← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
8k
tokens
569.3
PP tok/s
50.2
TG tok/s
14389
TTFT (ms)
64.0
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.4
macOS
macOS 26.4
Context
8,192