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.
Qwen3.6-27B-FP8Qwen3.8-27B-NVFP4gemma-4-E4B-it-fp8Qwen3.8-27B-NVFP4-ModelOptQwen-3.6-35B-A3B-VRAP-4-bit-AWQ-21.2GBgemma-4-31B-it-fp8Qwen3.8-27B-FP8-dynamicQwen3.6-27B-NVFP4Qwen3.6-27B-mini-IQ4-XS-MTP-16GB-VRAM-GGUFQwen3.8-27B-FP8gemma-4-12B-it-fp8Cosmos-Reason2-8B-NVFP4gemma-4-12B-it-nvfp4Qwen2.5-VL-7B-VRAGOrnith-1.0-35B-NVFP4-ModelOptQwen3.6-35B-A3B-NVFP4-MLP-Only-ModelOptShieldstral-1.0-3B-NVFP4-ModelOptQwen3.6-35B-A3B-NVFP4Cosmos-Reason2-2B-NVFP4Qwen3.6-35B-A3B-NVFP4-ModelOptvideo-8b-grpo-hopchain-v40-vript-gs160Sapnous-VR-47BSapnous-VR-6BOrnith-1.0-9B-NVFP4-ModelOptMiMo-VRPRM-7Bgemma-4-31B-it-nvfp4Sapnous-VR-6B-GGUFQwen2.5-VRPRM-7BGeoOSSVision-VRS-LoRA-Optimized-fullQwen3-VRPRM-4B
