IST Austria Distributed Algorithms and Systems Lab

university

https://ist.ac.at/en/research/alistarh-group/

https://github.com/IST-DASLab

AI & ML interests

None defined yet.

Recent Activity

softmax authored a paper 6 days ago

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

BlackSamorez new activity 11 days ago

ISTA-DASLab/Meta-Llama-3.1-70B-Instruct-AQLM-PV-2Bit-1x16:VLLM error

SpiridonSunRotator updated a model 17 days ago

ISTA-DASLab/Kimi-K2-Thinking-GPTQ-2b-32g-experts

View all activity

Papers

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

View all Papers

ISTA-DASLab 's models 146

ISTA-DASLab/Kimi-K2-Thinking-GPTQ-2b-32g-experts

170B • Updated 17 days ago • 55

ISTA-DASLab/gemma-3n-E4B-it-dev

7B • Updated 27 days ago • 63

ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-gptq-hadamard-transform

17B • Updated Nov 5 • 8

ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-gptq-identity-transform

17B • Updated Nov 5 • 8

ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-rtn-hadamard-transform

17B • Updated Nov 5 • 7

ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-rtn-identity-transform

17B • Updated Nov 5 • 5

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-mxfp4-gptq-hadamard-transform

7B • Updated Nov 5 • 9

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-identity-transform

7B • Updated Nov 5 • 4

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-hadamard-transform

7B • Updated Nov 5 • 113

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-mxfp4-gptq-identity-transform

7B • Updated Nov 5 • 5

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-identity-transform-actorder

7B • Updated Nov 5 • 5

ISTA-DASLab/NVIDIA-Nemotron-Nano-9B-v2-W4A4-nvfp4-gptq-hadamard-transform-actorder

7B • Updated Nov 5 • 5

ISTA-DASLab/Qwen3-30B-A3B-Instruct-2507-W4A4-mxfp4-gptq-hadamard-transform-fake_quant

Updated Nov 3 • 4 • 1

ISTA-DASLab/Llama-3.2-1B-Instruct-W4A4-mxfp4-rtn-identity-transform-sft-fp_quant

Updated Nov 1 • 8

ISTA-DASLab/Llama-3.2-1B-Instruct-W4A4-nvfp4-gptq-identity-transform-sft-fp_quant

Updated Oct 31 • 4

ISTA-DASLab/Llama-3.2-1B-Instruct-W4A4-nvfp4-gptq-hadamard-transform-sft-fp_quant

Updated Oct 31 • 3

ISTA-DASLab/Llama-3.2-1B-Instruct-W4A4-mxfp4-rtn-identity-transform

0.8B • Updated Oct 31 • 3

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4

5B • Updated Oct 27 • 5

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-MXFP4

5B • Updated Oct 27 • 11

ISTA-DASLab/Llama-3.1-8B-Instruct-FPQuant-QAT-NVFP4

5B • Updated Oct 27 • 164

ISTA-DASLab/Llama-3.1-8B-Instruct-FPQuant-QAT-MXFP4

5B • Updated Oct 27 • 283

ISTA-DASLab/Llama-3.2-3B-Instruct-FPQuant-QAT-NVFP4

2B • Updated Oct 27 • 5

ISTA-DASLab/Llama-3.2-3B-Instruct-FPQuant-QAT-MXFP4

2B • Updated Oct 27 • 22

ISTA-DASLab/Llama-3.2-1B-Instruct-FPQuant-QAT-NVFP4

0.8B • Updated Oct 27 • 3

ISTA-DASLab/Llama-3.2-1B-Instruct-FPQuant-QAT-MXFP4

0.8B • Updated Oct 27 • 5

ISTA-DASLab/nanochat-2b-mxfp4

ISTA-DASLab/Qwen3-8B-Instruct-FPQuant-QAT-MXFP4-TEMP

8B • Updated Oct 16 • 27

ISTA-DASLab/Qwen3-4B-FPQuant-QAT-NVFP4

Text Generation • 2B • Updated Oct 16 • 4

ISTA-DASLab/Qwen3-1.7B-FPQuant-QAT-NVFP4

Text Generation • 1B • Updated Oct 16 • 3

ISTA-DASLab/Qwen3-0.6B-FPQuant-QAT-NVFP4

Text Generation • 0.4B • Updated Oct 16 • 4