← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

M1 Max (32c) · 32 GB · 4bit · 2026-04-30

Performance

1k

tokens

491.0

PP tok/s

61.1

TG tok/s

2086

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8rc1

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	491.0	61.1	20.1 GB	current
4k	590.1	57.5	20.9 GB	view
8k	596.4	53.1	21.2 GB	view
16k	574.5	44.5	21.8 GB	view
32k	523.7	31.9	23.2 GB	view