Llama-3.1-8B-Instruct-nvfp4
Format: NVFP4 — weights & activations quantized to FP4 with dual scaling.
Base model: meta-llama/Llama-3.1-8B-Instruct
How it was made: One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration.
Notes: Keep
lm_headin high precision; calibrate on long, domain-relevant sequences.
Check the original model card for information about this model.
If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to spread the adoption.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Firworks/Llama-3.1-8B-Instruct-nvfp4
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct