FW-Ministral-3-3B-Instruct-2512

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.

About this model

Ministral 3 3B Instruct 2512 is the FP8 instruct post-trained version of the Ministral 3 3B family, built from a 3.4B language model and a 0.4B vision encoder. It supports text and image inputs, multilingual instruction following across dozens of languages, strong system-prompt adherence, and native function calling with JSON output. Designed for edge deployment, it can fit in 8GB of VRAM in FP8 and supports a 256K context window.

Key model capabilities

• Text-and-image understanding with image analysis
• Multilingual support across dozens of languages
• Strong system-prompt adherence
• Native function calling and JSON output
• Edge-optimized FP8 deployment
• 256K context window