← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 64 GB · 4bit · 2026-04-19

Performance

64k

tokens

792.5

PP tok/s

30.1

TG tok/s

82696

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 15.7.4

Context 65,536