← Back to community benchmarks

Qwen3.5-9B

M3 Ultra (80c) · 512 GB · 8bit · 2026-03-13
Performance
32k
tokens
1,294
PP tok/s
47.9
TG tok/s
25333
TTFT (ms)
12.7
Peak mem (GB)
Hardware
Chip M3 Ultra (80c)
Memory 512 GB
GPU Cores 80
Software
oMLX v0.2.10
macOS macOS 15.3
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,294 47.9 12.7 GB current
64k 1,103 38.8 14.8 GB view