← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
1k
tokens
562.8
PP tok/s
56.3
TG tok/s
1820
TTFT (ms)
66.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.13
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 562.8 | 56.3 | 66.3 GB | current |
| 4k | 580.4 | 53.5 | 66.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 56.3 | 1.00× |
| 2× | 83.8 | 1.49× |
| 4× | 113.9 | 2.02× |