← Back to community benchmarks

Qwen3.6-27B-UD-Q8_K_XL

M3 Ultra (60c) · 96 GB · 8bit · 2026-05-03
User commentTurboQuant 8-bit
Performance
64k
tokens
249.3
PP tok/s
14.3
TG tok/s
262907
TTFT (ms)
41.0
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 311.6 21.6 31.6 GB view
64k 249.3 14.3 41.0 GB current
128k 198.5 12.8 55.5 GB view