Menu

#Wevisone

3 posts

Feed·
3 of 3 posts
How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)
🖼️
0Read More

How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)

DEV Community: computervision·Alan West·21 days ago
#5VEEyyUN

It refuses to box objects that aren't there 96.4% of the time vs 18.3% for Qwen3-VL-8B. Q4_K_M plus projector is ~3.2 GB; Ollama and llama.cpp commands inside.

15s