Configuration Parsing Warning:Invalid JSON for config file config.json

Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4 (UNCENSORED)

NVFP4 Quantized Version for NVIDIA Blackwell GPUs

Model Description

This is the NVFP4 (FP4) quantized version of Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM, created using NVIDIA TensorRT Model Optimizer.

Model Size: ~18 GB (4-bit weights)

Requirements

NVFP4 format is optimized for:

  • NVIDIA Blackwell GPUs (B100, B200, GB200)
  • TensorRT-LLM v0.17+

This format is NOT compatible with:

  • Consumer GPUs (RTX 3000/4000/5000 series)
  • llama.cpp
  • Standard PyTorch inference

Usage

With TensorRT-LLM

Deploying NVIDIA Nemotron-3-Nano with TensorRT LLM

Quantization Details

  • Method: NVIDIA ModelOpt NVFP4_DEFAULT_CFG
  • Calibration: 512 samples from WikiText-2
  • Format: HuggingFace checkpoint with quantized weights

Related Models

Author

Eric Elbaz (Ex0bit)

License

NVIDIA Open Model License

Downloads last month
27
Safetensors
Model size
16B params
Tensor type
F32
Β·
BF16
Β·
F8_E4M3
Β·
U8
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4

Finetuned
(74)
this model

Datasets used to train Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4

Collection including Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4