The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
An 8B tool-calling model that picks the right tool with valid arguments and does not loop. Fine-tuned from Ministral 3 8B on production agent traffic. Apache-2.0.
Ministral 3 3B Instruct, quantized to Q4_K_M for fast local Ollama inference on Apple Silicon.
A Coding Model based On Ministral-3:3b
Neuris APEX is a 3B cybersecurity input-classification model fine-tuned from Ministral 3B to identify malicious, suspicious, ambiguous, and safe user-controlled inputs across common attack families.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. This version is the converted model from Huggingface with full FB16 precision.
Fine-tuned Ministral-3 8B for tool-calling in CAAL, an open-source voice assistant by CoreWorxLab.