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 3 quants, from 22.4 GB (Q4_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 Uncensored GGUF model
K2-Horizon-MoVA-36B-A4B is a 37.4B parameter model with 4B active parameters. It is a mixture of experts and was quantized to GGUF. The model removes refusal behavior through rank‑3 directional ablation.
Good at
- Large context handling
- Uncensored responses
- High parameter count
Limits
- No vision support
- Requires specialized llama.cpp fork
- Large VRAM needed
Best for
- Research on refusal removal
- Large‑context text generation
- Benchmarking Mixture of Experts models
Who it’s for. Researchers and developers needing a large, uncensored language model with minimal refusal behavior. The model is suitable for advanced experimentation and testing of refusal‑removal techniques.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 22.4 GB | 24.5 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 Q4_K_M (22.37 GB file, ~24.5 GB memory at 8k context). For 12 GB VRAM, Q6_K (30.77 GB file, ~32.9 GB memory). For 16 GB VRAM or higher, Q8_0 (39.83 GB file, ~41.9 GB memory). Memory estimates are approximate.
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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_M (22.4 GB file, about 24.5 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.
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 24.5 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: Q4_K_M is 22.4 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 InfinimindCreations/K2-Horizon-MoVA-36B-A4B-uncensored-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 this model on 8 GB VRAM?
Use the Q4_K_M quantization; it requires about 24.5 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does this model support vision?
No, the model has no vision capability.
What license applies?
The model is released under the apache-2.0 license.