← Back to community benchmarks

Qwen3.6-27B-MTPLX-Optimized-Speed

M4 Pro (16c) · 48 GB · 4bit · 2026-05-22
Performance
4k
tokens
101.3
PP tok/s
15.3
TG tok/s
40449
TTFT (ms)
17.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 100.6 15.8 15.8 GB view
4k 101.3 15.3 17.3 GB current
8k 96.0 14.4 18.3 GB view
16k 82.5 12.9 19.8 GB view
32k 77.4 11.1 22.8 GB view
Batching Results
Batch Size TG tok/s Speedup
15.8 1.00×
19.9 1.26×
24.5 1.55×