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
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
models
146
ISTA-DASLab/Kimi-K2-Thinking-GPTQ-2b-32g-experts
170B
•
Updated
•
55
ISTA-DASLab/gemma-3n-E4B-it-dev
7B
•
Updated
•
63
ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-gptq-hadamard-transform
17B
•
Updated
•
8
ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-gptq-identity-transform
17B
•
Updated
•
8
ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-rtn-hadamard-transform
17B
•
Updated
•
7
ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-rtn-identity-transform
17B
•
Updated
•
5
ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-mxfp4-gptq-hadamard-transform
7B
•
Updated
•
9
ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-identity-transform
7B
•
Updated
•
4
ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-hadamard-transform
7B
•
Updated
•
113
ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-mxfp4-gptq-identity-transform
7B
•
Updated
•
5