← Back to community benchmarks

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

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

Performance

16k

tokens

770.3

PP tok/s

56.6

TG tok/s

21271

TTFT (ms)

21.1

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 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,015	61.5	20.8 GB	view
16k	770.3	56.6	21.1 GB	current
64k	480.9	44.0	22.2 GB	view