← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
16k
tokens
507.8
PP tok/s
39.9
TG tok/s
32265
TTFT (ms)
63.3
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
16,384