GE

Gemma-4-26B-A4B-It

GemmaGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant9.5 GB
Quick answer

Gemma-4-26B-A4B-It needs about 23.4 GB of memory at its main file (a 14.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 9.5 GB to 20.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma‑4 26B‑A4B‑It APEX GGUF – a multimodal, Mixture‑of‑Experts model for local inference

Gemma‑4 26B‑A4B‑It is a 26 B parameter model with 4 B active parameters per token. It supports text and image input, with a 256 K token context window. The APEX quantization reduces memory usage while preserving multimodal capabilities.

Good at

  • Multimodal text‑image tasks
  • Reasoning with large context
  • Low‑latency local inference

Limits

  • Requires high VRAM (≈30 GB at 8 K context)
  • No native audio support
  • License is gemma (Apache 2.0)

Best for

  • Local chatbot with image input
  • Multilingual reasoning workflows
  • Agentic applications needing function calling

Who it’s for. Developers and researchers who need a locally deployable, multimodal LLM with a large context window and Mixture‑of‑Experts architecture. The model is suitable for edge devices with sufficient VRAM and for server‑side inference on GPUs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—9.5 GB 18.0 GB
Too big Get file →
—12.3 GB 20.8 GB
Too big Get file →
—14.8 GB 23.4 GB
Too big Get file →
—14.8 GB 23.4 GB
Too big Get file →
—19.0 GB 27.5 GB
Too big Get file →
—19.0 GB 27.5 GB
Too big Get file →
—20.6 GB 29.1 GB
Too big Get file →
—20.6 GB 29.1 GB
Too big Get file →

For 8 GB VRAM, use the 9.48 GB file (≈18 GB memory at 8 K context). For 16 GB VRAM, the 12.27 GB file (≈20.8 GB memory) is appropriate. For 24 GB VRAM, the 14.81 GB file (≈23.4 GB memory) fits. Memory estimates are approximate.

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 the main file (14.8 GB file, about 23.4 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (20.6 GB file, about 29.1 GB in use).

Which Gemma-4-26B-A4B-It quant should you choose?

If memory is tight, the smallest file is the first one in the table at 9.5 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters25.2B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized bymudler
FamilyGemma
Licensegemma
Downloads (HF)13,953
Last updated2026-08-17

Frequently asked questions about Gemma-4-26B-A4B-It

How much VRAM does Gemma-4-26B-A4B-It need?

About 23.4 GB at its main file with an 8K context window. That is the 14.8 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 18.0 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: file is 9.5 GB, file is 12.3 GB, file is 14.8 GB, file is 14.8 GB, file is 19.0 GB, file is 19.0 GB and 2 more.

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 mudler/gemma-4-26B-A4B-it-APEX-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 gemma. 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 file requires about 18 GB of VRAM at 8 K context. You would need at least 16 GB for the 12.27 GB file, but 24 GB is recommended for stable performance.

Does this model support audio input?

No, audio support is only available on the E2B, E4B, and 12B variants, not on the 26B‑A4B model.

What license applies to this model?

The model is released under the gemma license, which is Apache 2.0 compatible.

Other GGUFs of gemma-4-26B-A4B-it

Similar models

Browse all →

More from mudler

All by mudler →

More Gemma models

All Gemma →

Other medium models

All medium models →