SC

Scarlet Shadow 31B

ScarletGGUF by bartowskiUpdated 2026-09-12
Download on Hugging Face
Parameters30.7B
Context256K
Layers60
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Scarlet Shadow 31B needs about 52.2 GB of memory at Q4_K_M (a 19.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 26 quants, from 0.0 GB to 61.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.

Scarlet Shadow 31B – 31B‑parameter gemma4 model with roleplay and vision

Scarlet Shadow 31B is a 31B‑parameter gemma4 model built by merging several 31B models. It supports text, image, and audio input and is optimized for roleplay, creative writing, and storytelling. The model is released under the Apache‑2.0 license.

Good at

  • Roleplay and character interaction
  • Creative writing and storytelling
  • Multimodal vision and audio input

Limits

  • Requires large VRAM for higher quantizations
  • No speculative decoding support
  • Limited to text, image, and audio only

Best for

  • Interactive storytelling applications
  • Creative writing assistants
  • Multimodal content generation

Who it’s for. Developers and content creators who need a large, multimodal LLM for roleplay and creative writing. The model is suitable for local deployment with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 32.7 GB
Too big Get file →
IQ2_XXS9.2 GB 41.9 GB
Too big Get file →
IQ2_XS9.6 GB 42.3 GB
Too big Get file →
IQ2_S10.2 GB 42.9 GB
Too big Get file →
IQ2_M11.3 GB 44.1 GB
Too big Get file →
Q2_K11.9 GB 44.6 GB
Too big Get file →
IQ3_XXS13.3 GB 46.0 GB
Too big Get file →
Q3_K_S14.0 GB 46.7 GB
Too big Get file →
IQ3_XS14.0 GB 46.7 GB
Too big Get file →
Q3_K_M14.7 GB 47.4 GB
Too big Get file →
Q3_K_L15.6 GB 48.3 GB
Too big Get file →
IQ3_M16.4 GB 49.1 GB
Too big Get file →
IQ4_XS17.2 GB 49.9 GB
Too big Get file →
Q4_018.1 GB 50.8 GB
Too big Get file →
Q4_K_S18.3 GB 51.0 GB
Too big Get file →
IQ4_NL19.4 GB 52.1 GB
Too big Get file →
Q4_K_M19.5 GB 52.2 GB
Too big Get file →
Q4_119.8 GB 52.5 GB
Too big Get file →
Q4_K_L20.9 GB 53.6 GB
Too big Get file →
Q5_K_S22.0 GB 54.7 GB
Too big Get file →
Q5_K_M23.5 GB 56.2 GB
Too big Get file →
Q6_K_S25.8 GB 58.5 GB
Too big Get file →
Q6_K27.0 GB 59.7 GB
Too big Get file →
Q6_K_L28.3 GB 61.0 GB
Too big Get file →
Q8_032.6 GB 65.3 GB
Too big Get file →
BF1661.4 GB (2 parts) 94.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ2_XXS (9.16 GB) or IQ2_XS (9.61 GB). For 16‑GB VRAM, Q4_K_M (19.52 GB) offers a good balance of size and performance. For 32‑GB VRAM, Q6_K (26.96 GB) provides higher quality output.

What GPU do you need for Scarlet Shadow 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 (14.7 GB file, about 47.4 GB in use).

Which Scarlet Shadow 31B quant should you choose?

Q4_K_M is the usual starting point for Scarlet Shadow 31B: it balances file size and quality well. Here it is a 19.5 GB file.

The Q8_0 file is 32.6 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 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 bybartowski
FamilyScarlet
Licenseapache-2.0
Downloads (HF)2,127
Last updated2026-09-12

Frequently asked questions about Scarlet Shadow 31B

How much VRAM does Scarlet Shadow 31B need?

About 52.2 GB at Q4_K_M with an 8K context window. That is the 19.5 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 Scarlet Shadow 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 Scarlet Shadow 31B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 9.2 GB, IQ2_XS is 9.6 GB, IQ2_S is 10.2 GB, IQ2_M is 11.3 GB, Q2_K is 11.9 GB and 20 more.

What context length does Scarlet Shadow 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 Scarlet Shadow 31B GGUF?

The files are on Hugging Face in the bartowski/Vortex5_Scarlet-Shadow-31B-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 Scarlet Shadow 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 Scarlet Shadow 31B on 8 GB VRAM?

Use the IQ2_XXS or IQ2_XS quantizations, which are under 10 GB and require about 42 GB of RAM at 8k context.

Does this model support vision?

Yes, it supports image and audio input with the mmproj projector files included in the repo.

Other GGUFs of Scarlet-Shadow-31B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Scarlet models

All Scarlet →

Other medium models

All medium models →