← Back to community benchmarks

Qwen3.6-27B

M3 Ultra (80c) · 256 GB · 8bit · 2026-06-15

Performance

4k

tokens

415.6

PP tok/s

20.7

TG tok/s

9857

TTFT (ms)

34.6

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 256 GB

GPU Cores 80

Software

oMLX v0.4.4rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	376.5	20.8	33.0 GB	view
4k	415.6	20.7	34.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	20.8	1.00×
2×	26.1	1.25×
4×	43.2	2.08×
8×	62.5	3.00×