{"name":"unsloth","repo":"unslothai/unsloth","url":"https://midorreal.com/project/unslothai-unsloth","repository":"https://github.com/unslothai/unsloth","description":"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.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/unslothai/unsloth","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/unslothai/unsloth","checked":"22 Nov 2026"},"homepage":{"value":"https://unsloth.ai/docs","source":"https://unsloth.ai/docs","checked":"22 Nov 2026"},"last_release":{"value":"v0.1.920-beta, 19 Nov 2026","source":"https://github.com/unslothai/unsloth/releases","checked":"22 Nov 2026"},"releases":{"value":"90","source":"https://github.com/unslothai/unsloth/releases","checked":"19 Nov 2026"},"contributors":{"value":"458","source":"https://github.com/unslothai/unsloth/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/unslothai/unsloth","checked":"22 Nov 2026"}},"stars":79935.0,"writeup":{"what_it_is":"Unsloth is a local desktop app and web UI for running and training LLMs and diffusion models. It also offers a code-based version, Unsloth Core, and supports GGUF and MLX formats.","audience":"Users who want to run and fine-tune AI models locally on their own hardware","claims":[{"kind":"specific","claim":"Trains models 2x faster with 70% less VRAM","excerpt":"Train LLMs, diffusion, decision, TTS, and embedding models 2× faster with 70% less VRAM","status":"not_checked"},{"kind":"specific","claim":"Serves models through an OpenAI compatible API","excerpt":"Serve models through an [OpenAI compatible API]","status":"not_checked"},{"kind":"specific","claim":"Runs on Windows, Linux, WSL and macOS","excerpt":"Unsloth works on **Windows, Linux, WSL** and **macOS**.","status":"not_checked"},{"kind":"specific","claim":"Supports NVIDIA, AMD, Intel GPUs, CPUs and Vulkan","excerpt":"We support **Multi GPU setups, NVIDIA, AMD, Intel GPUs, CPUs** and the **Vulkan** backend.","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-10-27"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":81,"reality":98,"gap":-17,"momentum":1.3,"confidence":85,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-19T14:31:01+00:00","text":"Latest release v0.1.920-beta","source":"https://github.com/unslothai/unsloth/releases"},{"date":"2024-07-03T22:02:40+00:00","text":"First release","source":"https://github.com/unslothai/unsloth/releases"},{"date":"2023-11-29T16:50:09+00:00","text":"Repository created","source":"https://github.com/unslothai/unsloth"}],"cite":"unsloth is a GitHub project at https://github.com/unslothai/unsloth written mainly in Python, described there as \"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\".","attribution":"Data from Mid or Real, https://midorreal.com/project/unslothai-unsloth, checked 22 November 2026. Attribution with a link is required.","still_real":null}