← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
4k
tokens
1,911
PP tok/s
73.5
TG tok/s
2143
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.19
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,702 | 89.6 | 16.6 GB | view |
| 4k | 1,911 | 73.5 | 17.1 GB | current |