← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4e-fp16-mtp

M1 Max (32c) · 64 GB · 4bit · 2026-07-14

Performance

4k

tokens

467.6

PP tok/s

40.6

TG tok/s

8759

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	467.6	40.6	20.8 GB	current
16k	414.0	30.4	21.1 GB	view
64k	284.4	24.4	22.0 GB	view