← Back to community benchmarks

Qwopus3.5-27B-v3-vision

M2 Ultra (60c) · 64 GB · 4bit · 2026-04-14
Performance
32k
tokens
171.3
PP tok/s
16.4
TG tok/s
191298
TTFT (ms)
21.6
Peak mem (GB)
Hardware
Chip M2 Ultra (60c)
Memory 64 GB
GPU Cores 60
Software
oMLX v0.3.5.dev1
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 175.1 33.0 15.8 GB view
4k 182.1 31.0 17.3 GB view
8k 181.6 28.8 17.9 GB view
16k 178.4 24.3 19.1 GB view
32k 171.3 16.4 21.6 GB current
Batching Results
Batch Size TG tok/s Speedup
33.0 1.00×
40.9 1.24×
45.6 1.38×