← Back to community benchmarks

Qwen3.5-122B-A10B3.7bit-VL

M1 Max (32c) · 64 GB · 3bit · 2026-04-03

Performance

16k

tokens

182.5

PP tok/s

23.5

TG tok/s

89786

TTFT (ms)

56.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.2

macOS macOS 26.3.1

Context 16,384