Ministral 3 14B
Open vision-language model for efficient local deployment, instruction following, and tool use
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
RELEASE DATEDec 2, 2025
WEIGHTSOpen weights
CONTEXT WINDOW262.1K
MAX OUTPUT262.1K
REASONINGNo
TOOL CALLINGYes
INPUTStext, image
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.