Very High Reasoning

Codestral Mamba

Codestral Mamba is Mistral AI's specialized Mamba2 language model designed for code generation across 80+ programming languages, offering linear time inference and the ability to handle up to 256,000 tokens for lightning-fast local code assistance. With 7.3 billion parameters and benchmark performance matching larger models, it delivers state-of-the-art code generation capabilities while remaining freely available under the Apache 2.0 license.

256k Context

Very High Intelligence

Mar '24 Knowledge

Available for Chat, Vision, and File Uploads.

Performance Benchmarks

HumanEval

75.0%

MBPP

68.5%

MMLU

63.47%

How do you want to interact?

Start a Conversation

Ask anything.
Have a natural conversation, brainstorm ideas, draft emails, or ask for advice.

Start Chatting

Use a Persona

Specialized Experts.
Instruct the AI to act as a Coding Tutor, Marketing Expert, or Travel Guide.

Pick a Persona

Why use Codestral Mamba?

Capability Examples

Function Writing

Write me a Python function that returns the factorial of a number

def factorial(n): return 1 if n <= 1 else n factorial(n-1)

Code Cleanup

Clean up this messy JavaScript: var x=5;var y=10;console.log(x+y)

const x = 5; const y = 10; console.log(x + y);

How to use

Go to Chat

Navigate to the "AI Chat" page.

Select Model

Ensure Codestral Mamba is selected.

Type Prompt

Ask a question or paste code.

Interact

Refine the answer by replying to the AI.

Made with ❤ by AI4Chat

Flash Sale 50% Off!

Daily Limit Reached

Upgrade to Premium

Credits Exhausted