← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
4k
tokens
862.2
PP tok/s
32.2
TG tok/s
4750
TTFT (ms)
24.1
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 695.1 | 36.6 | 23.7 GB | view |
| 4k | 862.2 | 32.2 | 24.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.6 | 1.00× |
| 2× | 50.4 | 1.38× |
| 4× | 56.3 | 1.54× |