← Back to community benchmarks

Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-oQ8

M3 Ultra (80c) · 512 GB · 8bit · 2026-06-21
Performance
16k
tokens
408.0
PP tok/s
21.0
TG tok/s
40161
TTFT (ms)
32.3
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.4.4
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 418.9 22.3 29.8 GB view
8k 419.0 21.9 30.8 GB view
16k 408.0 21.0 32.3 GB current
32k 382.1 20.2 35.3 GB view