← Back to community benchmarks

Qwen3.6-27B-oQ8e-mtp

M3 Ultra (80c) · 512 GB · 8bit · 2026-07-17
Performance
16k
tokens
407.3
PP tok/s
20.6
TG tok/s
40230
TTFT (ms)
31.4
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.5.1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 418.3 21.6 28.3 GB view
4k 427.5 21.4 29.5 GB view
8k 422.2 18.1 30.2 GB view
16k 407.3 20.6 31.4 GB current
32k 379.1 19.6 32.7 GB view
64k 334.1 18.0 36.1 GB view
128k 269.4 15.6 42.1 GB view