HO

K2-Horizon-32B

HorizonGGUF by bartowskiUpdated 2026-10-07
Download on Hugging Face
Parameters34.8B
Context512K
Layers64
Architecturek2-horizon
Smallest quant0.0 GB
Quick answer

K2-Horizon-32B needs about 24.7 GB of memory at Q4_K_M (a 22.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 26 quants, from 0.0 GB to 69.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

32B dense decoder-only model with 512K context

K2-Horizon-32B is a 32B dense model from the Horizon family. It offers a 524,288-token context window and is fully open source under the Apache-2.0 license. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Large context reasoning
  • Dense decoding
  • Open-source training data

Limits

  • 512K context limits long‑term memory
  • Requires 8‑bit or higher quant for full performance
  • No vision support

Best for

  • Long‑form text generation
  • Complex reasoning tasks
  • Tool‑enabled dialogue

Who it’s for. Developers and researchers who need a large dense model with a very long context window. The model is suitable for applications that require detailed, extended text generation and reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.7 GB
Fits Get file →
IQ2_XXS10.6 GB 13.2 GB
Too big Get file →
IQ2_XS11.2 GB 13.8 GB
Too big Get file →
IQ2_S11.7 GB 14.4 GB
Too big Get file →
IQ2_M12.9 GB 15.5 GB
Too big Get file →
Q2_K13.4 GB 16.0 GB
Too big Get file →
IQ3_XXS15.3 GB 17.9 GB
Too big Get file →
Q3_K_S16.0 GB 18.6 GB
Too big Get file →
IQ3_XS16.0 GB 18.6 GB
Too big Get file →
Q3_K_M16.7 GB 19.4 GB
Too big Get file →
Q3_K_L18.3 GB 21.0 GB
Too big Get file →
IQ3_M18.7 GB 21.3 GB
Too big Get file →
IQ4_XS19.4 GB 22.1 GB
Too big Get file →
Q4_020.3 GB 23.0 GB
Too big Get file →
Q4_K_S20.7 GB 23.3 GB
Too big Get file →
IQ4_NL22.0 GB 24.7 GB
Too big Get file →
Q4_K_M22.0 GB 24.7 GB
Too big Get file →
Q4_122.3 GB 24.9 GB
Too big Get file →
Q4_K_L23.4 GB 26.1 GB
Too big Get file →
Q5_K_S24.8 GB 27.4 GB
Too big Get file →
Q5_K_M26.3 GB 28.9 GB
Too big Get file →
Q6_K_S29.2 GB 31.8 GB
Too big Get file →
Q6_K30.5 GB 33.1 GB
Too big Get file →
Q6_K_L31.9 GB 34.6 GB
Too big Get file →
Q8_037.0 GB 39.6 GB
Too big Get file →
BF1669.6 GB (2 parts) 72.2 GB
Too big Get file →

For 8‑GB VRAM, use Q4_K_M (22.04 GB file, ~24.7 GB VRAM at 8k context). For 12‑GB VRAM, Q4_K_L (23.45 GB file, ~26.1 GB VRAM). For 16‑GB VRAM, Q5_K_M (26.28 GB file, ~28.9 GB VRAM). Estimates are approximate.

What GPU do you need for K2-Horizon-32B?

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 (0.0 GB file, about 2.7 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 2.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K (13.4 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_S (20.7 GB file, about 23.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K_S (29.2 GB file, about 31.8 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (37.0 GB file, about 39.6 GB in use).

Which K2-Horizon-32B quant should you choose?

Q4_K_M is the usual starting point for K2-Horizon-32B: it balances file size and quality well. Here it is a 22.0 GB file.

The Q8_0 file is 37.0 GB, about 1.7 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 0.0 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
Parameters34.8B
Layers64
Trained context524,288 tokens
KV cache (fp16)256 KB per token

Source

Quantized bybartowski
FamilyHorizon
Licenseapache-2.0
Downloads (HF)6,308
Last updated2026-10-07

Frequently asked questions about K2-Horizon-32B

How much VRAM does K2-Horizon-32B need?

About 24.7 GB at Q4_K_M with an 8K context window. That is the 22.0 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-32B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 2.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of K2-Horizon-32B GGUF?

It depends on the quant: file is 0.0 GB, IQ2_XXS is 10.6 GB, IQ2_XS is 11.2 GB, IQ2_S is 11.7 GB, IQ2_M is 12.9 GB, Q2_K is 13.4 GB and 20 more.

What context length does K2-Horizon-32B support?

The GGUF header lists a trained context length of 524,288 tokens (512K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download K2-Horizon-32B GGUF?

The files are on Hugging Face in the bartowski/K2-Horizon-32B-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-32B 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-32B on 8 GB VRAM?

Use the Q4_K_M quantization; it requires about 24.7 GB VRAM at 8k context, so 8 GB is insufficient.

Does the model support vision inputs?

No, the model only supports text input.

What license does the model use?

Apache‑2.0, fully open source.

Other GGUFs of K2-Horizon-32B

Similar models

Browse all →

More from bartowski

All by bartowski →

More Horizon models

All Horizon →

Other large models

All large models →