← Back to community benchmarks

Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-mxfp8

M4 Max (32c) · 36 GB · 8bit · 2026-03-14

Performance

1k

tokens

187.5

PP tok/s

13.0

TG tok/s

5460

TTFT (ms)

27.5

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.2.11

macOS macOS 26.3.1

Context 1,024