Vinci MLE 1.0 · Open-weight release
MLE 30B 1.0
A larger research model trained to help investigate problems while building AI. Developed in Canada by SimpleDirect®, using IBM Granite 4.1 30B as its foundation.
What it is trained to help with
It is trained to read files and experiment results, look for problems, and explain what to do next.
The training uses 91 examples of multi-step work across 64 tasks. It covers eight areas: data quality; understanding experiments; restarting failed training; managing memory and batches; checking how results are scored; unstable training; packaging and running models; and matching model settings.
Change it. Leave it. Ask for more.
- Make a change
- Suggest a limited fix when the evidence supports it.
- Leave it alone
- Keep a working setup as it is when a change is not justified.
- Ask for more evidence
- Explain what is missing instead of guessing at a repair.
This describes the training, not proven results on new tasks.
What we have—and haven’t—tested
Evaluation coverage differs by model. Valid held-out ML-engineering and external MLE-bench evaluations were not completed for 1.0. We plan to require those evaluations before releasing MLE 1.1.
Each model card compares measured general capabilities with its own parent model and documents gains, tradeoffs, and missing evaluations. These results do not establish performance on new ML-engineering tasks.
The fixed 30B tool-call smoke run passed all cases. This is not a general reliability guarantee: validate tool names, arguments, final reports, and proposed changes in your application.
See the full results and limitationsRun it on your own setup
The model files, setup examples, and technical guides are on Hugging Face. You can choose the full weights or smaller GGUF versions. The download pages explain the available formats and their checks.
These are downloadable research models, not a ready-made app or hosted assistant. To let a model work with files or run commands, your application needs to provide the tools, a controlled workspace, and permissions. Review and test any changes it suggests.
8B offers a smaller download and lower memory needs. 30B scored higher than 8B in our coding and tool-use tests. 123B uses Devstral 2 and a different licence. These results do not rank the models on ML-engineering tasks.