← Back to community benchmarks

Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive

M4 Max (40c) · 128 GB · 4bit · 2026-04-27

Performance

4k

tokens

1,581

PP tok/s

97.9

TG tok/s

2591

TTFT (ms)

19.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,132	102.9	18.3 GB	view
4k	1,581	97.9	19.0 GB	current
8k	1,573	91.5	19.4 GB	view
16k	1,470	84.1	20.0 GB	view
32k	1,154	71.7	21.3 GB	view
64k	853.9	40.3	24.0 GB	view