← Back to community benchmarks

QwenPaw-Flash-9B-oQ6

M2 Max (30c) · 32 GB · 6bit · 2026-04-15
Performance
32k
tokens
296.6
PP tok/s
31.4
TG tok/s
110480
TTFT (ms)
11.3
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 32 GB
GPU Cores 30
Software
oMLX v0.3.4
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 310.0 37.8 9.8 GB view
32k 296.6 31.4 11.3 GB current