K2 Horizon MoVA 36B A4B APEX needs about 27.7 GB of memory at its main file (a 25.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 18.9 GB to 28.2 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
K2 Horizon MoVA 36B A4B APEX is a 37.4B-parameter Horizon model in GGUF format, quantized by vincespeed. Its trained context length is 512K tokens. The repository has 3 quant files, from 18.9 GB to 28.2 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 18.9 GB | 21.0 GB | Too big | Get file → | |
| — | 25.6 GB | 27.7 GB | Too big | Get file → | |
| — | 28.2 GB | 30.3 GB | Too big | Get file → |
What GPU do you need for K2 Horizon MoVA 36B A4B APEX?
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 (18.9 GB file, about 21.0 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (28.2 GB file, about 30.3 GB in use).
Which K2 Horizon MoVA 36B A4B APEX quant should you choose?
If memory is tight, the smallest file is the first one in the table at 18.9 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 K2 Horizon MoVA 36B A4B APEX
How much VRAM does K2 Horizon MoVA 36B A4B APEX need?
About 27.7 GB at its main file with an 8K context window. That is the 25.6 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 MoVA 36B A4B APEX on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 21.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of K2 Horizon MoVA 36B A4B APEX GGUF?
It depends on the quant: file is 18.9 GB, file is 25.6 GB, file is 28.2 GB.
What context length does K2 Horizon MoVA 36B A4B APEX 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 APEX GGUF?
The files are on Hugging Face in the vincespeed/K2-Horizon-MoVA-36B-A4B-APEX-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 APEX 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.