← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
966.3
PP tok/s
80.4
TG tok/s
1060
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 966.3 | 80.4 | 16.6 GB | current |
| 4k | 1,021 | 64.7 | 17.1 GB | view |
| 8k | 878.6 | 52.0 | 17.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 80.4 | 1.00× |
| 2× | 98.9 | 1.23× |
| 4× | 148.1 | 1.84× |
| 8× | 186.2 | 2.32× |