Plano-Orchestrator-30B-A3B-GGUF

🧠 Model Overview

Plano-Orchestrator-30B-A3B-GGUF is a quantized version of Plano-Orchestrator-30B-A3B-GGUF, optimized for efficient inference with reduced memory usage and faster runtime while preserving as much of the original model quality as possible.

This repository provides multiple quantized variants suitable for:

• Local inference
• Low-VRAM GPUs
• CPU-only environments

---

🔗 Original Model

• Base model: Plano-Orchestrator-30B-A3B
• Original repository: https://huggingface.co/katanemo/Plano-Orchestrator-30B-A3B
• Original authors: Katanemo

---

📦 Quantization Details

• Quantization method: GGUF
• Quantization tool: llama.cpp
• Precision: Mixed (2-8,bit depands in variant)
• Activation aware: No (weight-only quantinization)
• Group size: 256 (K-quant variants)

---

📦 Available Quantized Files

Quant Format	File Name	Approx. Size	VRAM / RAM Needed	Notes
Q2_K	plano-orchestrator-q2_k.gguf	~11.3 GB	~14 GB	Extreme compression; noticeable quality loss
Q3_K_S	plano-orchestrator-q3_k_s.gguf	~13.3 GB	~15.4 GB	Smaller, faster, lower quality
Q3_K_M	plano-orchestrator-q3_k_m.gguf	~14.7 GB	~16 GB	Better balance than Q3_K_S
Q3_K_L	plano-orchestrator-q3_k_l.gguf	~15.9 GB	~18 GB	Highest-quality 3-bit variant
Q4_0	plano-orchestrator-q4_0.gguf	~17.3 GB	~19.3 GB	Legacy format; simpler quantization
Q4_K_S	plano-orchestrator-q4_k_s.gguf	~17.5 GB	~19.5 GB	Smaller grouped 4-bit
Q4_K_M	plano-orchestrator-q4_k_m.gguf	~ GB	~ GB	Recommended default
Q5_0	plano-orchestratorq-5_0.gguf	~21 GB	~23 GB	Higher quality, larger size
Q5_K_S	plano-orchestrator-q5_k_s.gguf	~21.1 GB	~23 GB	Efficient high-quality variant
Q5_K_M	plano-orchestratorq-5_K_M.gguf	~X GB	~ GB	Near-FP16 quality
Q6_K	plano-orchestratorq-6_k.gguf	~25.1 GB	~27 GB	Minimal quantization loss
Q8_0	plano-orchestrator-q8_0.gguf	~32.5 GB	~36 GB	Maximum quality; large memory

💡 Recommendation: Start with Q4_K_M for the best quality-to-performance ratio.

---

🚀 Usage Example

llama.cpp

./main -m plano-orchestrator-30b-a3b-q6_k.gguf -p "Your prompt here" -n 256

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="plano-orchestrator-30b-a3b-q6_k.gguf",
    n_ctx=4096,
    n_threads=8
)

print(llm("Your prompt here"))

🙋 Contact

Maintainer: M Mashhudur Rahim [XythicK]

Role:
Independent Machine Learning Researcher & Model Infrastructure Maintainer

(Focused on model quantization, optimization, and efficient deployment)

For issues, improvement requests, or additional quantization formats, please use the Hugging Face Discussions or Issues tab.

❤️ Acknowledgements

Thanks to the original model authors for their ongoing contributions to open AI research, and to Hugging Face and the open-source machine learning community for providing the tools and platforms that make efficient model sharing and deployment possible.