Params
8B
Fastest decode
48.3 tok/s
M4 Pro · 4-bit MLX · rapid-mlx
Refusal
Official
Setups
1
Best reported pair · not live serving speed ↗
Runs on
Quoted one-stream decode on real boxes.
No public weights link on this desk yet.
Qwen3-8B
Qwen · dense
View all