← Back to community benchmarks

Qwen3.6-35B-A3B-Kimi-K2.6-Reasoning-Distilled-oQ4e

M4 Max (32c) · 36 GB · 4bit · 2026-05-07

Performance

8k

tokens

418.8

PP tok/s

53.1

TG tok/s

19562

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M4 Max (32c)

Memory 36 GB

GPU Cores 32

Software

oMLX v0.3.8

macOS macOS 15.1.1

Context 8,192