HO

K2-Horizon-MoVA-36B-A4B

HorizonGGUF by bartowskiUpdated 2026-10-07
Download on Hugging Face
Parameters37.4B
Context512K
Layers48
Architecturek2-horizon
Smallest quant0.3 GB
Quick answer

K2-Horizon-MoVA-36B-A4B needs about 24.8 GB of memory at Q4_K_M (a 22.7 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 25 quants, from 0.3 GB to 74.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

36B parameter Mixture‑of‑Experts model with 4B active per token

K2‑Horizon‑MoVA‑36B‑A4B is a sparse Mixture‑of‑Experts model that stores 36 B parameters and runs 4 B active per token. It supports a native 524 288‑token context and is fully open source under the Apache‑2.0 license.

Good at

  • High‑quality reasoning with 4 B active parameters
  • Large context handling up to 512 K tokens
  • Sparse expert architecture for efficient inference

Limits

  • Requires 8 K context for memory estimates
  • No vision or multimodal support
  • Large file sizes for higher‑quality quants

Best for

  • Agentic reasoning tasks
  • Long‑form scientific coding
  • Complex tool‑calling scenarios

Who it’s for. Developers and researchers needing a large‑scale, open‑source Mixture‑of‑Experts model for advanced reasoning and long‑context workloads. The model is suitable for environments that can accommodate its memory footprint and support llama.cpp or vLLM deployments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.3 GB 2.4 GB
Fits Get file →
IQ2_XXS10.6 GB 12.8 GB
Too big Get file →
IQ2_XS11.7 GB 13.8 GB
Too big Get file →
IQ2_S12.0 GB 14.1 GB
Too big Get file →
IQ2_M13.1 GB 15.2 GB
Too big Get file →
Q2_K13.6 GB 15.7 GB
Too big Get file →
IQ3_XXS15.8 GB 17.9 GB
Too big Get file →
Q3_K_S16.8 GB 18.9 GB
Too big Get file →
IQ3_XS17.3 GB 19.4 GB
Too big Get file →
Q3_K_M17.3 GB 19.5 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
IQ3_M17.9 GB 20.0 GB
Too big Get file →
IQ4_XS20.4 GB 22.5 GB
Too big Get file →
IQ4_NL21.5 GB 23.7 GB
Too big Get file →
Q4_021.6 GB 23.7 GB
Too big Get file →
Q4_K_S22.0 GB 24.2 GB
Too big Get file →
Q4_K_M22.7 GB 24.8 GB
Too big Get file →
Q4_K_L23.2 GB 25.3 GB
Too big Get file →
Q4_123.8 GB 25.9 GB
Too big Get file →
Q5_K_S26.0 GB 28.1 GB
Too big Get file →
Q5_K_M26.7 GB 28.8 GB
Too big Get file →
Q6_K32.1 GB 34.2 GB
Too big Get file →
Q6_K_L32.4 GB 34.5 GB
Too big Get file →
Q8_039.8 GB 41.9 GB
Too big Get file →
BF1674.9 GB (2 parts) 77.0 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (10.64 GB) or IQ2_XS (11.72 GB). For 16 GB VRAM, Q4_K_M (22.70 GB) offers a good balance of size and performance. For 32 GB VRAM, Q6_K (32.09 GB) provides higher fidelity.

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: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 2.4 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.6 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_0 (21.6 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (26.7 GB file, about 28.8 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 22.7 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 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

Architecturek2-horizon
Parameters37.4B (approximate, mixture of experts)
Active parameters4B
Layers48
Trained context524,288 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybartowski
FamilyHorizon
Licenseapache-2.0
Downloads (HF)12,138
Last updated2026-10-07

Frequently asked questions about K2-Horizon-MoVA-36B-A4B

How much VRAM does K2-Horizon-MoVA-36B-A4B need?

About 24.8 GB at Q4_K_M with an 8K context window. That is the 22.7 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 2.4 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, IQ2_XXS is 10.6 GB, IQ2_XS is 11.7 GB, IQ2_S is 12.0 GB, IQ2_M is 13.1 GB, Q2_K is 13.6 GB and 19 more.

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 bartowski/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 IQ2_XXS or IQ2_XS quantized files, which require approximately 12–14 GB of VRAM at 8 K context.

Does this model support vision or multimodal inputs?

No, the model only supports text input and does not include vision capabilities.

What context length does the model support?

The native context length is 524,288 tokens, enabling very long‑form text processing.

Other GGUFs of K2-Horizon-MoVA-36B-A4B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Horizon models

All Horizon →

Other large models

All large models →