A collection of low precision models generated by Intel Neural Compressor including mxfp8, mxfp4 and nvfp4.
Intel
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all Papers
Organization Card

GenAI SW Catalogue
Choose from a broad range of solutions designed to simplify and accelerate your AI development timeline, from training and optimization to deployment.
![]() Chat Q & A SolutionIntel® AI for Enterprise RAG Chat Q&A builds upon the strong foundation of OPEA. It extends this base with key features that enhance security, scalability, performance and user experience. |
![]() Code Generation SolutionA specialized AI model designed to generate high-quality computer code, accelerating the development process with greater efficiency. |
![]() Visual Q & A SolutionAnswers open-ended questions by interpreting visual data, allowing AI to understand and respond to queries about images. |
![]() Content Summarization SolutionSummarizes large documents or datasets, providing concise and relevant insights quickly. |
![]() Code TranslationAutomates code translation from one programming language to another to help maintain code efficiency and reduce human error in an enterprise setting. |
![]() Audio Q & A SolutionAn AI-powered bot that enables seamless voice-based interactions, allowing large language models (LLMs) to engage in dynamic conversations with users. |
![]() FAQ Generation SolutionGenerates frequently asked questions (FAQs) from various data types with optimized performance, security and scalability for thousands of users. |
||
Community
Join us on the Intel DevHub Discord.
Disclaimer
Intel is not responsible for the download or security of Hugging Face assets.
spaces
20
pinned
Running
11
Synthetic Data Generator
⚗
Create synthetic datasets for AI applications
pinned
Running
7
UnlearnDiffAtk Benchmark
🥇
Display and filter model evaluation results
pinned
Running
Featured
191
Low-bit Quantized Open LLM Leaderboard
🏆
Track, rank and evaluate open LLMs and chatbots
Running
2
Hebrew Math Tutor
🚀
Streamlit template space
Running
12
Intel® AI for Enterprise Inference
📚
LLM Chatbot with Intel® Gaudi®
models
263
Intel/Qwen3-235B-A22B-MXFP4-AutoRound
Updated
Intel/Qwen3-235B-A22B-MXFP8-AutoRound
Updated
Intel/FramePack-MXFP8-AutoRound-Recipe
Updated
Intel/Llama-3.1-70B-Instruct-AutoRound-Recipe
Updated
Intel/Llama-3.1-8B-Instruct-AutoRound-Recipe
Updated
Intel/Llama-4-Scout-17B-16E-Instruct-MXFP4-AutoRound-Recipe
Updated
Intel/FLUX.1-dev-MXFP8-AutoRound-Recipe
Updated
Intel/Llama-3.3-70B-Instruct-AutoRound-Recipe
Updated
Intel/Qwen3-8B-w2g64-AutoRound-test
2B
•
Updated
•
24
•
1
Intel/Qwen3-30B-A3B-FP8-Test-Only
31B
•
Updated
•
99
datasets
24
Intel/dynamic_model_information
Updated
•
381
Intel/ld_requests
Updated
•
808
•
4
Intel/blog
Viewer
•
Updated
•
6
•
416
Intel/misinformation-guard
Viewer
•
Updated
•
41.9k
•
207
•
1
Intel/SK-VQA
Viewer
•
Updated
•
2.01M
•
930
•
1
Intel/Uncovering_LVLM_Bias
Viewer
•
Updated
•
54.5M
•
351
Intel/NeuroComparatives
Viewer
•
Updated
•
8.71M
•
43
•
1
Intel/AI-Peer-Review-Detection
Updated
•
22
•
1
Intel/polite-guard
Viewer
•
Updated
•
100k
•
144
•
15
Intel/fivl-instruct
Viewer
•
Updated
•
1.22M
•
198






