← Back to community benchmarks

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

M1 Max (24c) · 32 GB · 4bit · 2026-05-09

Performance

16k

tokens

696.2

PP tok/s

53.8

TG tok/s

23533

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.9.dev1

macOS macOS 15.7.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	616.3	64.2	19.9 GB	view
4k	771.1	62.9	20.7 GB	view
8k	766.5	59.0	21.2 GB	view
16k	696.2	53.8	21.9 GB	current