← Back to community benchmarks
Qwen3-30B-A3B
Performance
4k
tokens
466.2
PP tok/s
46.3
TG tok/s
8785
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
32 GB
GPU Cores
32
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 | 465.3 | 58.7 | 16.6 GB | view |
| 4k | 466.2 | 46.3 | 17.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.7 | 1.00× |
| 2× | 77.9 | 1.33× |
| 4× | 94.2 | 1.60× |