GEMMA4 26B E4B DEUS needs about 20.1 GB of memory at Q5_0 (a 17.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 6 quants, from 14.1 GB (IQ4_XS) to 50.5 GB (BF16).
GEMMA4 26B E4B DEUS is a 25.2B-parameter Gemma model in GGUF format, quantized by HALO117MC. Its trained context length is 256K tokens. The repository has 6 quant files, from 14.1 GB (IQ4_XS) to 50.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 14.1 GB | 16.3 GB | Too big | Get file → | |
| IQ4_NL | 14.6 GB | 16.8 GB | Too big | Get file → | |
| Q5_0 | 17.5 GB | 20.1 GB | Too big | Get file → | |
| Q6_K | 22.8 GB | 26.1 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 30.6 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 57.1 GB | Too big | Get file → |
What GPU do you need for GEMMA4 26B E4B DEUS?
These figures add the file size, an fp16 KV cache at an 8K context window 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_0 (17.5 GB file, about 20.1 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 30.6 GB in use).
Which GEMMA4 26B E4B DEUS quant should you choose?
Q5_0 (17.5 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.
If memory is tight, the smallest file is IQ4_XS at 14.1 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GEMMA4 26B E4B DEUS
How much VRAM does GEMMA4 26B E4B DEUS need?
About 20.1 GB at Q5_0 with an 8K context window. That is the 17.5 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 GEMMA4 26B E4B DEUS on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 16.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GEMMA4 26B E4B DEUS GGUF?
It depends on the quant: IQ4_XS is 14.1 GB, IQ4_NL is 14.6 GB, Q5_0 is 17.5 GB, Q6_K is 22.8 GB, Q8_0 is 26.9 GB, BF16 is 50.5 GB.
What context length does GEMMA4 26B E4B DEUS support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download GEMMA4 26B E4B DEUS GGUF?
The files are on Hugging Face in the HALO117MC/GEMMA4-26B-E4B-DEUS repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does GEMMA4 26B E4B DEUS use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.