← Back to community benchmarks

Qwen3.6-35B-A3BVL-oQ8

M1 Max (32c) · 64 GB · 8bit · 2026-05-12

Performance

16k

tokens

486.5

PP tok/s

43.6

TG tok/s

33675

TTFT (ms)

37.3

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.9.dev1

macOS macOS 15.6.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	578.0	51.0	35.3 GB	view
4k	636.0	49.7	36.1 GB	view
8k	540.0	48.6	36.6 GB	view
16k	486.5	43.6	37.3 GB	current
32k	429.3	40.8	38.8 GB	view
64k	351.8	32.7	41.8 GB	view