Ministral 3 14B Instruct 2512 BF16
Mistral's Ministral 3 14B Instruct 2512 is a chat model that excels at instruction-based tasks, thanks to its fine-tuning in FP8 for such use cases. With a large context window of 262,144 tokens, it can process extensive conversations or texts.
Input
Output
Context
262K
Max Output
8K
Parameters
13.9B
Technical Specifications
Model TypeChat
Context Window262,144 tokens
Max Output Tokens8,000 tokens
Parameters13.9B
Release DateOct 31, 2025
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
TextImage
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Ministral 3 14B Instruct 2512 BF16
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.