--- pipeline_tag: image-text-to-text language: - multilingual library_name: transformers tags: - llm - image-text-to-text - neuralnode - multilingual - horus - tokenai ---
Horus Hiero 4B Mini is an advanced language model developed by TokenAI, an Egyptian AI startup founded by Assem Sabry. The model specializes in understanding and translating ancient Egyptian Hieroglyphs into various modern human languages. In addition, it is highly multilingual and masters 150 Languages + Hieroglyphic. To ensure accessibility and efficient deployment across different hardware setups, the model is also available in multiple GGUF variants.
## Model Overview **Horus Hiero 4B Mini** is a 4-billion parameter language model built on top of the robust [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B) 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. ### Leading Model in the Middle East
## Model Variants
The following quantized versions are available for different deployment scenarios:
| Variant | Format | Size | Best For |
| :--- | :--- | :--- | :--- |
| **[Full 16-bit](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B)** | Safetensors | ~8.0 GB | Maximum quality, GPU inference |
| **[GGUF Repo](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B-GGUF)** | GGUF | Various | All quantized variants (Q2_K through Q8_0) |
| **[Q8_0](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B-GGUF/blob/main/Horus-Hiero-Mini-4B-Q8_0.gguf)** | GGUF | ~4.4 GB | Minimal quality loss |
| **[Q6_K](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B-GGUF/blob/main/Horus-Hiero-Mini-4B-Q6_K.gguf)** | GGUF | ~3.4 GB | Near-full quality |
| **[Q4_K_M](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B-GGUF/blob/main/Horus-Hiero-Mini-4B-Q4_K_M.gguf)** | GGUF | ~2.6 GB | Balanced quality/size, CPU+GPU |
| **[Q2_K](https://huggingface.co/tokenaii/Horus-Hiero-Mini-4B-GGUF/blob/main/Horus-Hiero-Mini-4B-Q2_K.gguf)** | GGUF | ~1.8 GB | Maximum compression, lower RAM usage |
## Technical Specifications
| Feature | Specification |
| :--- | :--- |
| **Number of Parameters** | 4 Billion |
| **Input Modalities** | Text, Image, Video |
| **Context Length** | 524,288 tokens (512K) natively |
| **Training** | Multi-Token Prediction (MTP), strong-to-weak distillation |
| **Thinking Mode** | Enabled (toggleable via `enable_thinking` parameter) |
## Benchmark Results
| Benchmark | Score |
| :--- | :---: |
| **MMLU-Pro** | **74.2%** |
| **GPQA Diamond** | **72.3%** |
| **HumanEval** | **68.2%** |
| **LiveCodeBench** | **51.4%** |
| **MATH** | **45.8%** |
## Quick Start
**Using NeuralNode (Recommended)**
The easiest way to use Horus models is with the NeuralNode framework:
```python
import neuralnode as nn
# For GGUF models (recommended):
MODEL_ID = "tokenaii/Horus-Hiero-Mini-4B-GGUF/Horus-Hiero-Mini-4B-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)
```