← Back to community benchmarks

Qwen3.6-27B-oQ4-fp16-mtp

M5 Pro (16c) · 48 GB · 4bit · 2026-06-17
Performance
16k
tokens
344.6
PP tok/s
16.2
TG tok/s
47539
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.4.3
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 341.4 17.4 16.0 GB view
4k 365.3 17.1 17.1 GB view
8k 371.5 16.9 18.9 GB view
16k 344.6 16.2 20.4 GB current
Batching Results
Batch Size TG tok/s Speedup
17.4 1.00×
28.0 1.61×