K2 Horizon 7B needs about 7.3 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 5.3 GB (Q4_0) to 9.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
K2 Horizon 7B – a 7B dense decoder-only model with 512K context
K2 Horizon 7B is a 7B-core decoder-only model from the K2-Horizon family. It supports a native context window of 524,288 tokens and is designed for reasoning, coding, long-context work, and tool use. The model is fully open with Apache‑2.0 license.
Good at
- Reasoning tasks
- Long‑context generation
- Tool‑use and coding
Limits
- Requires K2 Horizon architecture support in llama.cpp
- No vision projector needed
- Large context requires significant VRAM
Best for
- Long‑form technical writing
- Complex code generation
- Agentic tool‑use scenarios
Who it’s for. Developers and researchers needing a dense model with a very large context window for advanced reasoning and coding tasks. The model is suitable for those who can run it on compatible hardware and have the necessary memory resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 5.3 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.3 GB | Tight | Get file → | |
| Q4_K_M | 6.0 GB | 7.7 GB | Tight | Get file → | |
| Q5_K_M | 6.5 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 9.6 GB | 11.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (5.34 GB file, 7 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (6.47 GB file, 8.2 GB memory) offers a balance of quality and memory. For 16 GB VRAM, Q6_K (7.39 GB file, 9.1 GB memory) provides higher precision.
What GPU do you need for 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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is Q4_K_M (6.0 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.3 GB in use).
Which K2 Horizon 7B quant should you choose?
Q4_K_M is the usual starting point for K2 Horizon 7B: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.6 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 Q4_0 at 5.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about K2 Horizon 7B
How much VRAM does K2 Horizon 7B need?
About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.6 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 K2 Horizon 7B on an 8 GB GPU?
Yes, with Q4_K_M: the 6.0 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of K2 Horizon 7B GGUF?
It depends on the quant: Q4_0 is 5.3 GB, Q4_K_M is 5.6 GB, Q4_K_M is 6.0 GB, Q5_K_M is 6.5 GB, Q6_K is 7.4 GB, Q8_0 is 9.6 GB.
What context length does 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 K2 Horizon 7B GGUF?
The files are on Hugging Face in the abenzerps/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 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 K2 Horizon 7B on 8 GB VRAM?
Yes, the Q4_0 quantization requires about 7 GB of VRAM at 8 k context, which fits within an 8 GB budget.
Does this model support vision?
No, the GGUF files are text‑only and do not include a vision projector.
What llama.cpp build is needed?
Use a llama.cpp build with K2 Horizon architecture support, such as the MBZUAI‑IFM fork.