New GGUF drop! 📦 Qwen3-0.6B ready to download 👉 huggingface.co/Open4bits/Qw...

Introduction to Artificial Intelligence
New blog is live! Learn what AI is and why it matters.

arkdevlabs.com/global/blog/...

#AI #ArtificialIntelligence #ArkDevLabs

New release!
Gemma-3-270M (GGUF) is now available for local AI workflows.

Grab it here 👇
huggingface.co/Open4bits/ge...

#LocalAI #GGUF #HuggingFace

New release!
Gemma-3-270M-IT (GGUF) is now live — great for Italian language tasks and local inference.

👉 huggingface.co/Open4bits/ge...

#LocalAI #GGUF #HuggingFace

We’ve just released a new blog on GGUF 🚀
Learn what it is, why it matters, and how it’s shaping local AI models.
👉 arkdevlabs.com/global/blog/...

#AI #GGUF #MachineLearning #ArkDevLabs

Open4bits/Granite-4.0-H-Micro-FP4 is now available on Hugging Face.

The FP4 variant delivers extreme compression for highly memory-constrained inference environments.

Download:
huggingface.co/Open4bits/gr...

Open4bits/Granite-4.0-H-Micro-NF4 is now available on Hugging Face.

The NF4 variant uses 4-bit NormalFloat quantization to maximize memory efficiency with minimal quality loss.

Download:
huggingface.co/Open4bits/gr...

Open4bits/Granite-4.0-H-Micro-INT8 is now available on Hugging Face.

The INT8 variant offers a balanced trade-off between performance, memory efficiency, and inference speed.

Download:
huggingface.co/Open4bits/gr...

Open4bits/Granite-4.0-H-Micro-FP16 is now available on Hugging Face.

The FP16 variant provides a high-fidelity baseline suitable for accurate inference and further experimentation.

Download:
huggingface.co/Open4bits/gr...

Open4bits/Granite-4.0-H-Micro-Quantized models are now available on Hugging Face.

Multiple quantized variants (FP16, FP8, INT8, NF4, FP4) are provided to support efficient inference across diverse hardware and deployment environments.

Download:
huggingface.co/Open4bits/gr...

Open4bits/LFM2.5-1.2B-Instruct-Quantized is now available on Hugging Face.

Multiple quantized variants (FP16, FP8, INT8, NF4) are provided for efficient inference across diverse hardware.

Download:
huggingface.co/Open4bits/LF...

Open4bits/LFM2.5-1.2B-Base-Quantized is now available on Hugging Face.

Quantized variants (FP16, FP8, INT8, NF4) are provided for efficient inference and deployment.

Download:
huggingface.co/Open4bits/LF...