← Back to community benchmarks

Qwen3.5-122B-A10B

M4 Max (40c) · 128 GB · 4bit · 2026-03-09
Performance
16k
tokens
521.0
PP tok/s
40.7
TG tok/s
31444
TTFT (ms)
67.7
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 552.8 46.5 67.0 GB view
16k 521.0 40.7 67.7 GB current