ISTA-DASLab/Llama-3.2-1B-Instruct-FPQuant-QAT-NVFP4
0.8B • Updated
• 12
FP-Quant QAT
High-quality QAT FP4 models to use with the fp_quant vLLM/Transformers integration on Blackwell NVIDIA GPUs. See https://arxiv.org/abs/2509.23202
-
-
ISTA-DASLab/Llama-3.2-1B-Instruct-FPQuant-QAT-MXFP4
0.8B • Updated • 2 -
ISTA-DASLab/Llama-3.2-3B-Instruct-FPQuant-QAT-NVFP4
2B • Updated • 52 -
ISTA-DASLab/Llama-3.2-3B-Instruct-FPQuant-QAT-MXFP4
2B • Updated -
ISTA-DASLab/Llama-3.1-8B-Instruct-FPQuant-QAT-NVFP4
5B • Updated • 1 -
ISTA-DASLab/Llama-3.1-8B-Instruct-FPQuant-QAT-MXFP4
5B • Updated -
ISTA-DASLab/Qwen3-0.6B-FPQuant-QAT-NVFP4
Text Generation • 0.4B • Updated • 3 -
ISTA-DASLab/Qwen3-1.7B-FPQuant-QAT-NVFP4
Text Generation • 1B • Updated • 12 -
ISTA-DASLab/Qwen3-4B-FPQuant-QAT-NVFP4
Text Generation • 2B • Updated • 6 -
ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4
5B • Updated • 7 -
ISTA-DASLab/Qwen3-8B-FPQuant-QAT-MXFP4
5B • Updated • 1