← Back to community benchmarks
Qwen3-30B-A3B-Instruct-2507
Performance
1k
tokens
251.4
PP tok/s
39.1
TG tok/s
4074
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M1 Pro (16c)
Memory
32 GB
GPU Cores
16
Software
oMLX
v0.3.6
macOS
macOS 26.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 251.4 | 39.1 | 16.6 GB | current |
| 4k | 253.5 | 31.9 | 17.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.1 | 1.00× |
| 2× | 48.0 | 1.23× |
| 4× | 54.5 | 1.39× |
| 8× | 63.7 | 1.63× |