← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-VLMoQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-28

Performance

128k

tokens

1,417

PP tok/s

42.9

TG tok/s

92504

TTFT (ms)

31.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 131,072