K2-Horizon-MoVA-36B-A4B needs about 23.4 GB of memory at its main file (a 21.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
K2-Horizon-MoVA-36B-A4B – 36B parameter MoE model with 4B active per token
K2-Horizon-MoVA-36B-A4B is a Mixture-of-Experts model that stores 36B parameters and activates 4B per token. It offers 524,288-token context and is trained for reasoning and tool use. The model is fully open under Apache‑2.0.
Good at
- Reasoning
- Tool use
- Agentic tasks
Limits
- Requires ~23.4 GB VRAM at 8 k context
- No vision support
- Large file size 21.28 GB
Best for
- Complex reasoning workflows
- Agentic tool integration
- Large‑context analysis
Who it’s for. Developers needing high‑efficiency MoE for reasoning and agentic applications. The model is suitable for research and production environments that can accommodate its VRAM and storage requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 21.3 GB | 23.4 GB | Too big | Get file → |
The available GGUF file is 21.28 GB and requires about 23.4 GB VRAM at 8 k context. For systems with less memory, no alternative quantization is provided. Use the single available quant if your hardware meets the memory estimate.
What GPU do you need for K2-Horizon-MoVA-36B-A4B?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (21.3 GB file, about 23.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about K2-Horizon-MoVA-36B-A4B
How much VRAM does K2-Horizon-MoVA-36B-A4B need?
About 23.4 GB at its main file with an 8K context window. That is the 21.3 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-MoVA-36B-A4B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 23.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K2-Horizon-MoVA-36B-A4B GGUF?
It depends on the quant: file is 21.3 GB.
What context length does K2-Horizon-MoVA-36B-A4B support?
The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download K2-Horizon-MoVA-36B-A4B GGUF?
The files are on Hugging Face in the WhiskyAKM/K2-Horizon-MoVA-36B-A4B-NVFP4-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-MoVA-36B-A4B 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-MoVA-36B-A4B on 8 GB VRAM?
No. The model requires approximately 23.4 GB VRAM at 8 k context, so 8 GB is insufficient.
Does the model support vision tasks?
No. The model has no vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.