GE

gemma 4 12B it qat q4 0

GemmaGGUF by googleUpdated 2026-07-17
Download on Hugging Face
Parameters11.9B
Context256K
Layers48
Architecturegemma4
Smallest quant7.0 GB
Quick answer

gemma 4 12B it qat q4 0 needs about 20.4 GB of memory at Q4_0 (a 7.0 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 it QAT Q4_0 – 12 B parameter multimodal model in GGUF format

Gemma 4 12B it QAT Q4_0 is a 12 B‑parameter, instruction‑tuned model from Google DeepMind. It supports text and image input, with a 256K‑token context window. The GGUF file is 6.98 GB and requires about 20.4 GB VRAM at 8K context.

Good at

  • Multimodal text‑image generation
  • Large‑context reasoning
  • Instruction‑following

Limits

  • Requires ~20 GB VRAM at 8K context
  • No native audio support
  • Apache 2.0 license

Best for

  • Chatbots needing long context
  • Image‑captioning pipelines
  • Research on multimodal reasoning

Who it’s for. Developers and researchers who need a multimodal LLM with a large context window and open‑source licensing. The model is suitable for deployment on high‑end GPUs that can provide the required memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.0 GB 20.4 GB
Too big Get file →

The only available quantization is Q4_0. The 6.98 GB GGUF file needs roughly 20.4 GB VRAM for 8K context. For lower VRAM budgets, consider using a smaller Gemma 4 variant or a different quant scheme if available.

What GPU do you need for gemma 4 12B it qat q4 0?

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 Q4_0 (7.0 GB file, about 20.4 GB in use).

Which gemma 4 12B it qat q4 0 quant should you choose?

Q4_0 (7.0 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized bygoogle
FamilyGemma
Licenseapache-2.0
Downloads (HF)937,324
Last updated2026-07-17

Frequently asked questions about gemma 4 12B it qat q4 0

How much VRAM does gemma 4 12B it qat q4 0 need?

About 20.4 GB at Q4_0 with an 8K context window. That is the 7.0 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 12B it qat q4 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 12B it qat q4 0 GGUF?

It depends on the quant: Q4_0 is 7.0 GB.

What context length does gemma 4 12B it qat q4 0 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 q4 0 GGUF?

The files are on Hugging Face in the google/gemma-4-12B-it-qat-q4_0-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 q4 0 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 12B it QAT Q4_0 on 8 GB VRAM?

No. The model requires about 20.4 GB VRAM at 8K context, so 8 GB is insufficient.

Does this model support vision?

Yes. It can process text and image input, but audio is not supported in this variant.

What license does it use?

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 google

All by google →

More Gemma models

All Gemma →

Other medium models

All medium models →