GE

gemma-4-26B-A4B

GemmaGGUF by ggml-orgUpdated 2026-10-19
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant26.9 GB
Quick answer

gemma-4-26B-A4B needs about 35.4 GB of memory at Q8_0 (a 26.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 26.9 GB (Q8_0) to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 26B A4B – multimodal LLM with 256K context

Gemma 4 26B A4B is a multimodal model that handles text and image input. It uses a mixture‑of‑experts architecture with 4 active experts and supports a 256K token context window. The model is released under the Apache‑2.0 license.

Good at

  • Multimodal reasoning
  • Large context handling
  • Mixture‑of‑Experts efficiency

Limits

  • No audio or video support
  • Requires >35GB VRAM for Q8_0
  • Large file size (26.86GB)

Best for

  • Long‑form text generation
  • Multimodal content analysis
  • Reasoning tasks

Who it’s for. Developers needing a powerful on‑device LLM with multimodal input and large context. Suitable for edge devices with high VRAM and for server‑side inference where memory is abundant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_026.9 GB 35.4 GB
Too big Get file →
BF1650.5 GB 59.1 GB
Too big Get file →

For 8‑GB VRAM, the model cannot run. With 35‑GB VRAM, Q8_0 is the smallest viable quant. If more memory is available, BF16 offers higher precision at 59.1‑GB VRAM usage. Estimates are approximate.

What GPU do you need for gemma-4-26B-A4B?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which gemma-4-26B-A4B quant should you choose?

Q8_0 (26.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

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 byggml-org
FamilyGemma
Licenseapache-2.0
Downloads (HF)934
Last updated2026-10-19

Frequently asked questions about gemma-4-26B-A4B

How much VRAM does gemma-4-26B-A4B need?

About 35.4 GB at Q8_0 with an 8K context window. That is the 26.9 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 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 35.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma-4-26B-A4B GGUF?

It depends on the quant: Q8_0 is 26.9 GB, BF16 is 50.5 GB.

What context length does gemma-4-26B-A4B 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 GGUF?

The files are on Hugging Face in the ggml-org/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 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 on 8 GB VRAM?

No. The smallest quant requires at least 35.4 GB VRAM at 8k context.

Does this model support vision?

Yes, it can process image input with variable aspect ratio and resolution.

Is it a mixture‑of‑experts model?

Yes, it has 4 active experts out of a larger expert pool.

Other GGUFs of gemma-4-26B-A4B

Similar models

Browse all →

More from ggml-org

All by ggml-org →

More Gemma models

All Gemma →

Other medium models

All medium models →