Gemma 4 31B IT NVFP4 needs about 50.7 GB of memory at its main file (a 18.0 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 5 quants, from 17.3 GB to 23.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
Gemma 4 31B IT NVFP4 – 30.7B parameter multimodal LLM
Gemma 4 31B IT NVFP4 is a 30.7B parameter transformer model that accepts text, image, and video inputs. It offers a 262,144‑token context window and is quantized with NVIDIA NVFP4 (W4A16). The model is released under Apache‑2.0 and is suitable for commercial use.
Good at
- Long‑context reasoning
- Multimodal understanding
- Function calling
Limits
- No vision support on non‑Blackwell GPUs
- Large VRAM requirement
- No mixed‑precision support beyond NVFP4
Best for
- Chatbots with long context
- Image‑to‑text extraction
- Research on multimodal LLMs
Who it’s for. Developers and researchers needing a large multimodal model with a 256K‑token context window. The model is open source under Apache‑2.0 and can be deployed on consumer GPUs that support NVFP4.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 17.3 GB | 50.0 GB | Too big | Get file → | |
| — | 17.7 GB | 50.4 GB | Too big | Get file → | |
| — | 18.0 GB | 50.7 GB | Too big | Get file → | |
| — | 19.3 GB | 52.0 GB | Too big | Get file → | |
| — | 23.6 GB | 56.3 GB | Too big | Get file → |
For 8 GB VRAM, use the 17.29 GB file (est. 50 GB memory at 8 k context). For 16 GB VRAM, the 19.31 GB file (est. 52 GB) is suitable. For 32 GB VRAM, the 23.55 GB file (est. 56.3 GB) provides the best quality. Estimates are approximate.
What GPU do you need for Gemma 4 31B IT 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: 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.
Which Gemma 4 31B IT NVFP4 quant should you choose?
If memory is tight, the smallest file is the first one in the table at 17.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 31B IT NVFP4
How much VRAM does Gemma 4 31B IT NVFP4 need?
About 50.7 GB at its main file with an 8K context window. That is the 18.0 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 31B IT NVFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 31B IT NVFP4 GGUF?
It depends on the quant: file is 17.3 GB, file is 17.7 GB, file is 18.0 GB, file is 19.3 GB, file is 23.6 GB.
What context length does Gemma 4 31B IT 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 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Gemma 4 31B IT NVFP4 GGUF?
The files are on Hugging Face in the esatapedico/Gemma-4-31B-IT-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 31B IT 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 Gemma 4 31B IT NVFP4 on 8 GB VRAM?
The 17.29 GB GGUF file requires about 50 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does this model support image inputs?
Yes, it accepts image inputs in RGB format and can process video as frame sequences.
What license applies to this model?
The model is released under Apache License 2.0, allowing commercial and non‑commercial use.