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.
Qwen3-Coder-30B-A3B-Instruct-GGUFQwen3.6-35B-A3B-NVFP4Ornith-1.5-35B-A3B-GGUFQwen2.5-3B-InstructLlama-3.2-3B-InstructQwen3-30B-A3BOrnith-1.5-35B-A3B-NVFP4Qwen3-VL-30B-A3B-Instruct-AWQPowerMoE-3bQwen3-Coder-30B-A3B-Instruct-FP8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4Qwen3-Coder-30B-A3B-Instruct-AWQ-4bitNVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4Qwen3.6-35B-A3B-abliterated-v4Qwen3-30B-A3B-Instruct-2507NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Qwen2.5-Coder-3B-InstructSmolLM3-3BSmolLM3-3B-BaseQwen3-Coder-30B-A3B-InstructNVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16Ornith-1.5-35B-A3B-FP8Qwen3-30B-A3B-Instruct-2507-FP8Qwen2.5-3B-Instruct-AWQQwen-AgentWorld-35B-A3B-GGUFQwen3.6-14B-A3B-FableVibes-GGUFgranite-4.1-3bOrnith-1.5-35B-A3BNVIDIA-Nemotron-3-Nano-30B-A3B-FP8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8