models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen2.5-3B-InstructLlama-3.2-3B-InstructNVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4NVIDIA-Nemotron-3-Nano-30B-A3B-BF16SmolLM3-3B-BaseQwen2.5-Coder-3B-InstructSmolLM3-3BNVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16Qwen2.5-3B-Instruct-AWQQwen3.6-14B-A3B-FableVibes-GGUFNVIDIA-Nemotron-3-Nano-30B-A3B-FP8Llama-3.2-3BQwen2.5-3BParable-Granite-4.1-3B-Claude-Fable-5-GGUFOrnith-1.5-35B-A3B-MLXLlama-3.2-3B-Instruct-FP8-dynamict5-3bQwen2.5-3B-Instruct-GGUFQwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUFLlama-3.2-3B-Instruct-GGUFNVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16Ornith-1.5-35B-A3B-MLX-8bitOrnith-1.5-35B-A3B-MLX-4bitLlama-3.2-3B-InstructLlama-3.2-3B-Instruct-FP8Ornith-1.5-35B-A3B-MLX-6bitorpheus-3b-0.1-ftLlama-3.2-3B-Instruct-GGUFLlama-3.2-3B-Instruct-GGUF