← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
32k
tokens
1,072
PP tok/s
40.3
TG tok/s
30572
TTFT (ms)
19.6
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.4.4
macOS
macOS 26.5.2
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 8k | 1,610 | 56.7 | 17.5 GB | view |
| 32k | 1,072 | 40.3 | 19.6 GB | current |