BA

Bathory X 26B A4B 0.2

BathoryGGUF by Nabbers1999Updated 2026-10-12
Download on Hugging Face
Parameters26B
Context256K
Layers30
Architecturegemma4
Smallest quant17.2 GB
Quick answer

Bathory X 26B A4B 0.2 needs about 25.8 GB of memory at Q4_K_M (a 17.2 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 5 quants, from 17.2 GB (Q4_K_M) to 52.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Bathory X 26B A4B 0.2 – a gemma4 mixture of experts model

Bathory X 26B A4B 0.2 is a 26 billion‑parameter gemma4 model with 4 billion active parameters. It was created through model surgery, merging layers from several source models. The model supports reasoning and tool usage.

Good at

  • Reasoning
  • Tool usage
  • Layer‑merged performance

Limits

  • No vision support
  • Large context size requires high VRAM
  • Apache‑2.0 license

Best for

  • Complex reasoning tasks
  • Tool‑enabled workflows
  • Research on model surgery

Who it’s for. Developers and researchers who need a large gemma4 model with advanced reasoning and tool integration. The model is suitable for experimentation with layer merging and direct editing techniques.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M17.2 GB 25.8 GB
Too big Get file →
Q5_K_M19.6 GB 28.2 GB
Too big Get file →
Q6_K23.2 GB 31.8 GB
Too big Get file →
Q8_027.6 GB 36.2 GB
Too big Get file →
BF1652.0 GB 60.5 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 17.21 GB, estimated 25.8 GB memory). For 16 GB VRAM use Q5_K_M (19.64 GB, 28.2 GB memory). For 32 GB VRAM use Q6_K (23.24 GB, 31.8 GB memory).

What GPU do you need for Bathory X 26B A4B 0.2?

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: the best quant that fits is Q6_K (23.2 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (27.6 GB file, about 36.2 GB in use).

Which Bathory X 26B A4B 0.2 quant should you choose?

Q4_K_M is the usual starting point for Bathory X 26B A4B 0.2: it balances file size and quality well. Here it is a 17.2 GB file.

The Q8_0 file is 27.6 GB, about 1.6 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters26B (approximate, mixture of experts)
Active parameters4B
Layers30
Trained context262,144 tokens
KV cache (fp16)960 KB per token

Source

Quantized byNabbers1999
FamilyBathory
Licenseapache-2.0
Downloads (HF)1,130
Last updated2026-10-12

Frequently asked questions about Bathory X 26B A4B 0.2

How much VRAM does Bathory X 26B A4B 0.2 need?

About 25.8 GB at Q4_K_M with an 8K context window. That is the 17.2 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 Bathory X 26B A4B 0.2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bathory X 26B A4B 0.2 GGUF?

It depends on the quant: Q4_K_M is 17.2 GB, Q5_K_M is 19.6 GB, Q6_K is 23.2 GB, Q8_0 is 27.6 GB, BF16 is 52.0 GB.

What context length does Bathory X 26B A4B 0.2 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 Bathory X 26B A4B 0.2 GGUF?

The files are on Hugging Face in the Nabbers1999/Bathory-X-26B-A4B-0.2-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 Bathory X 26B A4B 0.2 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 this model on 8 GB VRAM?

Use the Q4_K_M quant, which requires about 25.8 GB memory at 8k context, so 8 GB VRAM is insufficient.

Does this model support vision?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Bathory-X-26B-A4B-0.2

Similar models

Browse all →

More from Nabbers1999

All by Nabbers1999 →

More Bathory models

All Bathory →

Other medium models

All medium models →