gemma 4 E4B it heretic QAT needs about 6.2 GB of memory at Q4_K_XL (a 4.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
Gemma 4 E4B it heretic QAT – 4 GB Q4_K_XL GGUF for mobile and edge
Gemma 4 E4B it heretic QAT is a 7.5 B parameter model quantized to Q4_K_XL. The 4.26 GB GGUF file requires about 6.2 GB VRAM at 8 k context. It supports text, image, audio, and video modalities and is licensed under Apache 2.0.
Good at
- Multimodal text and image generation
- Coding tasks
- Reasoning with large context
Limits
- Requires ~6.2 GB VRAM at 8 k context
- No vision support in some runtimes
- Only 8 k context in llama.cpp
Best for
- Mobile inference on phones with 6 GB+ RAM
- Edge devices needing small GGUF models
- Rapid prototyping with llama.cpp
Who it’s for. Developers and researchers who need a compact, multimodal Gemma 4 model for mobile or edge deployment. The model is open‑source under Apache 2.0 and can be used in any environment that supports GGUF.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_XL | 4.3 GB | 6.2 GB | Fits | Get file → |
For 8 GB VRAM, the Q4_K_XL quantization is suitable, using the 4.26 GB file. If VRAM is limited to 6 GB, consider a higher‑quantization variant if available. The memory estimate of 6.2 GB is approximate and may vary with context length.
What GPU do you need for gemma 4 E4B it heretic QAT?
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: the best quant that fits is Q4_K_XL (4.3 GB file, about 6.2 GB in use).
Which gemma 4 E4B it heretic QAT quant should you choose?
Q4_K_XL (4.3 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 E4B it heretic QAT
How much VRAM does gemma 4 E4B it heretic QAT need?
About 6.2 GB at Q4_K_XL with an 8K context window. That is the 4.3 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 E4B it heretic QAT on an 8 GB GPU?
Yes, with Q4_K_XL: the 4.3 GB file needs about 6.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma 4 E4B it heretic QAT GGUF?
It depends on the quant: Q4_K_XL is 4.3 GB.
What context length does gemma 4 E4B it heretic QAT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download gemma 4 E4B it heretic QAT GGUF?
The files are on Hugging Face in the SC117/gemma-4-E4B-it-heretic-QAT-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 E4B it heretic QAT 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?
Yes, the Q4_K_XL quantized model uses about 6.2 GB VRAM at 8 k context, leaving headroom for other processes.
Does this model support vision?
Yes, it can process image input, but some runtimes may require additional configuration.
What license applies?
The model is released under the Apache 2.0 license.