← Back to community benchmarks

Qwen3-Coder-30B-A3B-Instruct

M3 Max (30c) · 36 GB · 4bit · 2026-03-10
Performance
4k
tokens
892.5
PP tok/s
61.6
TG tok/s
4589
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 853.3 74.2 16.6 GB view
4k 892.5 61.6 17.1 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 74.2 1.00×
2× 111.1 1.50×
4× 144.4 1.95×