Gemma 4 26B A4B it QAT NVFP4 needs about 23.0 GB of memory at its main file (a 14.4 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 32.2 GB.
Gemma 4 26B A4B it QAT NVFP4 – hybrid QAT‑optimized GGUF model
Gemma 4 26B A4B it QAT NVFP4 is a 25.2B‑parameter multimodal model with 4B active MoE parameters. It supports reasoning, tools, and vision, and offers a 262144‑token context window. The model is released under Apache 2.0.
Good at
- Reasoning and complex logic
- Multimodal text and image input
- Instruction‑tuned generation
Limits
- Requires 23 GB VRAM at 8 k context
- No audio support
- Only text output beyond vision
Best for
- Chat assistants needing large context
- Vision‑enabled content creation
- Research on MoE architectures
Who it’s for. Developers and researchers building large‑scale multimodal applications who need a high‑parameter model with MoE and vision support. The model is suitable for servers with ample VRAM and for users who prefer a hybrid QAT‑optimized format.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 14.4 GB | 23.0 GB | Too big | Get file → |
The available GGUF file is 14.44 GB with an estimated 23 GB VRAM requirement at 8 k context. This is suitable for systems with at least 24 GB VRAM. For lower VRAM budgets, no other quantizations are provided in the file list.
What GPU do you need for Gemma 4 26B A4B it QAT 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 (14.4 GB file, about 23.0 GB in use).
Specifications
Architecture from the GGUF header
Frequently asked questions about Gemma 4 26B A4B it QAT NVFP4
How much VRAM does Gemma 4 26B A4B it QAT NVFP4 need?
About 23.0 GB at its main file with an 8K context window. That is the 14.4 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 it QAT NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 26B A4B it QAT NVFP4 GGUF?
It depends on the quant: file is 14.4 GB.
What context length does Gemma 4 26B A4B it QAT 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 it QAT NVFP4 GGUF?
The files are on Hugging Face in the FreedomAISVR/Gemma-4-26B-A4B-it-QAT-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 it QAT 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 approximately 23 GB VRAM at 8 k context, so 8 GB is insufficient.
Does this model support vision?
Yes, it includes full multimodal vision support via the QAT mmproj.
What license does it use?
Apache 2.0, the same as the base model.