MedGemma GRPO needs about 4.1 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 3.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
MedGemma GRPO – 3.88B gemma3 model fine‑tuned for clinical case reasoning
MedGemma GRPO is a 3.88B parameter gemma3 model adapted for medical case reasoning. It was trained with supervised fine‑tuning and Group Relative Policy Optimization on synthetic medical case studies. The model is intended for research and not for clinical use.
Good at
- Medical case reasoning
- Logical diagnostic path
- Structured reasoning
Limits
- No vision support
- Not a medical device
- Requires 8k context for full performance
Best for
- Research on medical LLM reasoning
- Generating diagnostic explanations
- Testing rule‑based reward functions
Who it’s for. Researchers and developers working on medical language models who need a smaller, reasoning‑focused model. The model is licensed under apache-2.0 and is for research only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 1.1 GB | 2.8 GB | Fits | Get file → | |
| IQ1_M | 1.2 GB | 2.8 GB | Fits | Get file → | |
| IQ2_XXS | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XS | 1.4 GB | 3.0 GB | Fits | Get file → | |
| IQ2_S | 1.4 GB | 3.1 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 3.2 GB | Fits | Get file → | |
| Q2_K_S | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ3_XXS | 1.7 GB | 3.3 GB | Fits | Get file → | |
| Q2_K | 1.7 GB | 3.4 GB | Fits | Get file → | |
| IQ3_XS | 1.9 GB | 3.5 GB | Fits | Get file → | |
| IQ3_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_S | 1.9 GB | 3.6 GB | Fits | Get file → | |
| IQ3_M | 2.0 GB | 3.6 GB | Fits | Get file → | |
| Q3_K_M | 2.1 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_L | 2.2 GB | 3.9 GB | Fits | Get file → | |
| IQ4_XS | 2.3 GB | 3.9 GB | Fits | Get file → | |
| IQ4_NL | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_0 | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_S | 2.4 GB | 4.0 GB | Fits | Get file → | |
| Q4_K_M | 2.5 GB | 4.1 GB | Fits | Get file → | |
| Q4_1 | 2.6 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_S | 2.8 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.8 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 (2.37 GB) or Q4_K_S (2.38 GB). For 12 GB VRAM, Q5_K_M (2.83 GB) or Q6_K (3.19 GB) provide higher quality. Memory estimates are approximate and based on 8k context.
What GPU do you need for MedGemma GRPO?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q4_K_S (2.4 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.8 GB in use).
Which MedGemma GRPO quant should you choose?
Q4_K_M is the usual starting point for MedGemma GRPO: it balances file size and quality well. Here it is a 2.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MedGemma GRPO
How much VRAM does MedGemma GRPO need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 2.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run MedGemma GRPO on an 8 GB GPU?
Yes, with Q6_K: the 3.2 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MedGemma GRPO GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.1 GB, IQ1_M is 1.2 GB, IQ2_XXS is 1.3 GB, IQ2_XS is 1.4 GB, IQ2_S is 1.4 GB and 19 more.
What context length does MedGemma GRPO support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download MedGemma GRPO GGUF?
The files are on Hugging Face in the mradermacher/MedGemma-GRPO-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MedGemma GRPO use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run MedGemma GRPO on 8 GB VRAM?
Yes, use the Q4_0 or Q4_K_S quant, each about 2.37 GB in size.
Is MedGemma GRPO a medical device?
No, it is a research model and should not be used for actual medical diagnosis.
Does the model support vision inputs?
No, it is a text‑only model and does not include vision capabilities.