← Back to community benchmarks

Qwen3.6-27B-oQ8-mtp

M3 Ultra (80c) · 512 GB · 8bit · 2026-05-14
Performance
1k
tokens
381.1
PP tok/s
30.4
TG tok/s
2687
TTFT (ms)
28.8
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 381.1 30.4 28.8 GB current
4k 417.5 31.0 30.3 GB view
8k 413.1 30.1 31.3 GB view
16k 399.7 27.6 32.8 GB view
32k 381.6 26.7 35.8 GB view
Batching Results
Batch Size TG tok/s Speedup
30.4 1.00×
37.9 1.25×
50.9 1.67×
68.3 2.25×