← Back to community benchmarks

Qwen3.6-35B-A3B-oQ2

M5 (10c) · 24 GB · 2bit · 2026-04-27

Performance

4k

tokens

558.0

PP tok/s

49.9

TG tok/s

7341

TTFT (ms)

13.1

Peak mem (GB)

Hardware

Chip M5 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	658.9	154.9	13.7 GB	view
4k	558.0	49.9	13.1 GB	current
8k	1,160	48.1	13.4 GB	view