← Back to community benchmarks

Qwen3.6-27B-oQ6-fp16-mtp

M5 Max (40c) · 48 GB · 6bit · 2026-05-15
Performance
8k
tokens
811.3
PP tok/s
22.4
TG tok/s
10098
TTFT (ms)
24.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 48 GB
GPU Cores 40
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 751.7 23.4 22.6 GB view
4k 843.2 18.6 24.0 GB view
8k 811.3 22.4 24.6 GB current
Batching Results
Batch Size TG tok/s Speedup
23.4 1.00×
37.7 1.61×
38.1 1.63×