← Back to community benchmarks

Qwen3.6-27B4bit-MTP

M5 Max (40c) · 128 GB · 4bit · 2026-05-21

Performance

32k

tokens

755.8

PP tok/s

39.2

TG tok/s

43357

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	792.3	41.7	16.1 GB	view
4k	891.6	47.5	17.5 GB	view
32k	755.8	39.2	21.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	41.7	1.00×
2×	58.5	1.40×
4×	76.7	1.84×