Unsloth
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Unsloth scores 8.3/10 (Strong) in Fine-Tuning.
Language Python License Apache-2.0 Stars 67.8k★ Type library Self-host Yes Repo unslothai/unsloth Homepage https://unsloth.ai
Quality
Strong 8.3
Adoption 71
Activity 96
Maturity 94
Community 70
Capability 50
Show the math
Overall 8.3/10
value = 8.3/10
score = value
Adoption 7.4/10
value = 70.8/100
score = 1 + 9 * value / 100
Activity 9.7/10
value = 96.4/100
score = 1 + 9 * value / 100
Maturity 9.5/10
value = 94.1/100
score = 1 + 9 * value / 100
Community 7.3/10
value = 70.2/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
67.8k★ GitHub stars
1.1k/90d Recent commits
29 devs/90d Recent contributors
2.6y Project age
active Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
fine-tuning lora triton memory-efficient single-gpu