Information

Model quantized using TensorRT-Model-Optimizer. Model quantized to NVFP4 format with KV cache quantized to FP8 format for compatibility.

Safetensors

Model size

7B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rahtml/NVIDIA-Nemotron-Nano-12B-v2-NVFP4

Base model

Finetuned

Finetuned

(17)

this model