Unsloth
Model Serving & MLOpsFeatures
- Run inference on GGUF, LoRA adapters, and safetensors models locally
- Export trained models to multiple formats (GGUF, 16‑bit safetensors, etc.)
- Accelerate training up to 2× faster with up to 70 % less VRAM
Recent releases
View all 31 releases →
No immediate action
v0.1.48-beta
Breaking risk
Studio export, Llama-swap API, performance boosts
Review required
v0.1.47-beta
Breaking risk
Auth
RBAC
GLM 5.2, longer context, Chat Canvas, Hub redesign, Secure mode
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
About
Stars
68,386
Forks
6,152
Languages
Python
TypeScript
PowerShell
Install & Platforms
Install via
shell-script
binary
Platforms
linux
macos
windows
