← Back to community benchmarks
Qwen3-30B-A3B-Instruct-2507
Performance
1k
tokens
758.7
PP tok/s
76.8
TG tok/s
1350
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
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 | 758.7 | 76.8 | 16.6 GB | current |
| 4k | 719.1 | 62.0 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 76.8 | 1.00× |
| 2× | 105.0 | 1.37× |
| 4× | 124.4 | 1.62× |