← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M5 Max (40c) · 128 GB · 8bit · 2026-04-17

Performance

16k

tokens

3,577

PP tok/s

85.8

TG tok/s

4580

TTFT (ms)

37.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,140	98.0	35.4 GB	view
4k	3,585	95.1	36.2 GB	view
8k	3,832	91.7	36.5 GB	view
16k	3,577	85.8	37.1 GB	current
32k	3,166	74.0	38.5 GB	view
64k	2,294	56.3	41.2 GB	view
128k	1,315	37.3	46.5 GB	view