← Back to community benchmarks

Qwopus3.6-27B-v2-oQ6-fp16-mtp

M2 Max (38c) · 96 GB · 6bit · 2026-06-04
Performance
8k
tokens
177.1
PP tok/s
18.0
TG tok/s
46248
TTFT (ms)
24.8
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 96 GB
GPU Cores 38
Software
oMLX v0.4.1
macOS macOS 15.7.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 177.5 20.4 22.8 GB view
4k 186.5 19.2 24.2 GB view
8k 177.1 18.0 24.8 GB current
16k 180.4 15.5 26.1 GB view
32k 170.2 14.2 28.6 GB view
64k 151.1 11.1 33.6 GB view
Batching Results
Batch Size TG tok/s Speedup
20.4 1.00×
19.4 0.95×
21.7 1.06×
44.6 2.19×