← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
4k
tokens
433.2
PP tok/s
60.3
TG tok/s
9456
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 957.7 | 209.1 | 17.7 GB | view |
| 4k | 433.2 | 60.3 | 17.9 GB | current |