GE

Gemma 4 12B it qat NVFP4

GemmaGGUF by WhiskyAKMUpdated 2026-10-03
Download on Hugging Face
Parameters11.9B
Context256K
Layers4
Architecturegemma4-assistant
Smallest quant0.3 GB
Quick answer

Gemma 4 12B it qat NVFP4 needs about 2.4 GB of memory at BF16 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB to 7.0 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Gemma 4 12B IT QAT NVFP4 – multimodal 256K‑token GGUF model

Gemma 4 12B IT QAT NVFP4 is a multimodal GGUF model that handles text, image, and audio inputs and generates text output. It supports a 256K token context window and is optimized for efficient on‑device and server deployment.

Good at

  • Multimodal text, image, and audio understanding
  • 256K token context window
  • Native function calling

Limits

  • No vision support without mmproj.gguf
  • Requires NVFP4 or BF16 quantization
  • Large memory for 256K context

Best for

  • Chatbots needing long context
  • Multimodal content analysis
  • Agentic workflows with function calling

Who it’s for. Developers building multimodal applications that require long context and efficient inference on compatible hardware. The model is suitable for server deployments and on‑device inference with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 1.9 GB
Fits Get file →
BF160.9 GB 2.4 GB
Fits Get file →
—6.7 GB 8.3 GB
Too big Get file →
—7.0 GB 8.5 GB
Too big Get file →

For 8 GB VRAM, use the BF16 quant file (0.86 GB, 2.4 GB memory at 8K context). For 4 GB VRAM, use the NVFP4 quant file (0.32 GB, 1.9 GB memory at 8K context). Larger VRAM allows the 6.72 GB or 6.98 GB files for higher quality.

What GPU do you need for Gemma 4 12B 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: the best quant that fits is BF16 (0.9 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is BF16 (0.9 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (0.9 GB file, about 2.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.0 GB file, about 8.5 GB in use).

Which Gemma 4 12B it qat NVFP4 quant should you choose?

BF16 (0.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is the first one in the table at 0.3 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

Architecturegemma4-assistant
Parameters11.9B
Layers4
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byWhiskyAKM
FamilyGemma
Licenseapache-2.0
Downloads (HF)676
Last updated2026-10-03

Frequently asked questions about Gemma 4 12B it qat NVFP4

How much VRAM does Gemma 4 12B it qat NVFP4 need?

About 2.4 GB at BF16 with an 8K context window. That is the 0.9 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 12B it qat NVFP4 on an 8 GB GPU?

Yes, with BF16: the 0.9 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Gemma 4 12B it qat NVFP4 GGUF?

It depends on the quant: file is 0.3 GB, BF16 is 0.9 GB, file is 6.7 GB, file is 7.0 GB.

What context length does Gemma 4 12B 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Gemma 4 12B it qat NVFP4 GGUF?

The files are on Hugging Face in the WhiskyAKM/Gemma-4-12B-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 12B 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 4 GB VRAM?

Yes, the NVFP4 quant file is 0.32 GB and requires about 1.9 GB memory at 8K context, which fits 4 GB VRAM.

Do I need the mmproj.gguf file for image input?

Yes, mmproj.gguf contains the vision and audio projectors needed for multimodal inference.

Is the model licensed for commercial use?

The model is licensed under apache-2.0, which permits commercial use.

Similar models

Browse all →

More from WhiskyAKM

All by WhiskyAKM →

More Gemma models

All Gemma →

Other medium models

All medium models →