User seeks to run 35B NVFP4 models on RTX 5090 with long context

A user is asking for recommendations and assistance in running 35B parameter models using the NVFP4 quantization format on an NVIDIA RTX 5090 GPU. The goal includes supporting a context length of 100k+ tokens, ideally with uncensored or specialized models.

• Previous attempts to run AEON-7 Ornith 1.0 35B Uncensored NVFP4 failed, as the recommended serve command was optimized for GDX Spark 128GB hardware.
• The user reports no issues running 35B .gguf models but has been unable to successfully configure vLLM for this specific setup.

The post highlights current challenges in deploying high-capacity NVFP4 models on consumer-grade RTX 5090 hardware with extended context windows.