← Back to community benchmarks
Qwen3-30B-A3B
Performance
1k
tokens
1,325
PP tok/s
104.8
TG tok/s
773
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
48 GB
GPU Cores
40
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,325 | 104.8 | 15.8 GB | current |
| 4k | 1,410 | 86.8 | 16.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 104.8 | 1.00× |
| 2× | 164.6 | 1.57× |
| 4× | 216.8 | 2.07× |