Meet Gemma-4-Giftige-Blume-31B-v1-GGUF: a 31B merge model that's uncensored, creative, and ready for roleplay. It's a GGUF build, so you can run it locally with ease. Perfect for those who want a powerful, unrestricted AI companion.

Meet KOLIBRI-1-DERISKED-BF16-i1-GGUF: a GGUF model built for long-context conversations, reasoning, and tool-calling. With MoE architecture and bfloat16 precision, it's ready for vLLM and transformers. Perfect for devs exploring efficient AI.

Meet phi4-reasoning-supervisor-v1: a GGUF model fine-tuned for reasoning tasks. Built on phi3 architecture, it's ready for text-generation-inference and comes with an Apache-2.0 license. Perfect for your next reasoning project!

Meet Alternate-Qwen3.5-9B-Claude-4.6-Opus-GGUF: a 9B conversational model that blends Qwen3.5 with Claude 4.6 Opus vibes. GGUF format means it runs locally on your machine, no cloud needed. Perfect for chat apps and experiments.

Meet Qwopus3.5-9B-v3-GGUF: a 9B model built for reasoning and competitive programming. With chain-of-thought and LoRA fine-tuning, it's a lean mean coding machine you can run locally. #AI #LLM

Life when everything was an API not just a skill

Meet GaMS3-12B-Multimodal, a vision-language model that speaks Slovenian and English. It's a 12B parameter model packaged in GGUF format for easy local inference. Exciting for multilingual multimodal AI!

Meet Qwen-SEA-LION-v4-4B-VL-GGUF: a 4B parameter vision-language model optimized for Southeast Asia. It speaks English, Vietnamese, Indonesian, Thai, Malay, Tamil, Tagalog, and Burmese, all in a GGUF package for easy local deployment.

Meet BloomZ-7B1-Vi-Math-GGUF: a quantized version of a 7B model fine-tuned for Vietnamese math. It's ready for transformers and runs efficiently on consumer hardware. Perfect for building math tutoring tools or solving problems in Vietnamese.

Meet DeepSeek-R1-14B-CoT-Math-Reasoning-Full-GGUF: a 14B model that thinks step by step for math. Quantized for GGUF, it's ready to run locally and tackle your toughest problems.