← Back to community benchmarks

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

M2 Max (38c) · 96 GB · 4bit · 2026-05-13
Performance
8k
tokens
148.1
PP tok/s
14.6
TG tok/s
55317
TTFT (ms)
17.9
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.3.8
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 174.8 15.9 15.8 GB view
4k 151.8 15.3 17.3 GB view
8k 148.1 14.6 17.9 GB current
16k 143.1 13.8 19.1 GB view
Batching Results
Batch Size TG tok/s Speedup
15.9 1.00×
20.2 1.27×
25.5 1.60×
30.7 1.93×