← Back to community benchmarks

Qwen3.5-9B-oQ4-mtp

M3 Pro (18c) · 18 GB · 4bit · 2026-06-04
Performance
8k
tokens
337.1
PP tok/s
25.0
TG tok/s
24301
TTFT (ms)
7.2
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 18 GB
GPU Cores 18
Software
oMLX v0.4.1
macOS macOS 26.6
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 335.9 26.3 6.3 GB view
8k 337.1 25.0 7.2 GB current