HO

Sakura K2 Horizon 3.7B

HorizonGGUF by webmp3Updated 2026-10-08
Download on Hugging Face
Parameters5.06B
Context512K
Layers36
Architecturek2-horizon
Smallest quant2.2 GB
Quick answer

Sakura K2 Horizon 3.7B needs about 4.7 GB of memory at its main file (a 3.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.2 GB to 3.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Sakura K2 Horizon 3.7B – a 5.06B‑parameter decoder‑only model with 512K context

Sakura K2 Horizon 3.7B is a 5.06B‑parameter dense decoder‑only model from the Horizon family. It offers a 524,288‑token context window and is fully open under Apache‑2.0. Three GGUF files are available, each with different file sizes and memory estimates.

Good at

  • Large context generation
  • Reasoning tasks
  • Agentic interactions

Limits

  • No vision support
  • No official quantizations
  • Requires recent llama.cpp build

Best for

  • Long‑form content creation
  • Complex reasoning workflows
  • Agentic script execution

Who it’s for. Developers and researchers needing a large‑context, open‑source model for text‑only tasks. Suitable for those who can run llama.cpp with a recent build and have sufficient VRAM to load the chosen quantization.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—2.2 GB 3.9 GB
Fits Get file →
—3.0 GB 4.7 GB
Fits Get file →
—3.4 GB 5.1 GB
Fits Get file →

For 8 GB VRAM, use the 2.01 GiB GGUF file (est. 3.9 GB memory at 8 k context). For 12 GB VRAM, the 2.77 GiB file (est. 4.7 GB) is suitable. For 16 GB VRAM, the 3.13 GiB file (est. 5.1 GB) can be used. Memory estimates are approximate.

What GPU do you need for Sakura K2 Horizon 3.7B?

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: the best quant that fits is the main file (2.2 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (3.4 GB file, about 5.1 GB in use).

Which Sakura K2 Horizon 3.7B quant should you choose?

If memory is tight, the smallest file is the first one in the table at 2.2 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

Architecturek2-horizon
Parameters5.06B
Layers36
Trained context524,288 tokens
KV cache (fp16)144 KB per token

Source

Quantized bywebmp3
FamilyHorizon
Licenseapache-2.0
Downloads (HF)2,687
Last updated2026-10-08

Frequently asked questions about Sakura K2 Horizon 3.7B

How much VRAM does Sakura K2 Horizon 3.7B need?

About 4.7 GB at its main file with an 8K context window. That is the 3.0 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 Sakura K2 Horizon 3.7B on an 8 GB GPU?

Yes, with the smaller files: the 3.4 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura K2 Horizon 3.7B GGUF?

It depends on the quant: file is 2.2 GB, file is 3.0 GB, file is 3.4 GB.

What context length does Sakura K2 Horizon 3.7B support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Sakura K2 Horizon 3.7B GGUF?

The files are on Hugging Face in the webmp3/Sakura-K2-Horizon-3.7B-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 Sakura K2 Horizon 3.7B 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 Sakura K2 Horizon 3.7B on 8 GB VRAM?

Yes, the 2.01 GiB GGUF file uses about 3.9 GB memory at 8 k context, which fits within 8 GB VRAM.

Does this model support image input?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under Apache‑2.0.

Other GGUFs of K2-Horizon-3.7B

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Horizon models

All Horizon →

Other small models

All small models →