GE

Gemma 4 E4B it NVFP4

GemmaGGUF by FreedomAISVRUpdated 2026-10-21
Download on Hugging Face
Parameters7.52B
Context128K
Layers42
Architecturegemma4
Smallest quant5.2 GB
Quick answer

Gemma 4 E4B it NVFP4 needs about 7.1 GB of memory at its main file (a 5.2 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Gemma 4 E4B it NVFP4 – 7.52B parameter multimodal model

Gemma 4 E4B it NVFP4 is a 7.52 billion parameter model that supports text, image, video, and audio input. It is quantized to NVFP4 for NVIDIA Blackwell GPUs and retains the original Apache 2.0 license. The model offers a 131072 token context window.

Good at

  • Multimodal reasoning
  • Tool‑calling
  • Large context handling

Limits

  • Requires NVIDIA Blackwell GPUs for native FP4 support
  • No vision support in quantized file list
  • Memory estimate 7.1 GB at 8k context

Best for

  • Local inference on NVIDIA GPUs
  • Multimodal chat applications
  • Reasoning tasks

Who it’s for. Developers building local multimodal LLMs on NVIDIA hardware. Researchers needing a 7.52 billion parameter model with a large context window and tool‑calling capabilities.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.2 GB 7.1 GB
Fits Get file →

The single available quant is NVFP4 with a file size of 5.19 GB. It requires about 7.1 GB of VRAM at 8k context. For lower VRAM budgets, no other quant is available in the file list.

What GPU do you need for Gemma 4 E4B 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: the best quant that fits is the main file (5.2 GB file, about 7.1 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters7.52B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byFreedomAISVR
FamilyGemma
Licenseapache-2.0
Downloads (HF)740
Last updated2026-10-21

Frequently asked questions about Gemma 4 E4B it NVFP4

How much VRAM does Gemma 4 E4B it NVFP4 need?

About 7.1 GB at its main file with an 8K context window. That is the 5.2 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 E4B it NVFP4 on an 8 GB GPU?

Yes, with the smaller files: the 5.2 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 E4B it NVFP4 GGUF?

It depends on the quant: file is 5.2 GB.

What context length does Gemma 4 E4B it NVFP4 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Gemma 4 E4B it NVFP4 GGUF?

The files are on Hugging Face in the FreedomAISVR/Gemma-4-E4B-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 E4B 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 E4B it NVFP4 on 8 GB VRAM?

The model estimates 7.1 GB of VRAM at 8k context, so it can run on 8 GB VRAM with some overhead. For larger contexts, more VRAM will be needed.

Does this model support vision?

The quantized file list does not include vision support; the model is primarily text and multimodal but the quantized version lacks vision tensors.

What license applies to this quantized model?

The quantized model retains the original Apache 2.0 license from Google DeepMind.

Other GGUFs of gemma-4-E4B-it

Similar models

Browse all →

More from FreedomAISVR

All by FreedomAISVR →

More Gemma models

All Gemma →

Other small models

All small models →