K2 Horizon MoVA 36B A4B needs about 24.1 GB of memory at Q4_K (a 21.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 10 quants, from 0.3 GB to 74.9 GB (F16).
K2 Horizon MoVA 36B A4B is a 37.4B-parameter Horizon model in GGUF format, quantized by eaddario. Its trained context length is 512K tokens. The repository has 10 quant files, from 0.3 GB to 74.9 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 0.8 GB | Fits | Get file → | |
| — | 8.2 GB | 9.7 GB | Too big | Get file → | |
| Q2_K | 11.7 GB | 13.6 GB | Too big | Get file → | |
| Q3_K | 16.4 GB | 18.9 GB | Too big | Get file → | |
| Q4_K | 21.1 GB | 24.1 GB | Too big | Get file → | |
| Q5_K | 25.8 GB | 29.3 GB | Too big | Get file → | |
| Q6_K | 30.4 GB | 34.6 GB | Too big | Get file → | |
| Q7_K | 35.1 GB | 39.8 GB | Too big | Get file → | |
| Q8_0 | 39.8 GB | 45.1 GB | Too big | Get file → | |
| F16 | 74.9 GB | 84.4 GB | Too big | Get file → |
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 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 (0.3 GB file, about 0.8 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.8 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (8.2 GB file, about 9.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q2_K (11.7 GB file, about 13.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K (16.4 GB file, about 18.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K (25.8 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (39.8 GB file, about 45.1 GB in use).
Which K2 Horizon MoVA 36B A4B quant should you choose?
Q4_K (21.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.3 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
How much VRAM does K2 Horizon MoVA 36B A4B need?
About 24.1 GB at Q4_K with an 8K context window. That is the 21.1 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?
Yes, with the smaller files: the 0.3 GB file needs about 0.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of K2 Horizon MoVA 36B A4B GGUF?
It depends on the quant: file is 0.3 GB, file is 8.2 GB, Q2_K is 11.7 GB, Q3_K is 16.4 GB, Q4_K is 21.1 GB, Q5_K is 25.8 GB and 4 more.
What context length does K2 Horizon MoVA 36B A4B support?
The GGUF header lists a trained context length of 524,288 tokens (512K).
Where can I download K2 Horizon MoVA 36B A4B GGUF?
The files are on Hugging Face in the eaddario/K2-Horizon-MoVA-36B-A4B-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.