← Back to community benchmarks

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

M5 Pro (16c) · 48 GB · 4bit · 2026-05-15
Performance
1k
tokens
354.8
PP tok/s
18.0
TG tok/s
2886
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.9.dev2
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 354.8 18.0 15.8 GB current
4k 389.7 17.6 17.3 GB view
Batching Results
Batch Size TG tok/s Speedup
18.0 1.00×
29.7 1.65×
36.2 2.01×