← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M4 Pro (20c) · 48 GB · 4bit · 2026-04-18
Performance
8k
tokens
687.4
PP tok/s
52.8
TG tok/s
11918
TTFT (ms)
17.4
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 811.2 78.8 16.6 GB view
4k 805.4 64.9 17.1 GB view
8k 687.4 52.8 17.4 GB current
16k 490.4 37.8 18.2 GB view
Batching Results
Batch Size TG tok/s Speedup
78.8 1.00×
101.9 1.29×