DA

Dark Scarlett v1.0 35B A3B

DarkGGUF by ReadyArtUpdated 2026-06-16
Download on Hugging Face
Parameters35.5B
Context256K
Layers41
Architectureqwen35moe
Smallest quant21.4 GB
Quick answer

Dark Scarlett v1.0 35B A3B needs about 24.0 GB of memory at Q4_K_M (a 22.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 21.4 GB (Q4_0) to 38.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Dark Scarlett v1.0 35B A3B – a 35.5B parameter Qwen35moe model

Dark Scarlett v1.0 35B A3B is a 35.5B parameter Qwen35moe model with 3B active parameters. It supports reasoning, roleplay, and tools. The model is released under apache-2.0 and has a trained context of 262144 tokens.

Good at

  • Reasoning tasks
  • Roleplay scenarios
  • Tool usage

Limits

  • No vision support
  • Requires large VRAM for full context
  • License is apache-2.0

Best for

  • Complex dialogue generation
  • Interactive storytelling
  • AI assistant scripts

Who it’s for. Developers and researchers needing a large language model with reasoning and roleplay capabilities. Suitable for applications that can allocate sufficient VRAM and comply with the apache-2.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_021.4 GB 22.6 GB
Too big Get file →
Q4_K_M22.9 GB 24.0 GB
Too big Get file →
Q5_K_M26.4 GB 27.6 GB
Too big Get file →
Q6_K30.2 GB 31.4 GB
Too big Get file →
Q8_038.6 GB 39.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 21.41 GB, estimated 22.6 GB memory). For 12 GB VRAM, Q4_K_M (22.86 GB, 24 GB memory) is suitable. For 16 GB VRAM, Q5_K_M (26.42 GB, 27.6 GB memory) or Q6_K (30.2 GB, 31.4 GB memory) can be used.

What GPU do you need for Dark Scarlett v1.0 35B A3B?

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 Q4_K_M (22.9 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (30.2 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (38.6 GB file, about 39.8 GB in use).

Which Dark Scarlett v1.0 35B A3B quant should you choose?

Q4_K_M is the usual starting point for Dark Scarlett v1.0 35B A3B: it balances file size and quality well. Here it is a 22.9 GB file.

The Q8_0 file is 38.6 GB, about 1.7 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 Q4_0 at 21.4 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35moe
Parameters35.5B (approximate, mixture of experts)
Active parameters3B
Layers41
Trained context262,144 tokens
KV cache (fp16)82 KB per token

Source

Quantized byReadyArt
FamilyDark
Licenseapache-2.0
Downloads (HF)1,195
Last updated2026-06-16

Frequently asked questions about Dark Scarlett v1.0 35B A3B

How much VRAM does Dark Scarlett v1.0 35B A3B need?

About 24.0 GB at Q4_K_M with an 8K context window. That is the 22.9 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 v1.0 35B A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dark Scarlett v1.0 35B A3B GGUF?

It depends on the quant: Q4_0 is 21.4 GB, Q4_K_M is 22.9 GB, Q5_K_M is 26.4 GB, Q6_K is 30.2 GB, Q8_0 is 38.6 GB.

What context length does Dark Scarlett v1.0 35B A3B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Dark Scarlett v1.0 35B A3B GGUF?

The files are on Hugging Face in the ReadyArt/Dark-Scarlett-v1.0-35B-A3B-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 v1.0 35B A3B 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 v1.0 35B A3B on 8 GB VRAM?

Yes, using the Q4_0 quantization which requires approximately 22.6 GB memory at 8k context, but the model will need to be run with a smaller context or off‑load techniques.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from ReadyArt

All by ReadyArt →

More Dark models

All Dark →

Other large models

All large models →