← Back to community benchmarks

Qwen3.6-27B-oQ6-mtp

M3 Ultra (80c) · 512 GB · 6bit · 2026-05-14
Performance
4k
tokens
411.3
PP tok/s
37.1
TG tok/s
9958
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.3.9.dev1
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 381.3 35.2 23.0 GB view
4k 411.3 37.1 24.4 GB current
8k 406.6 34.6 25.4 GB view
16k 395.7 32.9 26.9 GB view
32k 374.9 31.2 29.9 GB view
Batching Results
Batch Size TG tok/s Speedup
35.2 1.00×
45.1 1.28×
56.0 1.59×
62.5 1.78×