🧠 Jesteban247/brats_medgemma-GGUF

This repository provides GGUF-format variants of the fine-tuned model
Jesteban247/brats_medgemma,
which originates from the BraTS (Brain Tumor Segmentation and TextBraTS) domain adaptation experiments detailed in
Jesteban247/medgemma-brats-experiments.

---

🧩 Model Description

These files are direct GGUF conversions of the brats_medgemma model, compatible with llama.cpp and the GGUF-my-repo conversion space.

The GGUF format allows efficient inference across CPU and GPU environments, offering a lightweight deployment option for medical visual-language applications such as MRI interpretation and radiology text reasoning.

---

🧮 Available Files

File	Precision	Size	Description
model_f16.gguf	FP16	7.77 GB	Full-precision float16 version
model_q8.gguf	Q8_0	4.13 GB	Balanced quantization for accuracy and speed
brats_medgemma-q5_k_m.gguf	Q5_K_M	2.83 GB	Medium quantization for balanced size and performance
mmproj_model_f16.gguf	FP16	851 MB	Multimodal projection weights (image-text alignment)

---

🔗 Related Resources

• Base fine-tuned model: Jesteban247/brats_medgemma
• Training & adaptation experiments: Jesteban247/medgemma-brats-experiments
• GGUF conversion via: ggml.ai’s GGUF-my-repo
• Conversion tools: ggml-org/llama.cpp