Thox-Pro-32B — Largest Single-Device Pro Configuration (Qwen3 32B, THOX-Configured)

Your AI. Your Data. Your Rules.™

Thox-Pro-32B is a THOX configuration and distribution of Alibaba Cloud’s Qwen3 32B, the largest single-device model in the Pro family, published for local professional work. The weight layer in this model’s Ollama manifest is byte-identical to the upstream provider’s Ollama weight layer (qwen3:32b). 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 described the build as full precision (FP16/BF16); the served build is Q4_K_M per the manifest config. It also presented HIPAA, SOC 2, FERPA, FISMA, and ITAR compliance as product properties and quoted per-scenario savings figures; THOX claims no certification for this model, and those have been removed. 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 a blanket MIT license for the model; that was incorrect for the weights (see License).

Run it

Ollama (published model)

ollama pull Thox-ai/thox-pro-32b
ollama run Thox-ai/thox-pro-32b

Summary

A THOX configuration and distribution of Qwen3 32B for local professional work on a single device: complex document analysis, multi-step professional workflows, and cross-domain synthesis, within the base model’s abilities, with all inference local. Configuration-derived: THOX did not train these weights.

The published Ollama model Thox-ai/thox-pro-32b is 20 GB.

Intended use

Local inference through Ollama for professional work, on hardware that fits a 32B Q4-class model:

• Strategic and executive analysis on isolated networks
• Clinical, legal, financial, and research document work under qualified human oversight
• Regulated-industry evaluation of local AI, subject to the operator’s own compliance obligations

All inference local, with complete control over sensitive material. 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: Qwen/Qwen3-32B by Alibaba Cloud, via Ollama tag qwen3:32b. 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 original card reports qualitative domain performance without published benchmark scores, and 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 32 GB RAM, 25 GB storage, NVIDIA Jetson Orin AGX class GPU (32GB VRAM). Recommended 64 GB RAM, 100 GB NVMe SSD, Jetson Orin AGX class GPU (64GB VRAM).

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.
• Best suited to professional and executive use, not casual conversation. Strategic, medical, legal, and financial outputs require qualified human judgment and review.
• 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 qwen3:32b distribution). The manifest also carries an MIT license layer (Copyright 2025-2026 Thox.ai LLC) covering THOX’s own packaging material only. Earlier versions of this page stated a blanket MIT license for the model; that was incorrect for the weights. 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: Qwen/Qwen3-32B, Ollama tag qwen3:32b; 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-32b. Correction history: the full-precision (FP16/BF16) description corrected to Q4_K_M, HIPAA/SOC 2/FERPA/FISMA/ITAR product-property presentation and savings figures removed (no certification claimed), and the blanket MIT license statement corrected, as recorded in the correction notice above. Enterprise: enterprise@thox.ai.