← Back to community benchmarks

Qwen3.5-122B-A10B6.5bit

M3 Ultra (60c) · 256 GB · 6bit · 2026-03-24

Performance

4k

tokens

713.4

PP tok/s

45.9

TG tok/s

5742

TTFT (ms)

95.5

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.2.20.dev2

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	713.4	45.9	95.5 GB	current
32k	597.3	34.8	99.7 GB	view