← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 64 GB · 4bit · 2026-03-09

Performance

16k

tokens

1,069

PP tok/s

62.9

TG tok/s

15329

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 26.3

Context 16,384