← Back to community benchmarks

Qwen3.5-VL-9B-4bitCRACK

M4 Pro (16c) · 64 GB · 4bit · 2026-03-13
Performance
4k
tokens
362.8
PP tok/s
46.8
TG tok/s
11291
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 64 GB
GPU Cores 16
Software
oMLX v0.2.10
macOS macOS 15.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 360.9 48.9 6.7 GB view
4k 362.8 46.8 7.0 GB current
Batching Results
Batch Size TG tok/s Speedup
48.9 1.00×
79.4 1.62×
84.5 1.73×