← Back to community benchmarks

Qwen3.6-27B-FP8-source-oQ4-mtp

M4 Max (40c) · 128 GB · 4bit · 2026-05-08

Performance

1k

tokens

236.1

PP tok/s

36.6

TG tok/s

4338

TTFT (ms)

16.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	236.1	36.6	16.9 GB	current
4k	188.7	30.4	18.4 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.6	1.00×
2×	42.3	1.16×
4×	46.0	1.26×