← Back to community benchmarks

Qwopus3.6-27B-v1-preview

M3 Max (30c) · 96 GB · 4bit · 2026-04-29
Performance
16k
tokens
91.3
PP tok/s
7.3
TG tok/s
179531
TTFT (ms)
19.1
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.3.8rc1
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 138.5 12.6 15.8 GB view
4k 102.3 5.4 17.3 GB view
8k 37.6 6.0 17.9 GB view
16k 91.3 7.3 19.1 GB current
32k 72.8 5.8 21.6 GB view
Batching Results
Batch Size TG tok/s Speedup
12.6 1.00×
13.2 1.05×
17.6 1.40×
20.4 1.62×