← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
16k
tokens
1,781
PP tok/s
54.4
TG tok/s
9198
TTFT (ms)
18.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.2rc1
macOS
macOS 26.5.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 4k | 2,071 | 79.7 | 17.1 GB | view |
| 16k | 1,781 | 54.4 | 18.6 GB | current |