Ministral 3 (14B Base 2512)
A balanced model in the Ministral 3 family, Ministral 3 14B is a powerful, efficient tiny language model with vision capabilities. This model is the base pre-trained version, not fine-tuned for instruction or reasoning tasks, making it ideal for custom post-training processes. The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 24GB of VRAM in BF16, and less than 12GB of RAM/VRAM when quantized.
Benchmark results
| Benchmark | Score | Tags | Source |
|---|---|---|---|
| AGIEval | 64.8% | self-reported llm-stats | link → |
| MATH (CoT) | 67.6% | self-reported llm-stats | link → |
| MMLU | 79.4% | self-reported llm-stats | link → |
| MMLU-Redux | 82.0% | self-reported llm-stats | link → |
| Multilingual MMLU | 74.2% | self-reported llm-stats | link → |
| TriviaQA | 74.9% | self-reported llm-stats | link → |