← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
530.9
PP tok/s
36.4
TG tok/s
30860
TTFT (ms)
97.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.0
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 16k | 530.9 | 36.4 | 97.3 GB | current |
| 32k | 470.6 | 29.5 | 99.7 GB | view |