Qwen3-0.6B

BaseRT .base builds of Qwen/Qwen3-0.6B for fast local inference on Apple Silicon (Metal).

Files

File	Precision	Size
Qwen3-0.6B-Q4.base	4-bit	430 MB
Qwen3-0.6B-Q8.base	8-bit	782 MB

Usage

curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/Qwen3-0.6B
basert chat basecompute/Qwen3-0.6B

Released under the apache-2.0 license, inherited from the base model.