
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Rewrites AI drafts so they read like a person wrote them — runs locally, keeps the facts
Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
Enterprise-grade benchmark evaluating whether AI agents deliver verifiable business outcomes in real business systems — general domain, finance, supply chain, and manufacturing.
JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.