Ministral-3B-2410

Parameters

3B (Estimated)

Context Length

128K

Modality

Text

Architecture

Dense

License

Mistral Commercial License

Release Date

10 Oct 2024

Knowledge Cutoff

-

API Pricing (per 1M)

-

Evaluation Benchmarks

No evaluation benchmarks for Ministral-3B-2410 available.

Rankings

Overall Rank

-

Coding Rank

-

About Ministral-3B-2410

Ministral-3B-2410 is a compact edge model developed by Mistral AI for privacy-first, on-device computing and agentic task routing. It supports native function calling and low-latency local inference across a 128K token context window.

Specifications

Architecture specifications are undisclosed for proprietary models.

About Ministral

The Ministral model family, developed by Mistral AI, includes 3B and 8B parameter versions for on-device and edge computing. Designed for compute efficiency and low latency, these models support up to 128K context length. The 8B version incorporates an interleaved sliding-window attention pattern for efficient inference.


Other Ministral Models