HO

K2 Horizon MoVA 36B A4B APEX

HorizonGGUF by MyricUpdated 2026-09-08
Download on Hugging Face
Parameters37.4B
Context512K
Layers48
Architecturek2-horizon
Smallest quant16.0 GB
Quick answer

K2 Horizon MoVA 36B A4B APEX needs about 20.0 GB of memory at its main file (a 17.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 16.0 GB to 22.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

K2 Horizon MoVA 36B A4B APEX – a sparse Mixture‑of‑Experts LLM

K2 Horizon MoVA 36B A4B APEX is a 37.4B‑parameter model with 4B active parameters per token. It supports a 524,288‑token context and is trained for reasoning and tool use. The model is released under Apache‑2.0.

Good at

  • Reasoning
  • Tool use
  • Large context

Limits

  • Requires a forked llama.cpp
  • No vision support
  • Large VRAM needed

Best for

  • Agentic applications
  • Complex reasoning tasks
  • Long‑form content generation

Who it’s for. Developers building agentic systems or advanced reasoning tools who need a high‑capacity sparse model. The model is suitable for research and production environments that can accommodate its VRAM requirements.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—16.0 GB 18.1 GB
Too big Get file →
—17.9 GB 20.0 GB
Too big Get file →
—22.6 GB 24.7 GB
Too big Get file →

The available GGUF files are unquantized. The 15.95 GB file uses about 18.1 GB of VRAM at 8 k context, the 17.92 GB file about 20 GB, and the 22.6 GB file about 24.7 GB. Choose the smallest file for 8 GB VRAM, the middle for 12 GB, and the largest for 16 GB or more. Memory estimates are approximate.

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 (17.9 GB file, about 20.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (22.6 GB file, about 24.7 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 16.0 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 byMyric
FamilyHorizon
Licenseapache-2.0
Downloads (HF)604
Last updated2026-09-08

Frequently asked questions about K2 Horizon MoVA 36B A4B APEX

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

About 20.0 GB at its main file with an 8K context window. That is the 17.9 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 18.1 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 16.0 GB, file is 17.9 GB, file is 22.6 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 Myric/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.

Can I run this model on 8 GB VRAM?

The smallest file requires about 18.1 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision?

No, the model does not include vision capabilities.

What license does it use?

The model is released under the Apache‑2.0 license.

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

Similar models

Browse all →

More from Myric

All by Myric →

More Horizon models

All Horizon →

Other large models

All large models →