← Back to community benchmarks

Qwen3.5-35B-A3Bvlm

M1 Max (32c) · 64 GB · 4bit · 2026-03-17

Performance

16k

tokens

584.8

PP tok/s

41.7

TG tok/s

28015

TTFT (ms)

19.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.2.13

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	588.1	63.1	19.1 GB	view
4k	618.6	60.9	19.2 GB	view
8k	613.2	42.6	19.4 GB	view
16k	584.8	41.7	19.8 GB	current