← Back to community benchmarks

Qwen3.6-27B-oQ4-mtp

M2 Pro (16c) · 32 GB · 4bit · 2026-05-21
Performance
4k
tokens
47.8
PP tok/s
10.2
TG tok/s
85765
TTFT (ms)
18.2
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.9rc1
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 47.4 9.7 16.7 GB view
4k 47.8 10.2 18.2 GB current
Batching Results
Batch Size TG tok/s Speedup
9.7 1.00×
11.9 1.23×
12.3 1.27×