← Back to community benchmarks

Qwopus3.6-27B-v2-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-05-23
Performance
16k
tokens
753.8
PP tok/s
16.0
TG tok/s
21735
TTFT (ms)
32.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 726.8 16.9 28.4 GB view
4k 848.0 16.6 29.8 GB view
8k 830.9 16.3 30.8 GB view
16k 753.8 16.0 32.3 GB current
32k 651.6 15.4 35.3 GB view