Gemma 4 26B A4B NVFP4 needs about 24.0 GB of memory at its main file (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.4 GB to 17.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma 4 26B A4B NVFP4 – multimodal LLM with 256K context
Gemma 4 26B A4B NVFP4 is a multimodal language model that handles text, image, video, and audio inputs. It offers a 256K-token context window and supports reasoning, coding, and function calling. The model is released under Apache‑2.0 and is ready for commercial use.
Good at
- Long‑context reasoning
- Multimodal understanding
- Function calling
Limits
- Requires >24 GB VRAM
- No vision support on older variants
- Active parameters 4 B out of 25.2 B
Best for
- Chatbots with long context
- Multimodal research
- Coding assistance
Who it’s for. Developers and researchers needing a large multimodal model for text and image tasks. The model is suitable for commercial or educational projects that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 15.4 GB | 24.0 GB | Too big | Get file → | |
| — | 17.7 GB | 26.2 GB | Too big | Get file → |
The available GGUF files are unquantized. The 15.44 GB file needs about 24 GB of VRAM at 8 k context, while the 17.68 GB file needs about 26.2 GB. For 8 GB VRAM, the model cannot be run. For 24 GB VRAM, use the 15.44 GB file; for 26 GB VRAM, use the 17.68 GB file.
What GPU do you need for Gemma 4 26B A4B NVFP4?
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 the main file (15.4 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (17.7 GB file, about 26.2 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 26B A4B NVFP4
How much VRAM does Gemma 4 26B A4B NVFP4 need?
About 24.0 GB at its main file with an 8K context window. That is the 15.4 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 Gemma 4 26B A4B NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 26B A4B NVFP4 GGUF?
It depends on the quant: file is 15.4 GB, file is 17.7 GB.
What context length does Gemma 4 26B A4B NVFP4 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma 4 26B A4B NVFP4 GGUF?
The files are on Hugging Face in the catlilface/Gemma-4-26B-A4B-NVFP4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gemma 4 26B A4B NVFP4 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.
Can I run this model on 8 GB VRAM?
No, the model requires at least 24 GB of VRAM at 8 k context.
Does the model support vision?
Yes, it processes text, image, video, and audio inputs.
What license does it use?
Apache‑2.0.