SK

sketch

SketchGGUF by calcuisUpdated 2025-10-07
Download on Hugging Face
Parameters11.9B
Context—
Layers—
Architecturepig
Smallest quant4.0 GB
Quick answer

sketch needs about 5.2 GB of memory at Q4_0 (a 4.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 17 quants, from 4.0 GB (Q2_K_S) to 4.5 GB (Q8_0).

Sketch: a 11.9B parameter LLM for creative text generation

Sketch is a 11.9B parameter model built on the pig architecture. It offers a range of quantized GGUF files from Q2_K_S to Q8_0. The model is available via the calcuis/sketch Hugging Face repository.

Good at

  • Creative text generation
  • Lightweight quantizations
  • Flexible GGUF support

Limits

  • No vision capabilities
  • License not specified
  • Context length not provided

Best for

  • Writing prompts
  • Story brainstorming
  • Content ideation

Who it’s for. Developers and content creators who need a lightweight, text‑only model for generating creative ideas. The model is suitable for environments with limited GPU memory due to its many quantized variants.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_S4.0 GB 5.0 GB
Fits Get file →
Q2_K4.1 GB 5.1 GB
Fits Get file →
Q3_K_S4.1 GB 5.1 GB
Fits Get file →
IQ3_XXS4.1 GB 5.1 GB
Fits Get file →
IQ3_S4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.2 GB 5.2 GB
Fits Get file →
Q3_K_M4.2 GB 5.2 GB
Fits Get file →
IQ4_NL4.2 GB 5.2 GB
Fits Get file →
Q4_04.2 GB 5.2 GB
Fits Get file →
Q4_K_S4.2 GB 5.2 GB
Fits Get file →
Q4_14.2 GB 5.2 GB
Fits Get file →
Q5_04.3 GB 5.3 GB
Fits Get file →
Q5_K_S4.3 GB 5.3 GB
Fits Get file →
Q5_14.3 GB 5.3 GB
Fits Get file →
Q5_K_M4.3 GB 5.4 GB
Fits Get file →
Q6_K4.4 GB 5.4 GB
Fits Get file →
Q8_04.5 GB 5.6 GB
Fits Get file →

For 8 GB VRAM, use Q2_K_S or Q2_K (≈5 GB memory at 8k context). For 12 GB VRAM, Q3_K_S or IQ3_XXS (≈5.1 GB). For 16 GB VRAM, Q4_0 or Q4_K_S (≈5.2 GB). Higher quantizations require more memory.

What GPU do you need for sketch?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q8_0 (4.5 GB file, about 5.6 GB in use).

Which sketch quant should you choose?

Q4_0 (4.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q2_K_S at 4.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepig
Parameters11.9B

Source

Quantized bycalcuis
FamilySketch
Repositorycalcuis/sketch
Downloads (HF)1,391
Last updated2025-10-07

Frequently asked questions about sketch

How much VRAM does sketch need?

About 5.2 GB at Q4_0 with an 8K context window. That is the 4.2 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 sketch on an 8 GB GPU?

Yes, with Q8_0: the 4.5 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of sketch GGUF?

It depends on the quant: Q2_K_S is 4.0 GB, Q2_K is 4.1 GB, Q3_K_S is 4.1 GB, IQ3_XXS is 4.1 GB, IQ3_S is 4.1 GB, IQ4_XS is 4.2 GB and 11 more.

Where can I download sketch GGUF?

The files are on Hugging Face in the calcuis/sketch repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Sketch on 8 GB VRAM?

Yes, the Q2_K_S and Q2_K variants use about 5 GB memory at 8k context, fitting within 8 GB VRAM.

Does Sketch support image inputs?

No, Sketch has no vision capabilities and is text‑only.

Where can I download the GGUF files?

Download from the calcuis/sketch Hugging Face repository or use gguf-connector to select a file.

Similar models

Browse all →

More from calcuis

All by calcuis →

Other medium models

All medium models →