← Back to community benchmarks

Qwen3.5-122B-A10B

M4 Max (40c) · 128 GB · 4bit · 2026-03-20
Performance
4k
tokens
597.8
PP tok/s
52.5
TG tok/s
6851
TTFT (ms)
67.9
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.19
macOS macOS 15.7.4
Context 4,096