← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
959.8
PP tok/s
211.2
TG tok/s
1067
TTFT (ms)
17.7
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
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 959.8 | 211.2 | 17.7 GB | current |
| 4k | 419.2 | 61.6 | 17.9 GB | view |