← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

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

Performance

8k

tokens

596.4

PP tok/s

53.1

TG tok/s

13736

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.8rc1

macOS macOS 26.2

Context 8,192

Performance by Context Length

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