GE

Dark Scarlett v0.3 26B A4B

GemmaGGUF by ReadyArtUpdated 2026-06-13
Download on Hugging Face
Parameters25.2B
Context256K
Layers30
Architecturegemma4
Smallest quant0.1 GB
Quick answer

Dark Scarlett v0.3 26B A4B needs about 25.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 0.1 GB to 26.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.

Gemma 4 26B A4B model with Mixture‑of‑Experts, 256K context, Apache‑2.0 license

Dark Scarlett v0.3 26B A4B is a Gemma 4 model with 26 billion parameters and 4 billion active MoE parameters. It supports a 256 K token context window and is tuned for roleplay. The model is released under Apache 2.0 and is available in several GGUF quantizations.

Good at

  • Large‑context reasoning
  • Roleplay conversations
  • Instruction‑tuned text generation

Limits

  • Requires 8 GB+ VRAM for Q4_K_M at 8 K context
  • No vision or audio support in this variant
  • License is Apache 2.0

Best for

  • Chatbots needing long context
  • Agents that handle extended dialogues
  • Local deployment on GPUs with 8 GB VRAM

Who it’s for. Developers building local LLM applications that need a large context window and MoE capabilities. The model is suitable for on‑device inference on laptops or servers with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 8.6 GB
Too big Get file →
IQ4_XS13.9 GB 22.5 GB
Too big Get file →
Q4_014.5 GB 23.0 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q4_K_M16.8 GB 25.3 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q5_K_M19.1 GB 27.7 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q6_K22.6 GB 31.2 GB
Too big Get file →
Q8_026.9 GB 35.4 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (file size 16.8 GB, ~25.3 GB memory at 8 K context). If more VRAM is available, Q5_K_M (19.13 GB, ~27.7 GB memory) or Q6_K (22.64 GB, ~31.2 GB memory) provide higher quality. The smallest quant is IQ4_XS (13.92 GB, ~22.5 GB memory).

What GPU do you need for Dark Scarlett v0.3 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: 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 the main file (0.1 GB file, about 8.6 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (14.5 GB file, about 23.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.6 GB file, about 31.2 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 Dark Scarlett v0.3 26B A4B quant should you choose?

Q4_K_M is the usual starting point for Dark Scarlett v0.3 26B A4B: it balances file size and quality well. Here it is a 16.8 GB file.

The Q8_0 file is 26.9 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.

If memory is tight, the smallest file is the first one in the table at 0.1 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 byReadyArt
FamilyGemma
Licenseapache-2.0
Downloads (HF)14,719
Last updated2026-06-13

Frequently asked questions about Dark Scarlett v0.3 26B A4B

How much VRAM does Dark Scarlett v0.3 26B A4B need?

About 25.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 Dark Scarlett v0.3 26B A4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dark Scarlett v0.3 26B A4B GGUF?

It depends on the quant: file is 0.1 GB, IQ4_XS is 13.9 GB, Q4_0 is 14.5 GB, Q4_K_M is 16.8 GB, Q4_K_M is 16.8 GB, Q5_K_M is 19.1 GB and 4 more.

What context length does Dark Scarlett v0.3 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 8.1 GB at 8K and 32.2 GB at 32K.

Where can I download Dark Scarlett v0.3 26B A4B GGUF?

The files are on Hugging Face in the ReadyArt/Dark-Scarlett-v0.3-26B-A4B-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 Dark Scarlett v0.3 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 Dark Scarlett v0.3 26B A4B on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 25.3 GB of VRAM at 8 K context, so 8 GB is insufficient; a larger VRAM or lower context is needed.

Does this model support image input?

No, the 26B A4B variant does not include vision support in the provided GGUF files.

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 ReadyArt

All by ReadyArt →

More Gemma models

All Gemma →

Other medium models

All medium models →