← Back to community benchmarks

Qwen3.5-122B-A10B-Text-mxfp4

M4 Max (40c) · 128 GB · 4bit · 2026-03-14
Performance
128k
tokens
234.8
PP tok/s
11.6
TG tok/s
558161
TTFT (ms)
73.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.11
macOS macOS 26.3
Context 131,072