← Back to community benchmarks

Qwen3.5-27BMTP

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-14

Performance

4k

tokens

316.7

PP tok/s

30.9

TG tok/s

12933

TTFT (ms)

30.3

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.3.9.dev2

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	294.0	31.9	28.8 GB	view
4k	316.7	30.9	30.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	31.9	1.00×
2×	39.3	1.23×
4×	50.1	1.57×