medicus needs about 3.1 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 1.2 GB (Q2_K) to 5.2 GB (F16).
Medicus: Medical domain adaptation of Gemma2-2b-it
Medicus is a medical AI assistant built on Gemma2-2b-it. It supports English and Russian and is fine‑tuned for healthcare tasks. The model was trained with 10 epochs of continued pretraining.
Good at
- Medical question answering
- Clinical note summarization
- Multilingual medical support
Limits
- No vision support
- License under Gemma Terms of Use
- Context limited to 8192 tokens
Best for
- Clinical chatbot integration
- Medical documentation assistance
- Health data analysis
Who it’s for. Developers building medical applications that require a lightweight, domain‑specific language model. The model is suitable for environments with moderate GPU memory and a need for bilingual support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.2 GB | 2.6 GB | Fits | Get file → | |
| Q3_K_S | 1.4 GB | 2.7 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 3.1 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 3.3 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 3.5 GB | Fits | Get file → | |
| Q8_0 | 2.8 GB | 4.2 GB | Fits | Get file → | |
| F16 | 5.2 GB | 6.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.71 GB, estimated 3.1 GB memory). For 12 GB VRAM, Q5_K_M (1.92 GB, 3.3 GB memory) offers better precision. If more memory is available, Q8_0 (2.78 GB, 4.2 GB memory) provides higher quality.
What GPU do you need for medicus?
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 Q6_K (2.2 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.2 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.2 GB file, about 6.6 GB in use).
Which medicus quant should you choose?
Q4_K_M is the usual starting point for medicus: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 2.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 1.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about medicus
How much VRAM does medicus need?
About 3.1 GB at Q4_K_M with an 8K context window. That is the 1.7 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 medicus on an 8 GB GPU?
Yes, with F16: the 5.2 GB file needs about 6.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of medicus GGUF?
It depends on the quant: Q2_K is 1.2 GB, Q3_K_S is 1.4 GB, Q4_K_M is 1.7 GB, Q5_K_M is 1.9 GB, Q6_K is 2.2 GB, Q8_0 is 2.8 GB and 1 more.
What context length does medicus support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.
Where can I download medicus GGUF?
The files are on Hugging Face in the Mykes/medicus repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Medicus on 8 GB VRAM?
Yes, the Q4_K_M quantization requires approximately 3.1 GB VRAM at 8192 context length.
Does Medicus support other languages?
It supports English and Russian only, as specified in the model card.
What license does Medicus use?
The model is distributed under the Gemma Terms of Use.