← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M3 Ultra (60c) · 96 GB · 4bit · 2026-05-14

Performance

1k

tokens

304.4

PP tok/s

46.5

TG tok/s

3364

TTFT (ms)

16.7

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	46.5	1.00×
2×	57.3	1.23×
4×	64.3	1.38×