Mixtral 8x22b Instruct V0.1
Mistral's Mixtral 8x 22B Instruct V 0.1 is a chat-focused large language model, fine-tuned for instruct-style interactions, with a context window of 65,536 tokens. It is particularly suited for handling complex, multi-step conversations and function calls, as evidenced by its support for special tokens related to tool calls and results.
Input
Output
Context
66K
Max Output
4K
Parameters
140.6B
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Estimated GPU Requirements for Mixtral 8x22b Instruct V0.1
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Mistral
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.