← Back to community benchmarks
Qwen3-Coder-30B-A3B-Instruct
Performance
1k
tokens
419.6
PP tok/s
54.7
TG tok/s
2440
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 419.6 | 54.7 | 16.6 GB | current |
| 4k | 386.2 | 45.8 | 17.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.7 | 1.00× |
| 2× | 72.7 | 1.33× |
| 4× | 82.6 | 1.51× |