DA

Dark Scarlett v2.0 31B

DarkGGUF by mradermacherUpdated 2026-08-23
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Dark Scarlett v2.0 31B needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.0 GB to 25.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Dark Scarlett v2.0 31B – a 30.7B‑parameter Gemma4 model for reasoning, roleplay, and tool use

Dark Scarlett v2.0 31B is a 30.7B‑parameter Gemma4 model trained on 262144 context tokens. It supports reasoning, roleplay, and tool usage. The model is released under the apache-2.0 license.

Good at

  • Reasoning tasks
  • Roleplay scenarios
  • Tool integration

Limits

  • No vision support
  • Large VRAM requirement
  • Requires 262144 context tokens

Best for

  • Complex dialogue generation
  • Interactive storytelling
  • AI assistant workflows

Who it’s for. Developers building conversational agents that need deep reasoning and roleplay capabilities. The model is suitable for applications that can allocate sufficient GPU memory and handle long context lengths.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ1_S7.2 GB 39.9 GB
Too big Get file →
IQ1_M7.7 GB 40.4 GB
Too big Get file →
IQ2_XXS8.7 GB 41.4 GB
Too big Get file →
IQ2_XS9.5 GB 42.2 GB
Too big Get file →
IQ2_S10.2 GB 42.9 GB
Too big Get file →
IQ2_M10.9 GB 43.6 GB
Too big Get file →
Q2_K_S11.0 GB 43.7 GB
Too big Get file →
Q2_K11.9 GB 44.6 GB
Too big Get file →
IQ3_XXS12.1 GB 44.8 GB
Too big Get file →
IQ3_XS13.1 GB 45.8 GB
Too big Get file →
IQ3_S13.8 GB 46.5 GB
Too big Get file →
Q3_K_S13.8 GB 46.5 GB
Too big Get file →
IQ3_M14.4 GB 47.1 GB
Too big Get file →
Q3_K_M15.3 GB 48.0 GB
Too big Get file →
Q3_K_L16.6 GB 49.3 GB
Too big Get file →
IQ4_XS16.7 GB 49.4 GB
Too big Get file →
Q4_017.7 GB 50.4 GB
Too big Get file →
Q4_K_S17.8 GB 50.5 GB
Too big Get file →
Q4_K_M18.7 GB 51.4 GB
Too big Get file →
Q4_119.5 GB 52.2 GB
Too big Get file →
Q5_K_S21.3 GB 54.0 GB
Too big Get file →
Q5_K_M21.8 GB 54.6 GB
Too big Get file →
Q6_K25.2 GB 57.9 GB
Too big Get file →

For 8 GB VRAM, use the "unknown" quant (0.01 GB file, 32.7 GB memory at 8 k context). For 16 GB VRAM, choose "IQ1_S" (7.16 GB file, 39.9 GB memory). For 24 GB VRAM, "IQ2_M" (10.92 GB file, 43.6 GB memory) offers a good balance of size and quality.

What GPU do you need for Dark Scarlett v2.0 31B?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q3_K_M (15.3 GB file, about 48.0 GB in use).

Which Dark Scarlett v2.0 31B quant should you choose?

Q4_K_M is the usual starting point for Dark Scarlett v2.0 31B: it balances file size and quality well. Here it is a 18.7 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 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
Parameters30.7B
Layers60
Trained context262,144 tokens
KV cache (fp16)3840 KB per token

Source

Quantized bymradermacher
FamilyDark
Licenseapache-2.0
Downloads (HF)403
Last updated2026-08-23

Frequently asked questions about Dark Scarlett v2.0 31B

How much VRAM does Dark Scarlett v2.0 31B need?

About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Dark Scarlett v2.0 31B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Dark Scarlett v2.0 31B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.2 GB, IQ1_M is 7.7 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.5 GB, IQ2_S is 10.2 GB and 18 more.

What context length does Dark Scarlett v2.0 31B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.

Where can I download Dark Scarlett v2.0 31B GGUF?

The files are on Hugging Face in the mradermacher/Dark-Scarlett-v2.0-31B-i1-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 v2.0 31B 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 v2.0 31B on 8 GB VRAM?

The smallest quant requires 32.7 GB memory at 8 k context, so 8 GB VRAM is insufficient.

Does the model support vision tasks?

No, this model is text‑only; vision support is not available.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Dark-Scarlett-v2.0-31B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Dark models

All Dark →

Other medium models

All medium models →