← Back to community benchmarks

Qwopus3.5-27B-v3

M5 Max (40c) · 128 GB · 8bit · 2026-04-15
Performance
8k
tokens
635.6
PP tok/s
17.5
TG tok/s
12888
TTFT (ms)
30.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.5.dev1
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 705.9 18.2 28.3 GB view
4k 807.9 18.0 29.8 GB view
8k 635.6 17.5 30.4 GB current
16k 600.8 16.5 31.7 GB view
32k 544.1 15.1 34.2 GB view
Batching Results
Batch Size TG tok/s Speedup
18.2 1.00×
29.4 1.62×
40.1 2.20×
48.3 2.65×