← Back to community benchmarks

Qwen3.6-35B-A3BVLM-oQ8

M1 Ultra (64c) · 64 GB · 8bit · 2026-04-24

Performance

8k

tokens

1,015

PP tok/s

224.3

TG tok/s

8074

TTFT (ms)

37.9

Peak mem (GB)

Hardware

Chip M1 Ultra (64c)

Memory 64 GB

GPU Cores 64

Software

oMLX v0.3.8.dev1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,516	267.8	36.7 GB	view
4k	946.6	223.6	37.8 GB	view
8k	1,015	224.3	37.9 GB	current
16k	844.1	176.4	38.6 GB	view