← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (60c) · 256 GB · 8bit · 2026-05-17
Performance
32k
tokens
292.2
PP tok/s
27.5
TG tok/s
112142
TTFT (ms)
35.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 309.0 29.0 32.1 GB view
32k 292.2 27.5 35.8 GB current
64k 256.7 23.3 41.8 GB view
128k 202.9 18.7 54.2 GB view