← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
64k
tokens
379.2
PP tok/s
23.6
TG tok/s
172835
TTFT (ms)
77.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.21
macOS
macOS 26.3
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 565.4 | 47.3 | 66.4 GB | view |
| 4k | 598.9 | 45.5 | 67.9 GB | view |
| 8k | 585.8 | 42.8 | 68.5 GB | view |
| 16k | 549.1 | 38.4 | 69.7 GB | view |
| 32k | 483.9 | 31.9 | 72.1 GB | view |
| 64k | 379.2 | 23.6 | 77.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.3 | 1.00× |
| 2× | 77.4 | 1.64× |
| 4× | 102.6 | 2.17× |