HO

Sakura K2 Horizon 0.9B

HorizonGGUF by webmp3Updated 2026-10-08
Download on Hugging Face
Parameters1.08B
Context128K
Layers28
Architecturek2-horizon
Smallest quant0.5 GB
Quick answer

Sakura K2 Horizon 0.9B needs about 1.4 GB of memory at its main file (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

Compact 1.08B decoder-only model with 128K context

Sakura K2 Horizon 0.9B is a 1.08B‑parameter dense model designed for reasoning and tool use. It supports up to 131,072 tokens with YaRN RoPE scaling. The model is fully open under Apache‑2.0 and available as a single GGUF file.

Good at

  • Reasoning across math and science
  • Tool‑use and agent tasks
  • Long‑context generation

Limits

  • No vision support
  • Requires 1.4 GB VRAM at 8 k context
  • Single quant available

Best for

  • Math problem solving
  • Code generation and debugging
  • Agent‑style instruction following

Who it’s for. Developers and researchers who need a small, open model capable of long‑context reasoning and tool use. The model is suitable for local deployment with llama.cpp or vLLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.5 GB 1.4 GB
Fits Get file →

The only available quant is the BF16‑based GGUF file of size 0.46 GB. It requires approximately 1.4 GB VRAM at 8 k context. For lower VRAM budgets, no other quant is provided in this release.

What GPU do you need for Sakura K2 Horizon 0.9B?

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 (0.5 GB file, about 1.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturek2-horizon
Parameters1.08B
Layers28
Trained context131,072 tokens
KV cache (fp16)56 KB per token

Source

Quantized bywebmp3
FamilyHorizon
Licenseapache-2.0
Downloads (HF)647
Last updated2026-10-08

Frequently asked questions about Sakura K2 Horizon 0.9B

How much VRAM does Sakura K2 Horizon 0.9B need?

About 1.4 GB at its main file with an 8K context window. That is the 0.5 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 Sakura K2 Horizon 0.9B on an 8 GB GPU?

Yes, with the smaller files: the 0.5 GB file needs about 1.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sakura K2 Horizon 0.9B GGUF?

It depends on the quant: file is 0.5 GB.

What context length does Sakura K2 Horizon 0.9B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download Sakura K2 Horizon 0.9B GGUF?

The files are on Hugging Face in the webmp3/Sakura-K2-Horizon-0.9B-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 0.9B 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 0.9B on 8 GB VRAM?

Yes, the model requires about 1.4 GB VRAM at 8 k context, leaving ample headroom in an 8 GB GPU.

Does this model support vision?

No, the model is a decoder‑only text model and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of K2-Horizon-0.9B

Similar models

Browse all →

More from webmp3

All by webmp3 →

More Horizon models

All Horizon →

Other tiny models

All tiny models →