Gemma 4 31B IT NVFP4 Src needs about 50.5 GB of memory at Q4_K_M (a 17.8 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 17.8 GB (Q4_K_M) to 31.5 GB (BF16). 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 model
Gemma 4 31B IT NVFP4 is a 30.7B parameter dense model with a 262144 token context window. It supports text, image, video, and audio input and outputs text. The model is available in three GGUF quantizations: Q4_K_M, Q8_0, and BF16.
Good at
- Reasoning
- Multimodal input handling
- Large context window
Limits
- No vision support in this quant set
- Requires large VRAM for full precision
- License is gemma
Best for
- Local inference on high‑end laptops
- Multimodal content generation
- Long‑form reasoning tasks
Who it’s for. Developers and researchers needing a large, multimodal LLM for local deployment. The model is suitable for environments with sufficient GPU memory and a need for extended context handling.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 17.8 GB | 50.5 GB | Too big | Get file → | |
| Q8_0 | 22.2 GB | 54.9 GB | Too big | Get file → | |
| BF16 | 31.5 GB | 64.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (17.79 GB file, ~50.5 GB memory at 8 k context). For 12 GB VRAM, Q8_0 (22.23 GB file, ~54.9 GB memory). For 16 GB VRAM or more, BF16 (31.5 GB file, ~64.2 GB memory). Estimates are approximate.
What GPU do you need for Gemma 4 31B IT NVFP4 Src?
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 Src quant should you choose?
Q4_K_M is the usual starting point for Gemma 4 31B IT NVFP4 Src: it balances file size and quality well. Here it is a 17.8 GB file.
The Q8_0 file is 22.2 GB, about 1.2 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma 4 31B IT NVFP4 Src
How much VRAM does Gemma 4 31B IT NVFP4 Src need?
About 50.5 GB at Q4_K_M with an 8K context window. That is the 17.8 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 Src on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 31B IT NVFP4 Src GGUF?
It depends on the quant: Q4_K_M is 17.8 GB, Q8_0 is 22.2 GB, BF16 is 31.5 GB.
What context length does Gemma 4 31B IT NVFP4 Src 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 Src GGUF?
The files are on Hugging Face in the LibertAIDAI/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 Src 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.
Can I run Gemma 4 31B IT NVFP4 on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 50.5 GB of VRAM at 8 k context, so 8 GB is insufficient.
Does this model support image input?
Yes, it handles text, image, video, and audio input.
What license applies to this model?
The model is licensed under gemma.