← Back to community benchmarks
Qwen3.5-122B-A10B-Text-mxfp4
Performance
195k
tokens
158.4
PP tok/s
7.7
TG tok/s
1262537
TTFT (ms)
90.6
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.2
macOS
macOS 26.4
Context
200,000