Unsloth

OTR ACTIVE STEADY

unslothai/unsloth · homepage ↗

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

fine-tuning
llama
llms
mistral
gemma
llama3

stars 68k

last activity today

open issues 789

language Python

license Apache-2.0

latest release v0.1.471-beta

momentum · per month since covered + 2k/mo (+8%/mo) · + 38k total since PR#2

metrics as of today

star history

Exact curve on star-history.com ↗

PR#2 30k★ 2025-02-19
now 68k★ + 38k since first covered

curve is sampled from GitHub's star history; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

covered in

PR#2 2025-02-19 on the radar

Faster, Memory-Efficient Fine-Tuning for LLMs

// comments

COMING SOON