Gemma 4 12B it QAT MXFP4 needs about 20.3 GB of memory at MXFP4 (a 6.9 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 MXFP4 – 4‑bit GGUF with vision support
Gemma 4 12B Instruct QAT MXFP4 is a 11.9 billion‑parameter model quantized to MXFP4. It supports text and image input and outputs text. The GGUF file is 6.88 GB and requires about 20.3 GB of VRAM at 8 k context.
Good at
- Reasoning
- Tool‑calling
- Vision OCR
Limits
- No audio support
- Requires 8 k context for accurate vision
- License is Apache 2.0
Best for
- Chat assistants needing vision
- Code generation with reasoning
- Multilingual text tasks
Who it’s for. Developers and researchers who need a compact, multimodal model for deployment on GPUs with limited VRAM. The model is suitable for applications that require text and image understanding in a single inference engine.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 6.9 GB | 20.3 GB | Too big | Get file → |
For 8 GB VRAM, use the 6.88 GB MXFP4 GGUF file; it will need about 20.3 GB of VRAM at 8 k context, so it is best suited for GPUs with at least 24 GB VRAM. If VRAM is limited, consider a higher‑bit quantization such as Q4_0, but that file is not provided here.
What GPU do you need for Gemma 4 12B it QAT MXFP4?
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 MXFP4 (6.9 GB file, about 20.3 GB in use).
Which Gemma 4 12B it QAT MXFP4 quant should you choose?
MXFP4 (6.9 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Gemma 4 12B it QAT MXFP4
How much VRAM does Gemma 4 12B it QAT MXFP4 need?
About 20.3 GB at MXFP4 with an 8K context window. That is the 6.9 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 MXFP4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma 4 12B it QAT MXFP4 GGUF?
It depends on the quant: MXFP4 is 6.9 GB.
What context length does Gemma 4 12B it QAT MXFP4 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 MXFP4 GGUF?
The files are on Hugging Face in the FreedomAISVR/Gemma-4-12B-it-QAT-MXFP4-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 MXFP4 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?
The 6.88 GB MXFP4 file requires about 20.3 GB of VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does this model support audio?
Audio is supported only on smaller Gemma 4 variants; this 12B model does not support audio.
What license applies to this model?
The model is released under the Apache 2.0 license.