GE

Gemma 4 12B it QAT NVFP4

GemmaGGUF by FreedomAISVRUpdated 2026-10-21
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant7.2 GB
Quick answer

Gemma 4 12B it QAT NVFP4 needs about 20.6 GB of memory at its main file (a 7.2 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 51.5 GB.

Gemma 4 12B Instruct QAT NVFP4 GGUF – 11.9 B parameters, 256K token context, vision enabled

Gemma 4 12B Instruct QAT NVFP4 GGUF is a 11.9 B‑parameter multimodal model with a 262,144‑token context window. It supports vision and text generation and is released under the Apache 2.0 license. The GGUF file is 7.22 GB and requires about 20.6 GB of VRAM at 8 k context.

Good at

  • Vision‑enabled OCR and image captioning
  • Large‑context reasoning up to 256K tokens
  • Instruction‑tuned text generation

Limits

  • No hybrid quantization – all weights NVFP4
  • Requires 20.6 GB VRAM at 8 k context
  • Vision support only in F32/BF16 mmproj

Best for

  • OCR and image‑to‑text tasks
  • Long‑form reasoning with large context
  • Multilingual instruction following

Who it’s for. Developers needing a multimodal LLM with a large context window and vision capability, who can allocate sufficient VRAM. The model is suitable for research and production environments that support GGUF and llama.cpp.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.2 GB 20.6 GB
Too big Get file →

The only available GGUF file is 7.22 GB with an estimated 20.6 GB VRAM requirement at 8 k context. For 8 GB VRAM, this model is not feasible. If a smaller quant is needed, a different quantization level must be sourced.

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: 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 (7.2 GB file, about 20.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters11.9B
Layers48
Trained context262,144 tokens
KV cache (fp16)1536 KB per token

Source

Quantized byFreedomAISVR
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,685
Last updated2026-10-21

Frequently asked questions about Gemma 4 12B it QAT NVFP4

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

About 20.6 GB at its main file with an 8K context window. That is the 7.2 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 12B it QAT NVFP4 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.6 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: file is 7.2 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 12.9 GB at 8K and 51.5 GB at 32K.

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

The files are on Hugging Face in the FreedomAISVR/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 8 GB VRAM?

No, the model requires about 20.6 GB VRAM at 8 k context, which exceeds 8 GB.

Does this model support vision?

Yes, it includes vision capability but the mmproj is shipped in F32/BF16; converting to F16 breaks vision.

What license applies to this model?

The model is released under the Apache 2.0 license.

Other GGUFs of gemma-4-12B-it-qat-q4_0-unquantized

Similar models

Browse all →

More from FreedomAISVR

All by FreedomAISVR →

More Gemma models

All Gemma →

Other medium models

All medium models →