Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
Paper • 2512.02010 • Published
Quantized NVFP4 version of Mistral-Nemo-Instruct-2407 with the down_proj tensors calibrated in FP8_DYNAMIC and the rest using Four Over Six adaptive block scaling, 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.
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for DataSnake/Mistral-Nemo-Instruct-2407-Down-4over6
Base model
mistralai/Mistral-Nemo-Base-2407 Finetuned
mistralai/Mistral-Nemo-Instruct-2407