← Back to community benchmarks

Qwen3.5-VL-4B-8bitCRACK

M4 (10c) · 16 GB · 8bit · 2026-03-13
Performance
4k
tokens
401.1
PP tok/s
20.9
TG tok/s
10211
TTFT (ms)
6.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.2.9
macOS macOS 26.2
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 396.3 21.6 5.8 GB view
4k 401.1 20.9 6.0 GB current
8k 389.6 19.0 6.3 GB view
16k 365.8 16.2 6.8 GB view
32k 323.7 12.3 7.8 GB view
64k 251.1 8.7 9.9 GB view
Batching Results
Batch Size TG tok/s Speedup
21.6 1.00×
43.1 2.00×
64.9 3.00×
67.5 3.12×