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.

From
£0.12
per 1M output tokens
£1 buys about 8.3 million tokens (≈ 6.3 million words)
Hosts
2
Loaded now
0

At a glance.

vision medical

  • Type: Text & chat
  • Hosts serving it now: 2 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 131,072 tokens
  • Rentable: a whole host from £0.04 an hour (rentals)
python · openai sdk
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
google
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.

Hosts serving medgemma:4b right now
HostTierPriceMeasured speedHealthStateRent
7B-A1B (5G)L1£0.13 in · £0.52 out9 tok/s · 313 ms first token82loads on request£0.04/h
GTX 1080 Ti (11G)L1£0.058 in · £0.12 out7 tok/s · 117891 ms first token78loads 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.

Hosts now
2
0 loaded in memory
Price to beat
£0.12
per 1M output tokens
Fastest measured
9 tok/s

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.