← Back to community benchmarks
Qwen3-30B-A3B-Instruct-2507
Performance
4k
tokens
313.0
PP tok/s
33.7
TG tok/s
13087
TTFT (ms)
17.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
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 | 348.5 | 42.5 | 16.6 GB | view |
| 4k | 313.0 | 33.7 | 17.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 42.5 | 1.00× |
| 2× | 56.6 | 1.33× |
| 4× | 61.6 | 1.45× |