Gemma-4-26B-A4B-It needs about 25.5 GB of memory at MXFP4_MOE (a 17.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 15.4 GB (MXFP4_MOE) to 17.0 GB (MXFP4_MOE). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma‑4‑26B‑A4B‑It: 25.2B‑parameter MoE model with vision support
Gemma‑4‑26B‑A4B‑It is a 25.2‑billion‑parameter mixture‑of‑experts model from the Gemma family. It supports text and image input and generates text output. The model is available in MXFP4 quantized variants for efficient local deployment.
Good at
- Multimodal text‑image tasks
- Large‑context reasoning up to 256K tokens
- Instruction‑tuned generation
Limits
- Requires 24–25.5 GB VRAM at 8K context
- No native audio support
- Apache‑2.0 license restricts commercial use without attribution
Best for
- Local inference on high‑end GPUs
- Multimodal chat assistants
- Long‑form reasoning with large context
Who it’s for. Developers needing a multimodal LLM that can run locally on GPUs with 24 GB or more of VRAM. The model is suitable for research, prototyping, and production use where the Apache‑2.0 license is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 15.4 GB | 24.0 GB | Too big | Get file → | |
| MXFP4_MOE | 17.0 GB | 25.5 GB | Too big | Get file → | |
| MXFP4_MOE | 17.0 GB | 25.5 GB | Too big | Get file → |
For 24 GB VRAM, use the 15.42 GB MXFP4_MOE variant. If 25 GB is available, the 16.96 GB variant is recommended. Memory usage is approximate and depends on context length.
What GPU do you need for Gemma-4-26B-A4B-It?
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_MOE (15.4 GB file, about 24.0 GB in use).
- 32 GB VRAM: the best quant that fits is MXFP4_MOE (17.0 GB file, about 25.5 GB in use).
Which Gemma-4-26B-A4B-It quant should you choose?
MXFP4_MOE (17.0 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
If memory is tight, the smallest file is MXFP4_MOE at 15.4 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gemma-4-26B-A4B-It
How much VRAM does Gemma-4-26B-A4B-It need?
About 25.5 GB at MXFP4_MOE with an 8K context window. That is the 17.0 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-4-26B-A4B-It on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gemma-4-26B-A4B-It GGUF?
It depends on the quant: MXFP4_MOE is 15.4 GB, MXFP4_MOE is 17.0 GB, MXFP4_MOE is 17.0 GB.
What context length does Gemma-4-26B-A4B-It support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Gemma-4-26B-A4B-It GGUF?
The files are on Hugging Face in the noctrex/gemma-4-26B-A4B-it-MXFP4_MOE-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-4-26B-A4B-It 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‑4‑26B‑A4B‑It on 8 GB VRAM?
No. The smallest MXFP4_MOE variant requires at least 24 GB VRAM at 8K context.
Does this model support audio input?
No. Audio support is only available on E2B, E4B, and 12B variants.
What license applies to this model?
The model is released under the Apache‑2.0 license.