← Back to community benchmarks

Qwopus3.5-9B-v3

M3 Max (40c) · 48 GB · 4bit · 2026-05-20
Performance
1k
tokens
654.9
PP tok/s
69.6
TG tok/s
1564
TTFT (ms)
5.8
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 654.9 69.6 5.8 GB current
4k 739.4 68.7 6.5 GB view