gemma 4 12B it SHQ6 needs about 20.1 GB of memory at IQ4_XS (a 6.7 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 – hybrid IQ4_XS quantization for 8 GB VRAM GPUs
Gemma 4 12B IT QAT – SHQ6 is a 11.9 billion parameter instruction‑tuned model. It uses a selective IQ4_XS hybrid quantization, with FFN tensors in IQ4_XS and attention layers in higher precision. The model supports a 262144‑token context window.
Good at
- Coding tasks
- Instruction following
- Large context handling
Limits
- No vision support
- Requires 8 GB VRAM for optimal performance
- License: Apache‑2.0
Best for
- Running on mid‑range GPUs
- Generating code snippets
- Long‑form text generation
Who it’s for. Developers and researchers needing a high‑capacity instruction‑tuned model that fits on 8 GB VRAM GPUs. The model is suitable for environments where memory is limited but coding and instruction following are required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 6.7 GB | 20.1 GB | Too big | Get file → |
For 8 GB VRAM GPUs, use the IQ4_XS quantization. The file size is 6.73 GB and requires approximately 20.1 GB of RAM at 8 k context. This is the only quant available for this model.
What GPU do you need for gemma 4 12B it SHQ6?
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 IQ4_XS (6.7 GB file, about 20.1 GB in use).
Which gemma 4 12B it SHQ6 quant should you choose?
IQ4_XS (6.7 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
Source
Frequently asked questions about gemma 4 12B it SHQ6
How much VRAM does gemma 4 12B it SHQ6 need?
About 20.1 GB at IQ4_XS with an 8K context window. That is the 6.7 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 SHQ6 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of gemma 4 12B it SHQ6 GGUF?
It depends on the quant: IQ4_XS is 6.7 GB.
What context length does gemma 4 12B it SHQ6 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 SHQ6 GGUF?
The files are on Hugging Face in the wepiqx/gemma-4-12B-it-SHQ6-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 SHQ6 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 an 8 GB GPU?
Yes, the IQ4_XS hybrid quantization is designed for 8 GB VRAM GPUs such as the GTX 1070.
What is the memory requirement?
Approximately 20.1 GB of RAM is needed at 8 k context for the IQ4_XS quantized model.
Is there a vision capability?
No, this model does not support vision input.