← Back to community benchmarks

Qwen3.5-35B-A3Blm

M4 Max (40c) · 48 GB · 4bit · 2026-04-15

Performance

16k

tokens

1,556

PP tok/s

85.7

TG tok/s

10528

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,328	120.4	18.3 GB	view
4k	1,652	59.5	19.1 GB	view
8k	1,676	107.9	19.4 GB	view
16k	1,556	85.7	20.0 GB	current
32k	1,307	65.9	21.4 GB	view
64k	1,027	42.6	24.1 GB	view