← Back to community benchmarks

Qwen3.5-VL-9B-4bitCRACK

M4 (10c) · 16 GB · 4bit · 2026-03-13
Performance
32k
tokens
187.5
PP tok/s
12.4
TG tok/s
174795
TTFT (ms)
8.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.9
macOS macOS 26.2
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 225.2 21.9 6.5 GB view
4k 226.1 21.2 6.8 GB view
8k 222.0 19.3 7.0 GB view
16k 202.9 16.5 7.5 GB view
32k 187.5 12.4 8.5 GB current
64k 163.8 8.6 10.6 GB view
Batching Results
Batch Size TG tok/s Speedup
21.9 1.00×
42.3 1.93×
50.1 2.29×
50.4 2.30×