K2 Horizon MoVA 36B A4B needs about 24.5 GB of memory at Q4_K_M (a 22.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 17.7 GB (Q3_K_M) to 39.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
K2 Horizon MoVA 36B A4B – sparse Mixture‑of‑Experts model with 4B active params
K2 Horizon MoVA 36B A4B is a sparse Mixture‑of‑Experts model with Mixture‑of‑Values attention. It stores 36B parameters and runs 4B active parameters per token. The model supports a native context length of 524,288 tokens.
Good at
- High‑capacity reasoning
- Agentic tool use
- Scientific coding
Limits
- Large memory requirement
- No vision support
- Requires llama.cpp build with K2 Horizon support
Best for
- Long‑form content generation
- Complex problem solving
- Research assistance
Who it’s for. Engineers and researchers needing a high‑capacity, open‑source LLM for advanced reasoning tasks. The model is ideal for those who can provide sufficient GPU memory and a compatible llama.cpp build.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 17.7 GB | 19.8 GB | Too big | Get file → | |
| Q4_0 | 21.3 GB | 23.4 GB | Too big | Get file → | |
| Q4_K_M | 22.4 GB | 24.5 GB | Too big | Get file → | |
| Q5_K_M | 26.4 GB | 28.6 GB | Too big | Get file → | |
| Q6_K | 30.8 GB | 32.9 GB | Too big | Get file → | |
| Q8_0 | 39.8 GB | 41.9 GB | Too big | Get file → |
For 8 GB VRAM, use Q3_K_M (file size 17.66 GB, estimated 19.8 GB memory at 8 k context). For 12 GB VRAM, Q4_0 (21.28 GB, 23.4 GB memory) is suitable. If 16 GB VRAM is available, Q4_K_M (22.37 GB, 24.5 GB memory) offers a good balance of size and performance.
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 Q4_0 (21.3 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (26.4 GB file, about 28.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (39.8 GB file, about 41.9 GB in use).
Which K2 Horizon MoVA 36B A4B quant should you choose?
Q4_K_M is the usual starting point for K2 Horizon MoVA 36B A4B: it balances file size and quality well. Here it is a 22.4 GB file.
The Q8_0 file is 39.8 GB, about 1.8 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 Q3_K_M at 17.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 24.5 GB at Q4_K_M with an 8K context window. That is the 22.4 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 19.8 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: Q3_K_M is 17.7 GB, Q4_0 is 21.3 GB, Q4_K_M is 22.4 GB, Q5_K_M is 26.4 GB, Q6_K is 30.8 GB, Q8_0 is 39.8 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 abenzerps/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.
Can I run K2 Horizon MoVA 36B A4B on 8 GB VRAM?
Use the Q3_K_M quantization; it requires approximately 19.8 GB memory at 8 k context, which exceeds 8 GB VRAM, so it is not feasible.
Does this model support vision tasks?
No, the model is text‑only and does not include a vision projector.
What license applies to this model?
The model is released under the Apache‑2.0 license.