Medgemma 27b Multimodal Ero needs about 23.4 GB of memory at Q5_K_S (a 18.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
Medgemma 27b Multimodal Ero is a 27B-parameter Medgemma model in GGUF format, quantized by inflatebot. Its trained context length is 128K tokens. The repository has 1 quant file, from 18.8 GB (Q5_K_S) to 18.8 GB (Q5_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → |
What GPU do you need for Medgemma 27b Multimodal Ero?
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: the best quant that fits is Q5_K_S (18.8 GB file, about 23.4 GB in use).
Which Medgemma 27b Multimodal Ero quant should you choose?
Q5_K_S (18.8 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Medgemma 27b Multimodal Ero
How much VRAM does Medgemma 27b Multimodal Ero need?
About 23.4 GB at Q5_K_S with an 8K context window. That is the 18.8 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 Medgemma 27b Multimodal Ero on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Medgemma 27b Multimodal Ero GGUF?
It depends on the quant: Q5_K_S is 18.8 GB.
What context length does Medgemma 27b Multimodal Ero 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 Medgemma 27b Multimodal Ero GGUF?
The files are on Hugging Face in the inflatebot/medgemma-27b-multimodal-ero-Q5_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.