MedGemma 1.5 4B
By Google · United States
Updated 2026-07-13
Overview
Google's v1.5 update to MedGemma — a 4B vision-and-text model fine-tuned on clinical literature, radiology imagery, and medical reports. 128k context, Gemma license.
When to pick this model
- Upgrading existing MedGemma 1.0 deployments without re-architecting
- Drafting and summarizing clinical reports with image grounding
- Research workflows in radiology and medical imaging
- On-prem clinical assistants where API calls aren't an option
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 2.3 GB |
| Q5_K_M | 2.8 GB |
| Q8_0 | 4.3 GB |
| FP16 (no quantization) | 8 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, MedGemma 1.5 4B fits an 8 GB consumer card at Q4_K_M (2.3 GB). Stepping up to Q8_0 nearly doubles the footprint to 4.3 GB, and unquantized FP16 weights take 8 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, MedGemma 1.5 4B needs roughly 5 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 25 tokens/sec on entry-level GPUs, on the order of 70 tokens/sec on a mid-range card, and up to 150 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches MedGemma 1.5 4B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for MedGemma 1.5 4B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | FP16 (8 GB used) |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | FP16 (8 GB used) |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | FP16 (8 GB used) |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | FP16 (8 GB used) |
| 32 GB | RTX 5090 | FP16 (8 GB used) |
Which GPU should you buy to run MedGemma 1.5 4B?
To run MedGemma 1.5 4B locally at Q4, you need ~2.3 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Strengths
- Iterative refinement over MedGemma 1.0 with the same footprint
- Compact 4B (~2.3GB VRAM at Q4)
- Multimodal — text plus medical imagery
- 128k context for long patient histories and literature
Limitations
- Decision-support tool only — not for direct clinical use
- Narrow medical focus, weak general performance
- Gated on Hugging Face
Typical workloads
In our catalog grid, MedGemma 1.5 4B is filed under Medical Imaging, Clinical Reports, Health Research — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: vision-language work — screenshots, charts, scanned documents; multilingual workloads.
The 125k-token context window covers long chats and mid-sized documents, though very large retrieval workloads will need chunking. It ships under the Gemma license — commercial use is generally possible but read the specific terms before embedding it in a product.
Architecture & training
Architecture: Gemma · 4B parameters · multimodal text + image · 128k context
Training: v1.5 iteration of Google's medical fine-tuning on Gemma: clinical literature, radiological imaging, reports.
A drop-in upgrade to MedGemma 1.0 with sharper clinical performance at the same compact size.
Quick start
ollama run medgemma1.5Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does MedGemma 1.5 4B need?
At the recommended Q4_K_M quantization, MedGemma 1.5 4B needs about 2.3 GB of VRAM. Q8_0 takes 4.3 GB, and unquantized FP16 weights take 8 GB.
Can MedGemma 1.5 4B run without a GPU?
Yes — with roughly 5 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does MedGemma 1.5 4B support?
MedGemma 1.5 4B supports a 125k-token context window (128,000 tokens).
Can I use MedGemma 1.5 4B commercially?
MedGemma 1.5 4B ships under the Gemma license. Commercial use is generally permitted subject to its terms — review the license text before shipping a product.
How fast is MedGemma 1.5 4B on consumer hardware?
Our compatibility engine estimates on the order of 70 tokens/sec on a mid-range GPU and up to 150 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of MedGemma 1.5 4B should I download first?
Start with Q4_K_M (2.3 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at FP16.