GE

REDCELL 26B A4B OSINT Cyber

GemmaGGUF by 0xSojalSecUpdated 2026-09-29
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant12.3 GB
Quick answer

REDCELL 26B A4B OSINT Cyber needs about 28.3 GB of memory at its main file (a 19.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 9 quants, from 12.3 GB to 50.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

REDCELL 26B A4B OSINT Cyber – a fine‑tuned Gemma 4 model for investigative work

REDCELL is a supervised fine‑tune of Gemma 4 26B‑A4B, oriented toward OSINT, cyber threat intelligence, and investigative journalism. It inherits Gemma 4’s multimodal capabilities and large 256K token context window. The model is released under Apache‑2.0 and is available in GGUF format.

Good at

  • OSINT and threat intelligence queries
  • Multimodal text and image processing
  • Large context reasoning

Limits

  • Requires 256K token context support
  • No native vision support beyond image input
  • Large memory footprint for full precision

Best for

  • Investigative journalism workflows
  • Threat intelligence analysis
  • OSINT research pipelines

Who it’s for. Designed for OSINT researchers, threat intelligence teams, CERTs, and investigative journalists who need a specialized, locally deployable model. It is not a general‑purpose uncensored model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.3 GB 20.8 GB
Too big Get file →
—14.7 GB 23.2 GB
Too big Get file →
—14.7 GB 23.2 GB
Too big Get file →
—19.7 GB 28.3 GB
Too big Get file →
—19.7 GB 28.3 GB
Too big Get file →
—20.7 GB 29.2 GB
Too big Get file →
—20.7 GB 29.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →
F1650.5 GB 59.1 GB
Too big Get file →

For 8 GB VRAM use the Q8_0 quant (26.86 GB file, ~35.4 GB memory at 8 k context). For 16 GB VRAM use the F16 quant (50.51 GB file, ~59.1 GB memory). The unknown quants are larger and not recommended for limited VRAM.

What GPU do you need for REDCELL 26B A4B OSINT Cyber?

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 (14.7 GB file, about 23.2 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (20.7 GB file, about 29.2 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).

Which REDCELL 26B A4B OSINT Cyber quant should you choose?

If memory is tight, the smallest file is the first one in the table at 12.3 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 by0xSojalSec
FamilyGemma
Licenseapache-2.0
Downloads (HF)1,077
Last updated2026-09-29

Frequently asked questions about REDCELL 26B A4B OSINT Cyber

How much VRAM does REDCELL 26B A4B OSINT Cyber need?

About 28.3 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 REDCELL 26B A4B OSINT Cyber on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 20.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of REDCELL 26B A4B OSINT Cyber GGUF?

It depends on the quant: 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, file is 20.7 GB and 3 more.

What context length does REDCELL 26B A4B OSINT Cyber 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 REDCELL 26B A4B OSINT Cyber GGUF?

The files are on Hugging Face in the 0xSojalSec/REDCELL-26B-A4B-OSINT-Cyber repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does REDCELL 26B A4B OSINT Cyber 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 REDCELL on 8 GB VRAM?

Use the Q8_0 quant; it requires about 35.4 GB memory at 8 k context, so 8 GB VRAM is insufficient. A smaller quant is not available.

Does REDCELL support image input?

Yes, it can process images, but it does not support video or audio input.

What license does REDCELL use?

The model is released under the Apache‑2.0 license.

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

Similar models

Browse all →

More from 0xSojalSec

All by 0xSojalSec →

More Gemma models

All Gemma →

Other medium models

All medium models →