← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Ultra (60c) · 256 GB · 4bit · 2026-03-16

Performance

195k

tokens

236.9

PP tok/s

12.6

TG tok/s

844248

TTFT (ms)

83.4

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.2.13

macOS macOS 26.3

Context 200,000

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
128k	318.6	17.2	77.4 GB	view
195k	236.9	12.6	83.4 GB	current