← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
4k
tokens
406.7
PP tok/s
36.8
TG tok/s
10071
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
4,096