docvm/medgemma-1.5-4b-it-GGUF

MedGemma 1.5 4B IT — GGUF Quantized

GGUF quantization of google/medgemma-1.5-4b-it for mobile/edge deployment.

File

File	Quant	Size	Use case
medgemma-1.5-4b-it-Q4_K_M.gguf	Q4_K_M	~2.5 GB	Mobile / edge devices

Usage

With llama.cpp

llama-cli -m medgemma-1.5-4b-it-Q4_K_M.gguf -cnv

With Ollama

Create a Modelfile:

FROM ./medgemma-1.5-4b-it-Q4_K_M.gguf

Then:

ollama create medgemma -f Modelfile
ollama run medgemma

On Android (llama.cpp Android build / MLC LLM)

Use the Q4_K_M file (~2.5 GB fits in most modern phone RAM).

Intended Use — Sakhi

This model powers Sakhi, an AI clinical companion for ASHA workers in rural India, with 3 modes:

1. CHECKUP — ANC readings → risk assessment
2. NEWBORN — Home visit findings → risk assessment
3. CHAT — Free-form clinical Q&A

Safety

• NOT a medical device or diagnostic tool
• Requires clinical oversight
• When in doubt, always refer to PHC

License

Health AI Developer Foundations Terms of Use