← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-09
Performance
8k
tokens
317.2
PP tok/s
30.6
TG tok/s
25823
TTFT (ms)
31.3
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.9.dev1
macOS macOS 26.4
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 296.2 31.5 28.8 GB view
4k 318.7 31.9 30.3 GB view
8k 317.2 30.6 31.3 GB current
16k 308.6 28.6 32.8 GB view
32k 288.6 26.9 35.8 GB view
64k 221.5 22.1 41.8 GB view