← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (20c) · 64 GB · 4bit · 2026-05-13
Performance
32k
tokens
407.7
PP tok/s
21.6
TG tok/s
80371
TTFT (ms)
22.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 421.3 25.5 16.8 GB view
32k 407.7 21.6 22.6 GB current
Batching Results
Batch Size TG tok/s Speedup
25.5 1.00×
31.2 1.22×
41.4 1.62×