Grok-1

The open-sourced Grok-1 model has 314 billion parameters.

CommonProductProductivityLarge Language ModelMixture-of-Experts Model

Grok-1 is a 314-billion parameter expert mixture model (Mixture-of-Experts) trained from scratch by xAI. This model has not been fine-tuned for specific applications (such as dialogue) and is a raw baseline checkpoint from the pre-training stage of Grok-1.

Provides a large language model without specific task fine-tuning
Contains 314 billion parameters
with 25% of the weights active on a given token
Trained using a custom training stack based on JAX and Rust

Suitable for enterprises and research institutions that need to conduct research and development on large language models. It can be used for a variety of natural language processing tasks.

Researchers use Grok-1 for experiments on natural language understanding and generation
Developers leverage Grok-1 to build intelligent systems capable of handling complex dialogues
Businesses utilize Grok-1 as a base model to further develop industry-specific AI applications

Visit

Grok-1 Visit Over Time

Monthly Visits

1314947

Bounce Rate

46.13%

Page per Visit

2.4

Visit Duration

00:01:07

Grok-1 Visit Trend

Grok-1 Visit Geography

Grok-1 Traffic Sources

Grok-1 Alternatives

Google Gemma 2 — Next-generation open-source AI model with exceptional performance.

Programming•AI model•open-source

138

Tele-FLM — An open-source multilingual large language model with 52 billion parameters

Programming•Large Language Model•Multilingual Support

InternLM-Math-Plus — A bilingual open-source large language model (LLM) specializing in mathematical reasoning.

Programming•Mathematical Reasoning•Bilingual Model

132

OpenBioLLM-Llama3-8B — An open-source large language model specifically designed for the biomedical field

OpenSource•Biomedical•Natural Language Processing

372

DBRX — A new efficient open-source large language model standard

Productivity•Artificial Intelligence•Large Language Model

3048

MediaTek Research Breeze-7B — An open-source large language model for Chinese and English.

Productivity•Open-source•Large Language Model

588

DeepSeek-R1-Lite-Preview — Unlock powerful reasoning capabilities to enhance AIME & MATH benchmark performance.

ChineseSelection•Reasoning•Performance

Mistral-Large-Instruct-2411 — A large language model with 123 billion parameters, equipped with advanced reasoning and coding capabilities.

Programming•Large Language Model•Reasoning

Qwen2.5-Coder-1.5B-Instruct-GGUF — The Qwen2.5-Coder series features a 1.5B parameter instruction-tuned model.

Programming•Code Generation•Code Reasoning

Pixtral-Large-Instruct-2411 — A 124B-parameter multimodal large language model.

Productivity•Multimodal•Large Language Model

Kaka Subtitle Assistant — An intelligent subtitle assistant based on LLM, generating high-quality video subtitles with one click

Video•Subtitle Generation•Speech Recognition

138

Qwen2.5-Coder-3B — The 3B parameter model in the Qwen2.5-Coder series focuses on code generation and comprehension.

Programming•Code Generation•Code Reasoning

Hermes 3 - Llama-3.1 70B — The latest large language model in the Hermes series.

Programming•Large Language Model•Text Generation

168

Nous Chat — The first unrestricted AI chatbot launched by Nous Research

chatting•Chatbot•Large Language Model

234

PPLLaVA — GPU implementation model for video sequence understanding

Video•Video Understanding•Large Language Model

Tencent-Hunyuan-Large — Industry-leading open-source large mixture-of-experts model

Productivity•Artificial Intelligence•Natural Language Processing

234

Ferret-UI-Llama8b — A multimodal large language model based on Llama-3-8B, focused on UI tasks.

Programming•Multimodal•Large Language Model

108

Universal-2 — Next-generation speech AI offering superior audio data processing capabilities.

Productivity•Speech Recognition•Audio Processing

easegen-admin — Open-source digital course creation platform

OpenSource•Open-source•Education

216

Llama-3.1-Nemotron-70B-Instruct — A large language model customized by NVIDIA to enhance the supportiveness of query answering.

Productivity•NVIDIA•large language model

168

SiYuan — Privacy-focused, self-hosted, fully open-source personal knowledge management system

Productivity•Electronic notes•Knowledge management

FaceFusion Labs — Industry-leading facial manipulation platform

Image•Facial Manipulation•Facial Recognition

216

Ministral-8B-Instruct-2410 — A high-performance language model that supports local intelligence and on-device computation.

Programming•Large Language Model•Local Intelligence

Open-O1 — An open-source large language model matching proprietary capabilities.

Programming•Open Source•Large Language Model

Diabetica-7B — A large language model specialized for diabetes care.

Others•AI Healthcare•Diabetes Care

Diabetica-1.5B — A large language model specifically designed for diabetes care.