michaelw9999/Nemotron-Cascade-2-30B-A3B-NVFP4-GGUF

Quantization vs nvidia/Nemotron-Cascade-2-30B-A3B. michaelw9999/Nemotron-Cascade-2-30B-A3B-NVFP4-GGUF is a quantized version of the other (T40/BF16).

On the Hub · Downloads on Model Pulse