Gemma-4-26B-A4B-It needs about 22.0 GB of memory at IQ3_XXS (a 13.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 11.5 GB (IQ2_XXS) to 15.9 GB (Q4_K). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Gemma‑4‑26B‑A4B‑It: 26 B total, 4 B active experts, 256k‑token context
Gemma‑4‑26B‑A4B‑It is a multimodal mixture‑of‑experts model with 25.2 B parameters and 4 B active parameters. It supports text and image input and generates text output. The model is released under Apache‑2.0 and is available in several GGUF quantizations.
Good at
- Reasoning
- Tool usage
- Multimodal text‑image tasks
Limits
- No native vision support beyond image
- Requires large VRAM for full precision
- Context limited to 256k tokens
Best for
- Local inference on laptops
- Edge devices with 8 GB VRAM
- Research prototyping of MoE models
Who it’s for. Developers and researchers who need a large, multimodal LLM that can run locally. The model is suitable for those who prefer open‑source weights and Apache‑2.0 licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 11.5 GB | 20.0 GB | Too big | Get file → | |
| IQ3_XXS | 13.4 GB | 22.0 GB | Too big | Get file → | |
| Q4_K | 15.9 GB | 24.4 GB | Too big | Get file → |
For 8 GB VRAM use IQ2_XXS (11.49 GB file, ~20 GB memory at 8k context). For 12 GB VRAM use IQ3_XXS (13.4 GB file, ~22 GB memory). For 16 GB VRAM or more use Q4_K (15.9 GB file, ~24.4 GB memory).
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 IQ3_XXS (13.4 GB file, about 22.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K (15.9 GB file, about 24.4 GB in use).
Which Gemma-4-26B-A4B-It quant should you choose?
IQ3_XXS (13.4 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_XXS at 11.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 22.0 GB at IQ3_XXS with an 8K context window. That is the 13.4 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 20.0 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: IQ2_XXS is 11.5 GB, IQ3_XXS is 13.4 GB, Q4_K is 15.9 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 Ninnix96/gemma-4-26B-A4B-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?
Yes, the IQ2_XXS quant uses about 20 GB of VRAM at 8k context, which fits within an 8 GB GPU with efficient batching.
Does this model support image input?
Yes, Gemma‑4‑26B‑A4B‑It handles text and image input but does not include native audio or video support.
What license applies to this model?
The model is released under Apache‑2.0, allowing free use and modification.