Thox-Pro-14B — Advanced Vision Configuration for Professional Work (Ministral 3 14B, THOX-Configured)

Your AI. Your Data. Your Rules.™

Thox-Pro-14B is a THOX configuration and distribution of Mistral AI’s Ministral 3 14B: a multimodal (text and image) model for professional document and image work, running locally on a single device. The weight layer in this model’s Ollama manifest is byte-identical to the upstream provider’s Ollama weight layer (ministral-3:14b). THOX’s work in this release is the MeshStack clustering layer these configurations were made for, configuration (runtime parameters and, where present, a system prompt), packaging, and distribution. THOX did not train these weights.

Correction notice. This page previously published approximate benchmark figures (MMMU, ChartQA, DocVQA, MathVista) and dollar savings per deployment scenario; none were THOX-run measurements, and they have been removed. It also presented HIPAA and SOC 2 compliance as product properties; THOX claims no certification for this model. No benchmark, throughput, latency, concurrency, uptime, cost-saving, or compliance figure is claimed for this release; figures of that kind that appeared on earlier versions of this page were inherited catalog copy and have been removed pending THOX-run evaluation on THOX deployments. Earlier versions also stated the license as MIT; that was incorrect (see License).

Run it

Ollama (published model)

ollama pull Thox-ai/thox-pro-14b
ollama run Thox-ai/thox-pro-14b

Summary

A THOX configuration and distribution of Ministral 3 14B for professional document and image work on a single device: text and image input for documents, charts, diagrams, and figures, with all inference local (image data is processed on your device, not uploaded). Configuration-derived: THOX did not train these weights.

The published Ollama model Thox-ai/thox-pro-14b is 9.1 GB.

Intended use

Local inference through Ollama for professional work, on hardware that fits a 14B Q4-class model:

• Document and exhibit review with visual content, under professional oversight
• Chart, dashboard, and scientific-figure interpretation

Downloading this model gives you local inference in Ollama. Distributed orchestration across devices is provided by MeshStack; a model download alone does not create a cluster or pool memory across devices.

Training data and procedure

No training by THOX. Base: mistralai/Ministral-3-14B-Instruct-2512 by Mistral AI, via Ollama tag ministral-3:14b. The original THOX release materials for this model claim no separate THOX fine-tuning run, training dataset, or training procedure, and none is claimed here. Base-model training data and procedure are those of the base model’s provider; see the base model card for that record. Datasets added by THOX for this release: none.

Evaluation

No THOX-run evaluation has been published for this model. The benchmark figures on earlier versions of this page were not THOX-run measurements and have been removed (see the correction notice); THOX claims no figure for this release. This section will be updated with method and results when a THOX-run evaluation lands.

Hardware Reference (from the original card)

Reference configuration from the original card: minimum 16 GB RAM, 12 GB storage, NVIDIA Jetson Orin NX class GPU (8GB VRAM). Recommended 32 GB RAM, 20 GB SSD, Jetson Orin AGX class GPU.

Limitations

• Outputs can be wrong. Professional, medical, legal, financial, and security-relevant outputs require qualified human review.
• Local deployment only in this distribution; behavior and speed depend entirely on the operator’s hardware and configuration.
• The operator is responsible for meeting any regulatory obligations that apply to their deployment.
• Maximum 5 images per request; not optimized for video (frame-by-frame only). Specialized imaging formats require proper format conversion.
• All processing is local by design; the model has no access to online information or external services unless the operator wires them in.

License

The model weights are distributed under the Apache License 2.0 (license layer in this model’s Ollama manifest, from the upstream ministral-3:14b distribution). Earlier versions of this page stated MIT; that was incorrect. THOX claims no license over the weights beyond the upstream terms.

MagStack and MeshStack technology is proprietary to Thox.ai LLC. Publication of this model does not license THOX mesh technology, patents, or trademarks beyond identifying the model.

Provenance

THOX Pro family, the single-device professional line released alongside the MeshStack Cluster family. First listed on Ollama under Thox-ai in 2025 and held private; publicly released 2026-10-31 by order of Tommy Xaypanya, CTO and Co-Founder of THOX.ai, as part of the MeshStack model family release. Upstream: mistralai/Ministral-3-14B-Instruct-2512, Ollama tag ministral-3:14b; the weight layer is byte-identical to the upstream provider’s Ollama weight layer (SHA-256 verified in the 2026-10-31 release review). Model card: https://huggingface.co/Thox-ai/thox-pro-14b. Correction history: unmeasured benchmark figures and dollar-savings claims removed, HIPAA/SOC 2 product-property presentation removed (no certification claimed), and the license statement corrected from MIT to Apache-2.0, as recorded in the correction notice above. Enterprise: enterprise@thox.ai.