← Back to community benchmarks

Qwen3.6-27B4bit-MTP

M5 Max (40c) · 128 GB · 4bit · 2026-05-19
Performance
32k
tokens
757.6
PP tok/s
28.9
TG tok/s
43254
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 742.4 32.4 15.8 GB view
4k 870.7 32.4 17.3 GB view
32k 757.6 28.9 21.6 GB current
Batching Results
Batch Size TG tok/s Speedup
32.4 1.00×
59.4 1.83×
76.1 2.35×