← Back to community benchmarks

Qwen3.6-27B-UD4bit

M2 Max (38c) · 96 GB · 4bit · 2026-04-30

Performance

4k

tokens

201.7

PP tok/s

13.6

TG tok/s

20307

TTFT (ms)

26.6

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	191.6	13.8	25.2 GB	view
4k	201.7	13.6	26.6 GB	current
8k	196.3	13.2	27.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	13.8	1.00×
2×	15.6	1.13×
4×	24.8	1.80×