Medgemma3 Thinking needs about 33.4 GB of memory at its main file (a 28.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Medgemma3 Thinking is a 27B-parameter Medgemma model in GGUF format, quantized by Testament200156. Its trained context length is 128K tokens. The repository has 1 quant file, from 28.7 GB to 28.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 28.7 GB | 33.4 GB | Too big | Get file → |
What GPU do you need for Medgemma3 Thinking?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is the main file (28.7 GB file, about 33.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Medgemma3 Thinking
How much VRAM does Medgemma3 Thinking need?
About 33.4 GB at its main file with an 8K context window. That is the 28.7 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 Medgemma3 Thinking on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 33.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Medgemma3 Thinking GGUF?
It depends on the quant: file is 28.7 GB.
What context length does Medgemma3 Thinking support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download Medgemma3 Thinking GGUF?
The files are on Hugging Face in the Testament200156/medgemma3-thinking repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Medgemma3 Thinking use?
Hugging Face lists the license as gemma. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.