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.
Qwen3.6-35B-A3B-NVFP4NVIDIA-Nemotron-3-Nano-4B-BF16Gemma-4-31B-IT-NVFP4NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4bigvgan_v2_22khz_80band_256xnemotron-3.5-asr-streaming-0.6bQwen2.5-VL-7B-Instruct-NVFP4NVIDIA-Nemotron-3-Super-120B-A12B-BF16Qwen3.5-122B-A10B-NVFP4dragon-multiturn-query-encoderdragon-multiturn-context-encoderGemma-4-26B-A4B-NVFP4Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8bigvgan_v2_44khz_128band_512xCosmos3-EdgeNVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4llama-nemotron-rerank-1b-v2NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4Cosmos-Reason2-2BQwen3-14B-NVFP4Qwen3.8-27B-NVFP4parakeet-tdt-0.6b-v3NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16Qwen3.6-27B-NVFP4GLM-5.2-NVFP4Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16llama-nemotron-embed-1b-v2
