← Back to community benchmarks

Qwopus3.5-9B-v3

M3 Max (40c) · 48 GB · 4bit · 2026-05-20
Performance
4k
tokens
739.4
PP tok/s
68.7
TG tok/s
5539
TTFT (ms)
6.5
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 654.9 69.6 5.8 GB view
4k 739.4 68.7 6.5 GB current