← Back to community benchmarks

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

M5 Max (40c) · 48 GB · 4bit · 2026-05-23
Performance
1k
tokens
781.3
PP tok/s
33.4
TG tok/s
1311
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 781.3 33.4 15.8 GB current
4k 833.0 32.7 17.3 GB view
Batching Results
Batch Size TG tok/s Speedup
33.4 1.00×
55.2 1.65×
67.2 2.01×
72.3 2.16×