Best Quantized Models
Updated Daily
The LEGO Ideas NASA Apollo Saturn V (21315) is a monumental achievement in Lego design, faithfully recreating the iconic rocket that took astronauts to the moon. This set boasts incredible detail and...
The Himeji Castle set is a stunning representation of Japanese history. It captures the intricate multi-tiered structure and traditional aesthetics of one of Japan's most famous landmarks. The build f...
The LEGO Technic Porsche 963 Hybrid Race Car (43157) is a highly detailed and functional replica of the iconic Porsche 963. This set features realistic suspension, steering, and a hybrid powertrain, o...
The LEGO Ideas Vespa is a nostalgic tribute to the iconic Italian scooter. It features a sleek design and realistic proportions that make it an excellent desk accessory or shelf piece. The build proce...
A detailed 2,573-piece model with working suspension, gearbox, and a winch, inspired by the classic Defender.
The Mistral 7B Instruct model, available in GGUF format, represents a fantastic entry point into self-hosted LLMs. Its relatively small size (7 billion parameters) makes it manageable on consumer hard...
A powerful general-purpose LLM that can be self-hosted and integrated into JetBrains for code assistance.
llama.cpp-mac is a highly optimized port of the llama.cpp library specifically tailored for Apple Silicon Macs. Its designed to deliver exceptional inference performance, particularly with GGUF quanti...
StarCoder2, trained by DeepMind and Hugging Face, is a highly respected, academically validated model for code generation. It excels at understanding the context provided by surrounding code blocks an...
Google's lightweight code model designed for local deployment and integration into IDEs like JetBrains.
This specific, highly optimized file format (GGUF) of the Mistral 7B model is the most accessible entry point for beginners. By using a quantized version, you drastically reduce VRAM requirements whil...
