Add Ministral 3 instruct support#3415
Open
dhandhalyabhavik wants to merge 4 commits into
Open
Conversation
- Add ministral-3.ipynb notebook for Ministral-3-3B-Instruct-2512 VLM - Uses OVModelForVisualCausalLM from optimum-intel PR openvinotoolkit#1659 - INT4 weight compression by default - Includes gradio_helper.py for interactive chatbot demo - Exports from mistralai/Ministral-3-3B-Instruct-2512-BF16 model
…demo image - Add model dropdown for 3B and 8B variants (Ministral-3-3B/8B-Instruct-2512-BF16) - Remove broken device=GPU cell that crashed the kernel - Replace ipywidgets device_widget with plain Python device selection - Use qwen3-vl demo image (beach scene) for image inference - Tested INT4 on both CPU and GPU for both model sizes
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Contributor
|
This PR will be closed in a week because of 2 weeks of no activity. |
Author
|
@aleksandr-mokrov please review this PR. |
Contributor
|
This PR will be closed in a week because of 2 weeks of no activity. |
Author
|
@aleksandr-mokrov please review this PR. |
Contributor
|
This PR will be closed in a week because of 2 weeks of no activity. |
Author
|
@aleksandr-mokrov please review this PR. |
| @@ -0,0 +1,386 @@ | |||
| { | |||
Collaborator
There was a problem hiding this comment.
Add disclaimer
⚠️ **EXPERIMENTAL NOTEBOOK** This notebook demonstrates a model that has not been fully validated with OpenVINO and is using a custom branch of optimum-intel. It may be fully supported and validated in the future.
Reply via ReviewNB
| @@ -0,0 +1,386 @@ | |||
| { | |||
Collaborator
There was a problem hiding this comment.
Line #4. device = "GPU" if "GPU" in available else "CPU"
Please replace it with
from notebook_utils import device_widget device = device_widget(default="AUTO", exclude=["NPU"])
Reply via ReviewNB
aleksandr-mokrov
requested changes
Jul 10, 2026
aleksandr-mokrov
left a comment
aleksandr-mokrov
left a comment
Collaborator
There was a problem hiding this comment.
Fix CI issues and the comments please
|
|
||
| - Install requirements | ||
| - Convert and Optimize model | ||
| - Prepare OpenVINO GenAI Inference Pipeline |
Collaborator
There was a problem hiding this comment.
It doesn't use genai
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR adds a notebook for running Ministral-3 (Mistral AI's multimodal model) with OpenVINO, supporting both 3B and 8B model variants.
Model selection dropdown for choosing between Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16
Image-based inference using OVModelForVisualCausalLM from optimum-intel (PR (huggingface/optimum-intel#1659))
Tested configurations
Tested and verified Ministral-3-3B-Instruct-2512-BF16 and Ministral-3-8B-Instruct-2512-BF16 both models,
Verified its working for CPU, dGPU, iGPU.
Note
openvino_genai.VLMPipeline does not support mistral3 model type yet, so this notebook uses the optimum-intel OVModelForVisualCausalLM pipeline for inference.
AI Disclaimer
Used AI to write notebook from above PR, performed end to end manual testing, verified both model on all listed devices.