Marketplace · Text & chat
medgemma:4b
Call medgemma:4b through one OpenAI-compatible API. It's served by 2 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.
At a glance.
vision medical
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
model="medgemma:4b",
messages=[{"role": "user", "content": "Hello"}],
)medgemma:4b in detail.
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension.
- Published by
- Parameters
- 4.3B
- Download size
- 3.3 GB (as packaged for Ollama)
- Quantisation
- Q4_K_M
- Format
- gguf
- Architecture
- gemma3
- Licence
- health-ai-developer-foundations · access is gated (accept the terms on Hugging Face)
- Based on
- google/medgemma-4b-pt
- Task
- image text to text
- Library
- transformers
- First published
- 19 May 2025
- Last updated
- 28 Oct 2025
- Downloads (30 days)
- 430,184 on Hugging Face
- Likes
- 1,141
gemma3 image-text-to-text medical radiology clinical-reasoning dermatology pathology ophthalmology chest-x-ray
The model card
Published by the model's authors on Ollama — shown as they wrote it, unedited by Inpherio.
MedGemma is a collection of Gemma 3 variants that are trained for performance on medical text and image comprehension. Developers can use MedGemma to accelerate building healthcare-based AI applications. MedGemma is available in 4B and 27B versions.
Both MedGemma multimodal versions utilize a SigLIP image encoder that has been specifically pre-trained on a variety of de-identified medical data, including chest X-rays, dermatology images, ophthalmology images, and histopathology slides. Their LLM components are trained on a diverse set of medical data, including medical text, medical question-answer pairs, FHIR-based electronic health record data (27B multimodal only), radiology images, histopathology patches, ophthalmology images, and dermatology images.
Reference
Model card
Sources: google/medgemma-4b-it on Hugging Face · medgemma:4b on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.
Who's serving it.
Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.
| Host | Tier | Price | Measured speed | Health | State | Rent |
|---|---|---|---|---|---|---|
| 7B-A1B (5G) | L1 | £0.13 in · £0.52 out | 9 tok/s · 313 ms first token | 82 | loads on request | £0.04/h |
| GTX 1080 Ti (11G) | L1 | £0.058 in · £0.12 out | 7 tok/s · 117891 ms first token | 78 | loads on request | £0.60/h |
Live data, refreshed on every visit. How billing works.
Room on the grid for your machine.
2 machines serve medgemma:4b today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.
Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load medgemma:4b, and the platform benchmarks it on your hardware before your first request.