GE

26B A4B

GemmaGGUF by terrorswiftUpdated 2026-10-13
Download on Hugging Face
Parameters25.2B
Context256K
Layers4
Architecturegemma4-assistant
Smallest quant0.5 GB
Quick answer

26B A4B needs about 21.3 GB of memory at its main file (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 0.5 GB to 50.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

26B A4B – a fine‑tuned Gemma 4 model for OSINT and cyber threat analysis

REDCELL is a supervised fine‑tune of Gemma 4 26B‑A4B, oriented toward open‑source intelligence, cyber threat intelligence, and investigative journalism. It retains the base model’s safety and reasoning while providing domain‑specific tradecraft. The model is available in GGUF format with several quantizations.

Good at

  • OSINT and threat intelligence queries
  • Investigative journalism support
  • Multimodal text and image processing

Limits

  • Requires 256K context window
  • No native vision support beyond image input
  • License is Apache‑2.0

Best for

  • Analyzing security reports
  • Generating investigative summaries
  • Processing multimodal evidence

Who it’s for. OSINT researchers, threat intelligence teams, CERTs, and investigative journalists who need a locally deployable, domain‑specific assistant. The model is not intended for general‑purpose uncensored use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 2.0 GB
Fits Get file →
—12.3 GB 13.8 GB
Too big Get file →
—14.7 GB 16.2 GB
Too big Get file →
—14.7 GB 16.2 GB
Too big Get file →
—19.7 GB 21.3 GB
Too big Get file →
—19.7 GB 21.3 GB
Too big Get file →
—20.7 GB 22.2 GB
Too big Get file →
—20.7 GB 22.2 GB
Too big Get file →
Q8_026.9 GB 28.4 GB
Too big Get file →
F1650.5 GB 52.1 GB
Too big Get file →

For 8‑GB VRAM use the Q8_0 quant (26.86 GB file, ~28.4 GB VRAM at 8K context). For 16‑GB VRAM the F16 quant (50.51 GB file, ~52.1 GB VRAM) is available. Smaller quants are not listed, so use the provided ones based on your memory budget.

What GPU do you need for 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: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.5 GB file, about 2.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (12.3 GB file, about 13.8 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (20.7 GB file, about 22.2 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 28.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 28.4 GB in use).

Which 26B A4B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 0.5 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-assistant
Parameters25.2B
Layers4
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byterrorswift
FamilyGemma
Licenseapache-2.0
Downloads (HF)14,743
Last updated2026-10-13

Frequently asked questions about 26B A4B

How much VRAM does 26B A4B need?

About 21.3 GB at its main file with an 8K context window. That is the 19.7 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 26B A4B on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of 26B A4B GGUF?

It depends on the quant: file is 0.5 GB, file is 12.3 GB, file is 14.7 GB, file is 14.7 GB, file is 19.7 GB, file is 19.7 GB and 4 more.

What context length does 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 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download 26B A4B GGUF?

The files are on Hugging Face in the terrorswift/REDCELL-26B-A4B-OSINT-Cyber-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 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 26B A4B on 8 GB VRAM?

The Q8_0 quant requires about 28.4 GB VRAM at 8K context, so 8 GB is insufficient.

Does the model support image input?

Yes, it can process images, but it does not include native vision support beyond image input.

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 from terrorswift

All by terrorswift →

More Gemma models

All Gemma →

Other medium models

All medium models →