Sakura K2 Horizon 7B needs about 7.4 GB of memory at its main file (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 3.8 GB to 6.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Sakura K2 Horizon 7B – a 9B‑parameter dense decoder with 524,288‑token context
Sakura K2 Horizon 7B is a 9‑billion‑parameter dense model from the K2‑Horizon family. It offers a 524,288‑token context window and is released under Apache‑2.0. Three GGUF files are available, each with a different size and memory footprint.
Good at
- Long‑context reasoning
- Agentic tasks
- Coding
Limits
- No vision support
- Large VRAM requirement for full‑size model
- No official quantizations beyond community builds
Best for
- Research on long‑context LLMs
- Developing agents with extended memory
- Evaluating reasoning benchmarks
Who it’s for. Researchers and developers who need a dense model with a very large context window and open‑source training data. The model is suitable for those who can allocate sufficient VRAM and are comfortable with community‑quantized GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 3.8 GB | 5.5 GB | Fits | Get file → | |
| — | 5.7 GB | 7.4 GB | Tight | Get file → | |
| — | 6.6 GB | 8.3 GB | Too big | Get file → |
For 8 GB VRAM, use the 3.84 GB file which estimates 5.5 GB memory at 8 k context. If 12 GB VRAM is available, the 5.67 GB file uses about 7.4 GB. For 16 GB or more, the 6.59 GB file requires roughly 8.3 GB. All estimates are approximate.
What GPU do you need for Sakura K2 Horizon 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (3.8 GB file, about 5.5 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (5.7 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (6.6 GB file, about 8.3 GB in use).
Which Sakura K2 Horizon 7B quant should you choose?
If memory is tight, the smallest file is the first one in the table at 3.8 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
Source
Frequently asked questions about Sakura K2 Horizon 7B
How much VRAM does Sakura K2 Horizon 7B need?
About 7.4 GB at its main file with an 8K context window. That is the 5.7 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 Sakura K2 Horizon 7B on an 8 GB GPU?
Yes, with the smaller files: the 5.7 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura K2 Horizon 7B GGUF?
It depends on the quant: file is 3.8 GB, file is 5.7 GB, file is 6.6 GB.
What context length does Sakura K2 Horizon 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 7B GGUF?
The files are on Hugging Face in the webmp3/Sakura-K2-Horizon-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 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 7B on 8 GB VRAM?
Yes, the 3.84 GB GGUF file uses about 5.5 GB memory at 8 k context, which fits within 8 GB VRAM.
Does this model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.