← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 4bit · 2026-06-20
Performance
128k
tokens
250.5
PP tok/s
10.4
TG tok/s
523295
TTFT (ms)
37.0
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.4
macOS macOS 27.0
Context 131,072