What open-source LLMs or SLMs are you in search of? 34266 in total.

LLM Leaderboard: HuggingFace Open LLM Leaderboard v1 (old) Was this list helpful?

Explore the llm list from the Hugging Face Open LLM Leaderboard, the premier source for tracking, ranking, and evaluating the best in open LLMs (large language models) and chatbots. This leaderboard, a vital resource for developers, AI researchers, and enthusiasts, showcases the cutting-edge of LLM technology.
What is the "HF Open LLM Leaderboard"? It is a platform where users can submit their models for automated evaluation on a GPU cluster, making the Hugging Face LLM Leaderboard a hub for innovation and development in AI.
Featuring evaluations conducted with the Eleuther AI harness, the Hugging Face Leaderboard offers in-depth insights into model performance across various domains, including high-school science knowledge, logical fallacies identification, and knowledge bias. It's a comprehensive tool for assessing language models, continuously refreshed with new benchmarks and updated evaluations.
For anyone looking to stay at the forefront of AI and language model development, the Hugging Face Leaderboard is an invaluable asset. It's more than just a leaderboard; it's a dynamic and evolving platform that reflects the latest advancements in LLM technology. Whether you're evaluating models or seeking inspiration, the Hugging Face LLM Leaderboard is the go-to destination for the latest in LLM and chatbot technology.
Model Size
LLM Leaderboard: HuggingFace Open LLM Leaderboard v1 (old)
Loading a list of LLMs...
Here comes the list of the Small and Large Language Models
Model Name Maintainer Size Score VRAM (GB) Quantized License Context Len Likes Downloads Modified Languages Architectures
— Large Language Model
— Adapter
— Code-Generating Model
— Listed on LMSys Arena Bot ELO Rating
— Original Model
— Merged Model
— Instruction-Based Model
— Quantized Model
— Finetuned Model
— Mixture-Of-Experts
Table Headers Explained  
  • Name — The title and maintainer account associated with the model.
  • Params — The number of parameters used in the model.
  • Score — The model's score depending on the selected rating (default is the Open LLM Leaderboard on HuggingFace).
  • Likes — The number of "likes" given to the model by users.
  • VRAM — The number of GB required to load the model into the memory. It is not the actual required amount of RAM for inference, but could be used as a reference.
  • Downloads — The total number of downloads for the model.
  • Quantized — Specifies whether the model is quantized.
  • CodeGen — Specifies whether the model can recognize or infer source code.
  • License — The type of license associated with the model.
  • Languages — The list of languages supported by the model (where specified).
  • Maintainer — The author or maintainer of the model.
  • Architectures — The transformer architecture used in the model.
  • Context Len — The content length supported by the model.
  • Tags — The list of tags specified by the model's maintainer.

Choose another global filter

  All Large Language Models   LMSYS ChatBot Arena ELO   OpenLLM LeaderBoard v1   OpenLLM LeaderBoard v2   Original & Foundation LLMs   OpenCompass LeaderBoard   Recently Added Models   Code Generating Models   Instruction-Based LLMs   Uncensored LLMs   LLMs Fit in 4GB RAM   LLMs Fit in 8GB RAM   LLMs Fit in 12GB RAM   LLMs Fit in 24GB RAM   LLMs Fit in 32GB RAM   GGUF Quantized Models   GPTQ Quantized Models   EXL2 Quantized Models   Fine-Tuned Models   LLMs for Commercial Use   TheBloke's Models   Context Size >16K Tokens   Mixture-Of-Experts Models   Apple's MLX LLMs   Small Language Models
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601