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

anm2211 new activity about 9 hours ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF:thank you for what you do

helcig updated a model about 11 hours ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

helcig published a model about 11 hours ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

View all activity

Papers

Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts

WUSH-KV: KV Cache Quantization with Data-Adaptive Transforms

View all Papers

in ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF about 9 hours ago

thank you for what you do

#1 opened about 11 hours ago by

updated a model about 11 hours ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

Text Generation • 197B • Updated about 10 hours ago • 32.5k • 106

published a model about 11 hours ago

ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF

Text Generation • 197B • Updated about 10 hours ago • 32.5k • 106

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF about 23 hours ago

Q2_0 randomly generates Chinese tokens during English responses

#60 opened 1 day ago by

in ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller 3 days ago

Nice work. Can you please also release the safetensors?

#4 opened 4 days ago by

updated 2 models 3 days ago

ISTA-DASLab/Qwen3-8B-MatGPTQ

Text Generation • 8B • Updated 3 days ago • 134 • 3

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

Text Generation • 8B • Updated 3 days ago • 188

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 5 days ago

Model update: improved reliability, vision and agentic coding

#25 opened 5 days ago by

updated a model 5 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Image-Text-to-Text • 117B • Updated 5 days ago • 973k • 483

updated a model 5 days ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF

Image-Text-to-Text • 117B • Updated 5 days ago • 973k • 483

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF 9 days ago

Q4 and Q5 versions please?

#35 opened 23 days ago by

in ISTA-DASLab/Kimi-K2.5-P48NVFP4-MoESQ 14 days ago

diamond degradation

#1 opened 24 days ago by

in ISTA-DASLab/Qwen3-8B-MatGPTQ 16 days ago

Add metadata and usage example

#2 opened 23 days ago by

in ISTA-DASLab/Llama-3.1-8B-Instruct-MatGPTQ 16 days ago

Add pipeline tag to model card

#1 opened 23 days ago by

in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUF 17 days ago

Calibration mix and expert scores for the Coder cut?

#22 opened 18 days ago by

authored 2 papers 19 days ago

The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM

Paper • 2510.01650 • Published Feb 23 • 1

Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts

Paper • 2610.02241 • Published 25 days ago • 5

updated a model 19 days ago

ISTA-DASLab/Kimi-K3-P48NVFP4-MoESQ

Text Generation • Updated 19 days ago • 348 • 3

updated a collection 19 days ago

MoESQ

Paired-4:8 + NVFP4 W4A4 expert compressed MoE models for NVIDIA Blackwell Sparse Tensor Cores. • 6 items • Updated 2 days ago • 5

published a model 19 days ago

ISTA-DASLab/Kimi-K3-P48NVFP4-MoESQ

Text Generation • Updated 19 days ago • 348 • 3