← Back to community benchmarks

Qwen3.6-35B-A3B-HereticoQ4

M4 Max (40c) · 64 GB · 4bit · 2026-04-18

Performance

64k

tokens

1,086

PP tok/s

57.7

TG tok/s

60373

TTFT (ms)

25.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.0.1

Context 65,536