Gemma 4 26B A4B QAT Voice GGUFs needs about 15.8 GB of memory at Q4_K_XL (a 14.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 0.3 GB (Q4_0) to 14.6 GB (Q4_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Gemma 4 26B A4B QAT Voice GGUFs – multimodal assistant model
Gemma 4 26B A4B QAT Voice is a 25.2B parameter model optimized with Quantization‑Aware Training. It supports text, image, and voice input and outputs text. The GGUF format enables easy deployment across ecosystems.
Good at
- Multimodal reasoning
- Tool usage
- Voice‑enabled interactions
Limits
- No vision support in this release
- Requires QAT quantization for compatibility
- License not specified
Best for
- Voice‑controlled assistants
- Multimodal chatbots
- Audio‑to‑text pipelines
Who it’s for. Developers building voice‑enabled assistants or multimodal chat applications. The model is suitable for research and production use where QAT‑optimized inference is desired.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.3 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_XL | 14.2 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_XL | 14.6 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_XL | 14.6 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quant file (0.25 GB, 1.8 GB memory at 8 k context). For 16 GB VRAM, the Q4_K_XL files (14.25 GB, 15.8 GB memory) are suitable. Memory estimates are approximate.
What GPU do you need for Gemma 4 26B A4B QAT Voice GGUFs?
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: the best quant that fits is Q4_0 (0.3 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (0.3 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (0.3 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (0.3 GB file, about 1.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_XL (14.2 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_XL (14.6 GB file, about 16.2 GB in use).
Which Gemma 4 26B A4B QAT Voice GGUFs quant should you choose?
Q4_K_XL (14.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q4_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. 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
Frequently asked questions about Gemma 4 26B A4B QAT Voice GGUFs
How much VRAM does Gemma 4 26B A4B QAT Voice GGUFs need?
About 15.8 GB at Q4_K_XL with an 8K context window. That is the 14.2 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 26B A4B QAT Voice GGUFs on an 8 GB GPU?
Yes, with Q4_0: the 0.3 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gemma 4 26B A4B QAT Voice GGUFs GGUF?
It depends on the quant: Q4_0 is 0.3 GB, Q4_K_XL is 14.2 GB, Q4_K_XL is 14.6 GB, Q4_K_XL is 14.6 GB.
What context length does Gemma 4 26B A4B QAT Voice GGUFs support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Gemma 4 26B A4B QAT Voice GGUFs GGUF?
The files are on Hugging Face in the alexisStacksCode/Gemma-4-26B-A4B-QAT-Voice-GGUFs repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the Q4_0 GGUF file is 0.25 GB and requires about 1.8 GB of VRAM at 8 k context.
Does this model support vision?
No, this release does not include vision support.
What quantization is needed for assistant compatibility?
Both the assistant and target models must use the same QAT precision, such as Q4_0.