← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M5 Pro (16c) · 48 GB · 4bit · 2026-05-12
Performance
1k
tokens
360.2
PP tok/s
16.8
TG tok/s
2843
TTFT (ms)
16.5
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 360.2 16.8 16.5 GB current
8k 385.4 16.2 18.5 GB view
64k 273.9 2.7 27.3 GB view
Batching Results
Batch Size TG tok/s Speedup
16.8 1.00×
25.4 1.51×
28.5 1.70×