← Back to community benchmarks

Qwopus3.5-27B-v3-vision

M2 Ultra (60c) · 64 GB · 4bit · 2026-04-14
Performance
1k
tokens
175.1
PP tok/s
33.0
TG tok/s
5849
TTFT (ms)
15.8
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 175.1 33.0 15.8 GB current
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 view
Batching Results
Batch Size TG tok/s Speedup
33.0 1.00×
40.9 1.24×
45.6 1.38×