← Back to community benchmarks

Qwen3.6-35B-A3B-MTP

M3 Ultra (80c) · 96 GB · 4bit · 2026-07-12

Performance

64k

tokens

1,631

PP tok/s

73.8

TG tok/s

40183

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 96 GB

GPU Cores 80

Software

oMLX v0.5.0

macOS macOS 26.5.2

Context 65,536