← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M4 Pro (16c) · 24 GB · 4bit · 2026-05-19
Performance
1k
tokens
405.8
PP tok/s
61.9
TG tok/s
2523
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 405.8 61.9 16.6 GB current
4k 594.1 59.9 17.1 GB view
Batching Results
Batch Size TG tok/s Speedup
61.9 1.00×
90.3 1.46×
96.7 1.56×