open source

Mistral 8x22B

Provided by: • Framework: JAX

Mixtral 8x22B is a cutting‑edge open‑source Mixture‑of‑Experts LLM by Mistral AI. With 141B total params of which 39B are active, a huge 64K context window, and Apache 2.0 license, it excels at multilingual reasoning, math, and code—delivering top-tier benchmarks in efficiency and performance.

Model Performance Statistics

29

Views

April 17, 2024

Released

Jul 20, 2025

Last Checked

0.2

Version

Capabilities
  • Text Generation
  • Code Completion
Performance Benchmarks
MMLU82.1%
Inference Speed12 tokens/sec (A100)
Technical Specifications
Parameter Count
N/A
Training & Dataset

Dataset Used

C4, Wikipedia, StackExchange

Related AI Models

Discover similar AI models that might interest you

More AI Models
Modelopen source

BERT

BERT

BERT

Google

BERT is a groundbreaking open-source transformer model developed by Google that enables bidirectional understanding of text, improving many NLP tasks like question answering and sentiment analysis.

Natural Language Processingnlp
54
Modelopen source

GPT-Neo

GPT-Neo

GPT-Neo

EleutherAI

GPT-Neo is an open-source large language model developed by EleutherAI, designed as an alternative to OpenAI’s GPT-3. It uses the Transformer architecture to generate coherent, human-like text based on a given prompt. GPT-Neo is trained on the Pile dataset, which is a diverse and large-scale text corpus, making it capable of many NLP tasks such as text generation, summarization, translation, and question answering. GPT-Neo models come in different sizes, the most popular being the 1.3B and 2.7B parameter versions.

Natural Language Processingnlp
42
Modelopen source

Fairseq

Fairseq

Fairseq

Meta AI

Fairseq is Meta AI’s open-source PyTorch-based toolkit for training sequence-to-sequence models, widely used in machine translation, text summarization, and other NLP applications.

Natural Language Processingnlptranslation
38