← Back to community benchmarks
Qwen3-30B-A3B-Instruct-2507
Performance
4k
tokens
2,496
PP tok/s
75.3
TG tok/s
1641
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.5
macOS
macOS 26.4
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,874 | 91.9 | 16.6 GB | view |
| 4k | 2,496 | 75.3 | 17.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.9 | 1.00× |
| 2× | 127.3 | 1.39× |
| 4× | 159.3 | 1.73× |