ollama run Nac/smolvlm
A port of ggml-org/SmolVLM-500M-Instruct-GGUF, you may use it with:
curl http://localhost:11434/api/generate -d '{
"model": "Nac/smolvlm",
"prompt": "",
"images": ["<base64_encoded_image>"]
}'
Prompt must be empty.
Original post: https://ollama.com/riven/smolvlm