Horizon GGUF models

112 GGUF models in the Horizon family, quantized by 41 uploaders. Sizes run from 1.08B to 379B parameters. The longest trained context is 512K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
HO
Diplodocus preview 4
Horizon · OsaurusAI
Params9B
Context512K
Q4_K_M6.3 GB
ReasoningTool use
HO
K2 Horizon 7B
Horizon · IFM
Params9B
Context512K
Q4_K_M5.6 GB
GGUF
HO
K2 Horizon MoVA 36B A4B
Horizon · IFM
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
HO
K2 Horizon 3.7B
Horizon · IFM
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HO
K2 Horizon MoVA 36B A4B
Horizon · NANI-Nithin
Params37.4B
Context512K
Q4_K_M22.4 GB
Reasoning
HO
K2 Horizon 0.9B
Horizon · IFM
Params1.08B
Context128K
Q4_K_M0.7 GB
Reasoning
HO
K2-Horizon-MoVA-36B-A4B
Horizon · bartowski
Params37.4B
Context512K
Q4_K_M22.7 GB
GGUF
HO
K2 Horizon MoVA 36B A4B Uncensored
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
HO
K2 Horizon 7B Heretic
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
GGUF
HO
K2-Horizon-MoVA-36B-A4B
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
HO
K2-Horizon-32B
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
GGUF
HO
K2-Horizon-32B
Horizon · bartowski
Params34.8B
Context512K
Q4_K_M22.0 GB
GGUF
HO
K2-Horizon-7B
Horizon · bartowski
Params9B
Context512K
Q4_K_M5.8 GB
GGUF
HO
K2 Horizon 32B Heretic
Horizon · mradermacher
Params34.8B
Context512K
Q4_K_M21.1 GB
Coding
HO
K2 Horizon 7B Uno Uncensored
Horizon · geantendormi
Params9B
Context512K
Smallest5.1 GB
GGUF
HO
K2-Horizon-3.7B
Horizon · bartowski
Params5.06B
Context512K
Q4_K_M3.3 GB
GGUF
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HO
K2 Horizon 3.7B
Horizon · NANI-Nithin
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HO
K2 Horizon MoVA 36B A4B ROCmFP4
Horizon · kingjones777
Params37.4B
Context512K
Smallest19.9 GB
Reasoning
HO
K2 Horizon 7B
Horizon · NANI-Nithin
Params9B
Context512K
Q4_K_M5.6 GB
GGUF
HO
K2-Horizon-3.7B
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HO
K2 Horizon 3.7B Heretic
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
GGUF
HO
K2 Horizon 7B Candor Uncensored
Horizon · candor-lab
Params9B
Context512K
Q4_K_M5.6 GB
ReasoningTool use
HO
Sakura K2 Horizon 7B
Horizon · webmp3
Params9B
Context512K
Smallest3.8 GB
GGUF
HO
K2-Horizon-7B
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
GGUF
HO
K2 Horizon 7B UnrealEngine
Horizon · mradermacher
Params9B
Context512K
Q4_K_M5.6 GB
CodingReasoningTool use
HO
K2 Horizon 3.7B Claude Opus Reasoning Distilled
Horizon · mradermacher
Params5.06B
Context512K
Q4_K_M3.2 GB
ReasoningTool use
HO
K2 Horizon MoVA 36B A4B Uncensored
Horizon · mradermacher
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
HO
K2 Horizon MoVA 36B A4B
Horizon · ngquocvinh
Params37.4B
Context512K
Q4_K_M22.4 GB
GGUF
HO
K2 Horizon 32B
Horizon · IFM
Params34.8B
Context512K
Q4_K_M21.1 GB
GGUF

About the Horizon GGUF models

Horizon is represented on ggufmodels.com by 112 GGUF models, quantized by 41 uploaders on Hugging Face. The most downloaded are Diplodocus preview 4, K2 Horizon 7B and K2 Horizon MoVA 36B A4B. Parameter counts run from 1.08B to 379B, and the longest trained context window is 512K tokens.

A Q4_K_M file of a Horizon model is between 0.7 to 237.8 GB, which is the quant most people start with. Most files come from mradermacher (38), bartowski (6) and IFM (5). The quants you will meet most often are Q4_K_M (82), Q6_K (79), Q5_K_M (75) and Q8_0 (68), where the number is how many models offer that quant.

Frequently asked questions

Which Horizon GGUF should I download?

The most downloaded Horizon GGUF here is Diplodocus preview 4. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Horizon model need?

Q4_K_M files of Horizon models on this site range from 0.7 to 237.8 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Horizon GGUF files come from?

The most common quantizers here are mradermacher, bartowski and IFM. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing