← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (32c) · 64 GB · 4bit · 2026-04-29

Performance

64k

tokens

391.7

PP tok/s

21.8

TG tok/s

167309

TTFT (ms)

25.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8rc1

macOS macOS 26.3.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	424.0	125.6	20.6 GB	view
4k	391.0	58.3	20.0 GB	view
8k	595.5	54.4	20.4 GB	view
16k	549.7	45.1	21.0 GB	view
32k	486.1	33.7	22.4 GB	view
64k	391.7	21.8	25.0 GB	current
128k	257.7	13.2	30.4 GB	view