Downloads · 30 days
31
7% of all-time downloads
tokenaii/Horus-Hiero-9B
Horus-Hiero-9B is a image-text-to-text model from tokenaii. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.
<div align="center" <h1<b style="font-size: 1.5em;"Horus Hiero 9B</b</h1 </div
Downloads · 30 days
31
7% of all-time downloads
All-time downloads
421
Public
Parameters
9B
17.9 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors17.9 GB · 100%
From the Hugging Face model README
Horus Hiero 9B is a 9-billion parameter language model built on top of the robust Qwen/Qwen3.5-9B architecture (or its GGUF equivalent). It is designed to handle extremely long contexts and leverages a sophisticated hybrid attention mechanism to deliver high performance and efficiency.
The following quantized versions are available for different deployment scenarios:
| Variant | Format | Size | Best For |
|---|---|---|---|
| Full 16-bit | Safetensors | ~18.0 GB | Maximum quality, GPU inference |
| GGUF Repo | GGUF | Various | All quantized variants (Q2_K through Q8_0) |
| Q8_0 | GGUF | ~9.8 GB | Minimal quality loss |
| Q6_K | GGUF | ~7.6 GB | Near-full quality |
| Q4_K_M | GGUF | ~5.8 GB | Balanced quality/size, CPU+GPU |
| Q2_K | GGUF | ~3.9 GB | Maximum compression, lower RAM usage |
| Feature | Specification |
|---|---|
| Number of Parameters | 9 Billion |
| Input Modalities | Text, Image, Video |
| Context Length | 524,288 tokens (512K) natively |
| Hidden Dimension | 4,096 |
| Number of Layers | 32 |
| Token Embedding | 248,320 (Padded) |
| LM Output | 248,320 (Padded) |
| Training | Multi-Token Prediction (MTP), strong-to-weak distillation |
| Thinking Mode | Enabled (toggleable via enable_thinking parameter) |
| Benchmark | Score |
|---|---|
| MMLU-Pro | 79.3% |
| GPQA Diamond | 78.1% |
| HumanEval | 83.7% |
| LiveCodeBench | 62.4% |
| AIME | 40.1% |
Using NeuralNode (Recommended)
The easiest way to use Horus models is with the NeuralNode framework:
import neuralnode as nn
# For GGUF models (recommended):
MODEL_ID = "tokenaii/Horus-Hiero-9B-GGUF/Horus-Hiero-9B-Q6_K.gguf"
DEVICE = "cpu" # Change to "cuda" for GPU acceleration
# Download and load
model = nn.HorusModel(MODEL_ID, device=DEVICE).load()
# Use immediately
response = model.chat([
{"role": "user", "content": "Translate this hieroglyph: 𓂋𓏏𓈖𓀀"}
])
print(response.content)
<br><p align="center"><a href="https://tokenai.llc/projects/horus-hiero"><b>Create your own code to use Horus Hiero →</b></a></p>
TokenAI is a non-profit AI startup founded in 2025 by Assem Sabry, located in Alexandria, Egypt.
The Horus family is our line of advanced language models. The series began with Horus 1.0 4B, which achieved remarkable success as the very first language model to be fully trained from scratch in Egypt. Building on that foundation, Horus Hiero brings specialized capabilities in ancient languages while retaining powerful modern multilingual performance.
If you use Horus Hiero 9B in your research or applications, please cite it as:
@misc{tokenai_horus_hiero_9b,
title={Horus Hiero 9B: Advanced Multilingual and Hieroglyphs Language Model},
author={Assem Sabry and TokenAI},
year={2026},
url={https://huggingface.co/tokenaii/Horus-Hiero-9B}
}