extGemma4 40 5B needs about 65.4 GB of memory at its main file (a 23.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 23.6 GB to 41.3 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 165.4 GB.
extGemma4 40 5B is a 38.9B-parameter Extgemma model in GGUF format, quantized by TOTORONG. Its trained context length is 256K tokens. The repository has 2 quant files, from 23.6 GB to 41.3 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 23.6 GB | 65.4 GB | Too big | Get file → | |
| — | 41.3 GB | 83.2 GB | Too big | Get file → |
What GPU do you need for extGemma4 40 5B?
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: no quant fits at an 8K context.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about extGemma4 40 5B
How much VRAM does extGemma4 40 5B need?
About 65.4 GB at its main file with an 8K context window. That is the 23.6 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 extGemma4 40 5B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 65.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of extGemma4 40 5B GGUF?
It depends on the quant: file is 23.6 GB, file is 41.3 GB.
What context length does extGemma4 40 5B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 41.3 GB at 8K and 165.4 GB at 32K.
Where can I download extGemma4 40 5B GGUF?
The files are on Hugging Face in the TOTORONG/extGemma4-40_5B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does extGemma4 40 5B 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.