---
language:
- en

license: apache-2.0

library_name: llama.cpp

tags:
- gguf
- llama.cpp
- multimodal
- vision-language-model
- smolvlm
- cytology
- medical-imaging

pipeline_tag: image-text-to-text

base_model:
- HuggingFaceTB/SmolVLM-500M-Instruct

---

# SmolVLM Cytology GGUF

Fine-tuned SmolVLM multimodal model for cytology image analysis.

## Files

- SmolVLM-Cytology-Q4_K_M.gguf
- mmproj-SmolVLM-Cytology-f16.gguf

## Usage

```bash
llama-mtmd-cli \
  -m SmolVLM-Cytology-Q4_K_M.gguf \
  --mmproj mmproj-SmolVLM-Cytology-f16.gguf \
  --image test.png \
  -p "<image> Describe this image"
```

## Notes

- Quantized using llama.cpp
- Compatible with llama-mtmd-cli
- Vision encoder exported separately as mmproj GGUF