Qwen
Qwen/Qwen3-30B-A3B

OverviewRuns

Quantizations

QuantQuantized bySizeDecodePrefillScoreActions
4bitMLX's logo.
MLX Community
MLX Community		16.0 GB98.3 tok/s1,233.2 tok/sRuns well

Device Comparison

Results include trials with 4,096 input tokens and 1,024 output tokens only.

Decode / Prefill Speeds

1 device