Downloads · 30 days
9
13% of all-time downloads
Mistral-Nemo-Instruct-2407-NVFP4-FP8-RTN
DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8-RTN
Mistral-Nemo-Instruct-2407-NVFP4-FP8-RTN is a machine learning model from DataSnake. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Quantized NVFP4 version of Mistral-Nemo-Instruct-2407 with the self-attention tensors calibrated in FP8DYNAMIC, created to compare against my hybrid quant. Made with the same version of llm-compressor and compressed-t…
All-time downloads
72
Public
Parameters
8.4B
9.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.7 GB · 100%
Parameter types
How the weights are stored.
U84.4B · 52%
Base models
Model card
From the Hugging Face model README
Quantized NVFP4 version of Mistral-Nemo-Instruct-2407 with the self-attention tensors calibrated in FP8_DYNAMIC, created to compare against my hybrid quant. Made with the same version of llm-compressor and compressed-tensors, using the same calibration data, to isolate the variables as much as possible.
- Type
- mistral
- License
- apache-2.0
- Created
- Mar 28, 2026
- Updated
- May 23, 2026