https://arxiv.org/abs/2502.05003
IST Austria Distributed Algorithms and Systems Lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
4
Models prequantized with [HIGGS](https://arxiv.org/abs/2411.17525) zero-shot quantization. Requires the latest `transformers` to run.
-
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
Paper • 2411.17525 • Published -
ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-GPTQ-4bit
Updated • 40 • 2 -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-GPTQ-4bit
Text Generation • Updated • 5 -
ISTA-DASLab/Llama-3.1-8B-Instruct-HIGGS-GPTQ-3bit
Text Generation • Updated • 13
models
87
ISTA-DASLab/Llama-2-7b-AQLM-1Bit-1x8-hf
Updated
•
2
ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g
Image-Text-to-Text
•
Updated
•
14.1k
•
9
ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g
Image-Text-to-Text
•
Updated
•
512
•
6
ISTA-DASLab/QuEST-800M-INT4
Text Generation
•
Updated
ISTA-DASLab/QuEST-800M-INT1
Updated
ISTA-DASLab/QuEST-800M-sparse-INT4
Updated
ISTA-DASLab/DeepSeek-R1-Distill-Qwen-14B-HIGGS-4bit
Text Generation
•
Updated
•
14
ISTA-DASLab/DeepSeek-R1-HIGGS-4bit
Updated
•
8
ISTA-DASLab/DeepSeek-R1-Distill-Qwen-32B-HIGGS-4bit
Text Generation
•
Updated
•
26
ISTA-DASLab/DeepSeek-R1-Distill-Llama-70B-HIGGS-4bit
Text Generation
•
Updated
•
6