← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Max (24c) · 32 GB · 3bit · 2026-04-05

Performance

64k

tokens

462.0

PP tok/s

24.8

TG tok/s

141852

TTFT (ms)

23.3

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.4

macOS macOS 26.3.1

Context 65,536