medgap gemma 4 12b needs about 11.4 GB of memory at Q6_K (a 9.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 0.5 GB (Q8_0) to 12.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
MedGap Gemma 4 12B – multimodal medical fine‑tuned LLM
MedGap Gemma 4 12B is a 11.9 billion‑parameter model fine‑tuned on FDA warning letters. It supports text, image, audio, and video inputs and outputs text. The model is available in GGUF format for local deployment.
Good at
- Medical text reasoning
- Multimodal input handling
- Instruction following
Limits
- No vision support in the fine‑tuned version
- Requires 8 k context for memory estimates
- License: llama3
Best for
- Medical document summarization
- Clinical decision support queries
- Multimodal medical data analysis
Who it’s for. Developers building local medical AI tools that need multimodal reasoning. Researchers needing a fine‑tuned Gemma 4 model for FDA‑related tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.5 GB | 2.0 GB | Fits | Get file → | |
| Q6_K | 9.8 GB | 11.4 GB | Too big | Get file → | |
| Q8_0 | 12.7 GB | 14.2 GB | Too big | Get file → |
For 8 GB VRAM, use the Q8_0 quant (0.47 GB file, 2 GB memory at 8 k context). For 16 GB VRAM, the Q6_K quant (9.79 GB file, 11.4 GB memory) is suitable. Larger VRAM allows the 12.67 GB Q8_0 file (14.2 GB memory).
What GPU do you need for medgap gemma 4 12b?
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 Q8_0 (0.5 GB file, about 2.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 2.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (0.5 GB file, about 2.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.7 GB file, about 14.2 GB in use).
Which medgap gemma 4 12b quant should you choose?
Q6_K (9.8 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
If memory is tight, the smallest file is Q8_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about medgap gemma 4 12b
How much VRAM does medgap gemma 4 12b need?
About 11.4 GB at Q6_K with an 8K context window. That is the 9.8 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 medgap gemma 4 12b on an 8 GB GPU?
Yes, with Q8_0: the 0.5 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of medgap gemma 4 12b GGUF?
It depends on the quant: Q8_0 is 0.5 GB, Q6_K is 9.8 GB, Q8_0 is 12.7 GB.
What context length does medgap gemma 4 12b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download medgap gemma 4 12b GGUF?
The files are on Hugging Face in the protocolsyncllc/medgap-gemma-4-12b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does medgap gemma 4 12b use?
Hugging Face lists the license as llama3. 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 MedGap Gemma 4 12B on 8 GB VRAM?
Yes, the Q8_0 quant file is 0.47 GB and requires about 2 GB of VRAM at 8 k context.
Does the model support vision?
The base model supports vision, but the fine‑tuned version may not expose it in the provided GGUF.
What license applies?
The model is licensed under llama3, which allows local use and redistribution.