← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
4k
tokens
312.1
PP tok/s
38.7
TG tok/s
13126
TTFT (ms)
17.2
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
32 GB
GPU Cores
19
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 295.6 | 48.6 | 16.6 GB | view |
| 4k | 312.1 | 38.7 | 17.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 48.6 | 1.00× |
| 2× | 59.6 | 1.23× |
| 4× | 68.8 | 1.42× |