GE

gemma 4 26B A4B it heretic APEX

GemmaGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant13.0 GB
Quick answer

gemma 4 26B A4B it heretic APEX needs about 28.1 GB of memory at its main file (a 19.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 7 quants, from 13.0 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 heretic APEX – a multimodal Mixture‑of‑Experts model

Gemma 4 26B A4B it heretic APEX is a 26B‑parameter Mixture‑of‑Experts model with 4B active parameters per token. It supports text and image input and generates text output. The model is available in several quantized GGUF files ranging from 12.98 GB to 20.58 GB.

Good at

  • Multimodal text and image processing
  • Coding and function‑calling
  • Reasoning tasks

Limits

  • Requires large VRAM – 21.5 GB+ at 8K context
  • No audio support in this variant
  • License: gemma (Apache 2.0)

Best for

  • Local inference on high‑end GPUs
  • Developers building multimodal agents
  • Researchers testing MoE quantizations

Who it’s for. This model is intended for developers and researchers who need a large multimodal Mixture‑of‑Experts model that can run locally on powerful GPUs. It is suitable for building advanced AI agents and for experimentation with APEX quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—13.0 GB 21.5 GB
Too big Get file →
—15.5 GB 24.0 GB
Too big Get file →
—15.5 GB 24.0 GB
Too big Get file →
—19.5 GB 28.1 GB
Too big Get file →
—19.5 GB 28.1 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 12.98 GB file – it estimates 21.5 GB memory at 8K context, which is approximate. For 16 GB VRAM, the 15.5 GB file is suitable, estimating 24 GB memory. For 24 GB VRAM, the 19.51 GB file provides 28.1 GB memory usage. Larger VRAM allows the 20.58 GB file with 29.1 GB estimate.

What GPU do you need for gemma 4 26B A4B it heretic APEX?

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 (15.5 GB file, about 24.0 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 heretic APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 13.0 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)20,867
Last updated2026-08-17

Frequently asked questions about gemma 4 26B A4B it heretic APEX

How much VRAM does gemma 4 26B A4B it heretic APEX need?

About 28.1 GB at its main file with an 8K context window. That is the 19.5 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 heretic APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of gemma 4 26B A4B it heretic APEX GGUF?

It depends on the quant: file is 13.0 GB, file is 15.5 GB, file is 15.5 GB, file is 19.5 GB, file is 19.5 GB, file is 20.6 GB and 1 more.

What context length does gemma 4 26B A4B it heretic APEX 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 heretic APEX GGUF?

The files are on Hugging Face in the mudler/gemma-4-26B-A4B-it-heretic-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 heretic APEX 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 this model on 8 GB VRAM?

The smallest GGUF file is 12.98 GB and estimates 21.5 GB memory at 8K context, so 8 GB VRAM is insufficient.

Does this model support audio input?

Audio is supported only on small Gemma 4 models; this 26B variant does not support audio.

What is the context window size?

The model supports up to 256K tokens context window.

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

Similar models

Browse all →

More from mudler

All by mudler →

More Gemma models

All Gemma →

Other medium models

All medium models →