Magistral-Small-2509-Vision

Model - Magistral-Small-2509-Vision (24B Parameters)<br />

Description: <br /> This model was re-configured using MistralAI's "Mistral3ForConditionalGeneration" processor, configuration and then saved as a Vision Multimodal version of Magistral-Small-2509 with working Vision functioanlity re-enabled. The Chat-template and System-prompt files are also reworked and are custom compared to the originals supplied by MistralAI. No modifications, edits, or additional configuration is required to use this model with Huggingface SafeTensors, Pipeline, or vLLM (It simply requires the standard Mistral-Small-3.X/Magistral setup and configuration)! Both Vision and Text work. (^.^)

IMPORTANT NOTICE as of (GMT-8) 02:24 November 17th 2025: <br /> Be aware that the chat-template AND the system-prompt files are different from what MistralAI supplied. You can absolutey use the standard template and prompt, but I have supplied what I personally used and found to be very good in performance and usability. The standard files released by MistralAI will be uploaded within the next few days but, this model is 100% usable with what is currently provided in this customized release. <br /><br /> Happy LLM Inferrencing,<br /> -- Jon Z (EnlistedGhost)

---

Model Updates (as of: November 17th, 2025)

Recently finished updates:

• Uploaded: All Safetensor, configuration, and required files for Model use.
• Created: ModelCard <br /> (this page)

Currently in-progress updates:

• Upload: standard MistralAI template and system prompt as alternate options to current custom versions.
• Update: ModelCard <br /> (This modelcard was created quickly to provide basic information while a proper one is being completed)

---

How to run this Model <br />

You can run this model by using Huggingface pipeline or safetensors systems. Detailed instructions will be made available within the next few days.

---

Intended Use

Same as original:

• [MistralAI]

Out-of-Scope Use

Same as original:

• [MistralAI]

Bias, Risks, and Limitations

Same as original:

• [MistralAI]

Training Details

Training sets and data are from:

• [MistralAI] <br />(This is a direct off-shoot/decendant of the above mentioned model)

Evaluation

• This model has NOT been evaluated in any form, scope or method of use.
• !!! USE AT YOUR OWN RISK !!!
• !!! NO WARRANTY IS PROVIDED OF ANY KIND !!!

---

Citation (Original Paper)

[MistalAI Magistral-Small-2509 Original Paper]

Detailed Release Information

• Originally Developed by: [mistralai]
• Modified with Vision re-Enabled by: [EnlistedGhost]
• Model type & format: [SafeTensors]
• License type: [Apache-2.0]

Attributions (Credits)

A big thank-you is extended to the below credited sources!<br /> This release is only possible thanks to the below mentioned community-member(s)/organization(s)

• [MistralAI]

Model Card Authors and Contact

[EnlistedGhost]