← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 64 GB · 4bit · 2026-05-07
Performance
32k
tokens
381.5
PP tok/s
21.3
TG tok/s
85895
TTFT (ms)
23.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 430.4 24.5 16.8 GB view
4k 468.1 25.6 18.2 GB view
8k 466.2 24.7 19.2 GB view
16k 418.0 23.5 20.7 GB view
32k 381.5 21.3 23.7 GB current
64k 314.9 16.8 29.8 GB view