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 7 days ago

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

BlackSamorez new activity 13 days ago

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

SpiridonSunRotator updated a model 19 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/Llama-3.1-8B-Instruct-MR-GPTQ-mxfp

Image-Text-to-Text • 5B • Updated Oct 3 • 7

ISTA-DASLab/Llama-3.1-8B-Instruct-MR-GPTQ-nvfp

Image-Text-to-Text • 5B • Updated Oct 3 • 25

ISTA-DASLab/Llama-3.2-1B-Instruct-GGUF

1B • Updated Sep 11 • 97

ISTA-DASLab/Llama-3.1-8B-Instruct-GGUF

8B • Updated Sep 11 • 94

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4-1000steps

Text Generation • 5B • Updated Aug 11 • 7

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4-1400steps

Text Generation • 5B • Updated Aug 11 • 4

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4-600steps

Text Generation • 5B • Updated Aug 10 • 5

ISTA-DASLab/Qwen3-8B-FPQuant-QAT-NVFP4-200steps

Text Generation • 5B • Updated Aug 10 • 9

ISTA-DASLab/Qwen3-1.7B-FPQuant-QAT-NVFP4-600steps

Text Generation • 1B • Updated Aug 10 • 6

ISTA-DASLab/Qwen3-1.7B-FPQuant-QAT-NVFP4-200steps

Text Generation • 1B • Updated Aug 10 • 4

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

Text Generation • 5B • Updated Aug 4 • 8

ISTA-DASLab/Qwen3-1.7B-FPQuant-RTN-MXFP4

Text Generation • 1B • Updated Aug 4 • 6

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

Text Generation • 1B • Updated Aug 4 • 5

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

Text Generation • 2B • Updated Aug 4 • 5

ISTA-DASLab/Qwen3-4B-FPQuant-RTN-MXFP4

Text Generation • 2B • Updated Aug 4 • 4

ISTA-DASLab/Qwen3-0.6B-FPQuant-RTN-MXFP4

Text Generation • 0.4B • Updated Aug 4 • 6 • 1

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

Text Generation • 0.4B • Updated Aug 4 • 9

ISTA-DASLab/Qwen3-32B-FPQuant-GPTQ-MXFP4

18B • Updated Jul 24 • 2

ISTA-DASLab/Qwen3-14B-FPQuant-GPTQ-MXFP4

9B • Updated Jul 24 • 4

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

5B • Updated Jul 24 • 6

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

5B • Updated Jul 20 • 5

ISTA-DASLab/Qwen3-8B-FPQuant-RTNv2-MXFP4

5B • Updated Jul 19 • 6

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

Text Generation • 5B • Updated Jul 15 • 7

ISTA-DASLab/DeepSeek-V3-0324-GPTQ-4b-128g-experts

Text Generation • Updated Jun 3 • 11 • 3

ISTA-DASLab/DeepSeek-R1-0528-GPTQ-4b-128g-experts

Text Generation • Updated Jun 2 • 17 • 5

ISTA-DASLab/gemma-3-12b-it-GPTQ-4b-128g

Image-Text-to-Text • 3B • Updated Apr 13 • 1.38k • 6

ISTA-DASLab/gemma-3-4b-it-GPTQ-4b-128g

Image-Text-to-Text • 2B • Updated Apr 13 • 908 • 6

ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g-experts

Text Generation • Updated Apr 8 • 16 • 4

ISTA-DASLab/DeepSeek-R1-GPTQ-4b-128g

Text Generation • Updated Apr 8 • 13

ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g

Image-Text-to-Text • 5B • Updated Apr 6 • 579 • 17