GE

Gemma-4-26B-A4B-It

GemmaGGUF by Kremon96Updated 2026-10-28
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant0.5 GB
Quick answer

Gemma-4-26B-A4B-It needs about 25.5 GB of memory at Q4_K_M (a 16.9 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 25 quants, from 0.5 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‑It: 26‑Billion‑parameter multimodal LLM

Gemma‑4‑26B‑A4B‑It is a 25.2‑billion‑parameter model with 4‑billion active MoE parameters. It supports text, image, and audio input and outputs text. The model offers a 262144‑token context window and is released under Apache‑2.0.

Good at

  • Reasoning
  • Tool‑calling
  • Multimodal input

Limits

  • Large VRAM requirement
  • No native vision support in GGUF
  • Requires 8‑k context for memory estimates

Best for

  • Long‑form text generation
  • Complex reasoning tasks
  • Multimodal content creation

Who it’s for. Developers needing a high‑capacity multimodal model for local deployment. The model is suitable for research and production environments that can accommodate its memory footprint.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.5 GB 9.0 GB
Too big Get file →
—0.5 GB 9.0 GB
Too big Get file →
BF160.9 GB 9.4 GB
Too big Get file →
F160.9 GB 9.4 GB
Too big Get file →
IQ2_XXS9.9 GB 18.5 GB
Too big Get file →
IQ2_M10.0 GB 18.6 GB
Too big Get file →
Q2_K_XL10.5 GB 19.1 GB
Too big Get file →
IQ3_S11.3 GB 19.8 GB
Too big Get file →
IQ3_XXS11.4 GB 20.0 GB
Too big Get file →
Q3_K_M12.7 GB 21.3 GB
Too big Get file →
Q3_K_XL12.9 GB 21.5 GB
Too big Get file →
IQ4_XS13.6 GB 22.2 GB
Too big Get file →
IQ4_NL13.6 GB 22.2 GB
Too big Get file →
Q4_K_S16.5 GB 25.0 GB
Too big Get file →
MXFP4_MOE16.6 GB 25.1 GB
Too big Get file →
Q4_K_M16.9 GB 25.5 GB
Too big Get file →
Q4_K_XL17.0 GB 25.6 GB
Too big Get file →
Q5_K_S18.9 GB 27.4 GB
Too big Get file →
Q5_K_M21.2 GB 29.7 GB
Too big Get file →
Q5_K_XL21.2 GB 29.8 GB
Too big Get file →
Q6_K23.2 GB 31.7 GB
Too big Get file →
Q6_K_XL23.3 GB 31.8 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →
Q8_K_XL27.6 GB 36.2 GB
Too big Get file →
BF1650.5 GB (2 parts) 59.1 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (16.95‑GB file, ~25.5‑GB memory at 8‑k context). For 12‑GB VRAM, Q5_K_M (21.15‑GB file, ~29.7‑GB memory). For 16‑GB VRAM, Q6_K (23.17‑GB file, ~31.7‑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: the best quant that fits is BF16 (0.9 GB file, about 9.4 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (0.9 GB file, about 9.4 GB in use).
  • 24 GB VRAM: the best quant that fits is IQ4_NL (13.6 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_XL (23.3 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (27.6 GB file, about 36.2 GB in use).

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

Q4_K_M is the usual starting point for Gemma-4-26B-A4B-It: it balances file size and quality well. Here it is a 16.9 GB file.

The Q8_0 file is 0.5 GB, about 0.0 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q8_0 at 0.5 GB, with the quality trade-offs that come with fewer bits. 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 byKremon96
FamilyGemma
Licenseapache-2.0
Downloads (HF)2,847
Last updated2026-10-28

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

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

About 25.5 GB at Q4_K_M with an 8K context window. That is the 16.9 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-It on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.0 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: Q8_0 is 0.5 GB, file is 0.5 GB, BF16 is 0.9 GB, F16 is 0.9 GB, IQ2_XXS is 9.9 GB, IQ2_M is 10.0 GB and 19 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 Kremon96/gemma-4-26B-A4B-it-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 quant requires at least 9‑GB VRAM. Use a lower‑bit quant like Q4_K_M if you have 8‑GB VRAM.

Does the model support vision?

The GGUF version does not include native vision support; only text and image input are supported.

What license applies to this model?

The model is released under the Apache‑2.0 license.

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

Similar models

Browse all →

More Gemma models

All Gemma →

Other medium models

All medium models →