← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-fp16-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-06-05

Performance

8k

tokens

1,814

PP tok/s

98.6

TG tok/s

4516

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.4.0

macOS macOS 26.5.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,147	108.2	19.9 GB	view
4k	1,794	103.3	20.7 GB	view
8k	1,814	98.6	21.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	108.2	1.00×
2×	165.5	1.53×
4×	227.8	2.11×