← Back to community benchmarks

Qwen3.6-27B

M1 Ultra (48c) · 64 GB · 4bit · 2026-06-04

Performance

4k

tokens

140.2

PP tok/s

21.3

TG tok/s

29213

TTFT (ms)

16.5

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 64 GB

GPU Cores 48

Software

oMLX v0.4.0rc2

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	134.9	22.2	15.1 GB	view
4k	140.2	21.3	16.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	22.2	1.00×
2×	26.4	1.19×
4×	29.2	1.32×