← Back to community benchmarks

Qwythos-9B-v2-oQ4e-VL

M1 Pro (14c) · 16 GB · 4bit · 2026-07-20
Performance
16k
tokens
204.5
PP tok/s
22.2
TG tok/s
80119
TTFT (ms)
7.2
Peak mem (GB)
Hardware
Chip M1 Pro (14c)
Memory 16 GB
GPU Cores 14
Software
oMLX v0.5.2.dev1
macOS macOS 26.5.2
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 187.5 24.8 5.9 GB view
4k 209.3 24.3 6.5 GB view
8k 211.8 23.5 6.7 GB view
16k 204.5 22.2 7.2 GB current
32k 173.1 19.8 8.1 GB view
64k 153.0 16.7 10.0 GB view