← Back to community benchmarks

Qwen3.5-9B-oQ4-mtp

M3 Pro (18c) · 18 GB · 4bit · 2026-06-04
Performance
4k
tokens
335.9
PP tok/s
26.3
TG tok/s
12193
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 18 GB
GPU Cores 18
Software
oMLX v0.4.1
macOS macOS 26.6
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 335.9 26.3 6.3 GB current
8k 337.1 25.0 7.2 GB view