← Back to community benchmarks
Qwen3-30B-A3B-Instruct-2507
Performance
1k
tokens
411.0
PP tok/s
44.8
TG tok/s
2491
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 411.0 | 44.8 | 16.6 GB | current |
| 4k | 394.8 | 35.0 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 44.8 | 1.00× |
| 2× | 59.1 | 1.32× |
| 4× | 68.1 | 1.52× |