← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
32k
tokens
437.8
PP tok/s
29.5
TG tok/s
74854
TTFT (ms)
64.7
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.11
macOS
macOS 26.3
Context
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 32k | 437.8 | 29.5 | 64.7 GB | current |
| 64k | 348.8 | 19.2 | 67.5 GB | view |