# unslothai/unsloth

> Desktop app and web UI for locally running, fine-tuning and serving LLMs, diffusion, embedding and audio models, with OpenAI-compatible API and integrations for Claude Code, Codex and MCP agents.

- Magnitude: 2.9 out of 10 — Steady
- Stars: 78,974 total · +48 stars measured 2026-11-02, 00:10–23:06 UTC
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2023-11-29 · Last push: 2026-11-02
- GitHub: https://github.com/unslothai/unsloth · Homepage: https://unsloth.ai/docs · Page: https://gitnova.dev/en/r/unslothai/unsloth

## Useful for

- Fine-tune a LoRA or QLoRA adapter on a local LLM with reduced VRAM usage.
- Serve a downloaded GGUF model through an OpenAI-compatible API on the local network.
- Connect Claude Code or Codex to a local model via the unsloth start command.

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:10–23:06: 78926 → 78974 stars (+48). This is the change over that interval.
- About 13 forks a day — people are taking the code.
- Recent forks include notable developers: @herniqeu (250 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 7,358
- Issues and pull requests: 16,134
- Watchers: 379
- Average over the last week: 58 per day
- Usual pace: 62 per day
- Stars in the last hour (measured): 3
- Latest release: v0.1.913-beta (2026-10-30)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 30, 47, 48, 144, 142, 114, 80, 87, 93, 67, 62, 78, 55, 67, 36, 61, 54, 62, 69, 44, 51, 46, 51, 48, 83, 52, 56, 66, 53, 48

## Magnitude by day, last 14 days

10-16 2.8, 10-17 2.7, 10-18 2.7, 10-19 2.5, 10-20 2.7, 10-25 2.4, 10-26 2.5, 10-27 2.6, 10-28 3.1, 10-29 3.6, 10-30 2.9, 10-31 2.8, 11-01 3.0, 11-02 2.9

## Similar by description

1. **ollama/ollama** — 3.6 · Steady · Language models · Go · +118 stars measured 2026-11-02, 00:09–23:04 UTC
   Run open language models (Kimi, GLM, DeepSeek, Qwen, Gemma and more) locally via CLI and REST API with integrations into editors and assistants.
   Full card: https://gitnova.dev/en/r/ollama/ollama.md
2. **techjarves/Portable-Local-Studio** — 5.0 · Breakout · Apps · JavaScript · +62 stars measured 2026-11-02, 00:07–23:03 UTC
   Offline local AI studio for Windows, Linux and macOS with a zero-setup GUI: image generation (Stable Diffusion), GGUF LLM chat, speech-to-text (Whisper) and text-to-speech (Kokoro TTS).
   Full card: https://gitnova.dev/en/r/techjarves/Portable-Local-Studio.md
3. **lemonade-sdk/lemonade** — 1.9 · Steady · Language models · C++ · +31 stars measured 2026-11-02, 00:15–23:09 UTC
   A local AI server that runs optimized LLMs, whisper, TTS, and image generation on the user's GPU and NPU, exposing OpenAI-, Anthropic-, and Ollama-compatible APIs. Available as a service or an embeddable binary for apps.
   Full card: https://gitnova.dev/en/r/lemonade-sdk/lemonade.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 23:16 UTC, updated every 30 minutes.