📌 Overview

Huihui4-8B-A4B is a lightweight MoE (Mixture of Experts) conversational model optimized from Google's gemma-4-26B-A4B-it architecture. Through expert pruning and supervised fine-tuning on high-quality dialogue data, this model significantly reduces computational overhead while preserving core reasoning and interaction capabilities. It is specifically designed for deployment on consumer-grade hardware and code-related conversational tasks.

This model is not an ablation variant.

ollama

Please use the latest version of ollama

You can use huihui_ai/huihui-4:8b directly,

markdown
Copy code
ollama run huihui_ai/huihui-4:8b

🧱 Architecture & Configuration

📊 Training Data & Methodology

• Data Source: 500+ high-quality dialogue samples carefully extracted from code preference data.
• Training Method: Supervised Fine-Tuning (SFT).
• Optimization Goal: Maintain semantic coherence, instruction-following capability, and code context understanding post-pruning.

📈 Evaluation & Performance

• Evaluation Tool: Quantitative perplexity assessment using the calculate_perplexity script.
• Test Results: Preliminary dialogue tests indicate smooth interactions and stable logic. The model performs reliably in daily conversations and code-assistance tasks, with no significant performance degradation observed after pruning.

💻 Inference & Deployment Recommendations

• Recommended Frameworks: vLLM / llama.cpp / HuggingFace Transformers
• VRAM Requirements:
  • FP16: < 18GB
  • INT4/INT8 Quantized: < 6~9GB (compatible with mainstream single consumer GPUs)
• Use Cases: Code conversation assistants, lightweight task planning, local deployment prototyping, and baseline validation for MoE pruning/merging techniques.

🗺️ Roadmap

1. Multi-Domain Fine-Tuning: Further SFT on four distinct datasets to enhance the generalization capabilities of this 32-expert model.
2. Expert Merging Validation: Experiment with merging the four independently fine-tuned models back into a 128-expert architecture, validating the feasibility of a "prune → fine-tune → merge" pipeline.
3. Core Objective: Ultimately verify the engineering viability of training and iterating on large-scale MoE models using only consumer-grade hardware.
4. If you're interested, feel free to fine-tune this model on your own datasets. We plan to merge all resulting models into a unified version at the end.

📝 Notes

• This model represents the initial pruned and fine-tuned iteration of the Huihui series. Future updates will involve multi-dataset integration and expert merging.
• calculate_perplexity evaluation script).
• Evaluation results

markdown
Copy code
python evaluate_perplexity_final.py --model_path ./google/gemma-4-26B-A4B-it

Model Path     : ./google/gemma-4-26B-A4B-it
Eval Samples   : 100
Max Length     : 8192

Citation

markdown
Copy code
@misc{huihui4-8b-a4b,
      title  = {{Huihui4-8B-A4B}: A lightweight MoE (Mixture of Experts) conversational model},
      author = {Huihui-ai},
      year   = {2026},
      url    = {https://hf.co/huihui-ai/Huihui4-8B-A4B}
}

Contact

If you have any questions, please raise an issue or contact us at support@huihui.ai.