Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
unslothai/unsloth is accelerating — star growth is speeding up by +8.6/day (93rd percentile in the tracked cohort), on top of +54.3 stars/day. A recent release is helping fuel the run.
Release count rose to 83.
Release count rose to 82.
Release count rose to 81.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/unslothai/unsloth)Elevated breakout odds over the next 14 days, led by star acceleration (93th pctl) and star velocity (91th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Reconstructed from 384 snapshots — the time-series GitHub’s API doesn’t expose.
Release count rose to 80.
Release count rose to 79.
Release count rose to 78.
Release count rose to 77.
Release count rose to 76.
Release count rose to 75.
Release count rose to 74.
Release count rose to 73.
Release count rose to 73.