Thox-Pro-24B — Agentic Coding Configuration (Devstral Small 2 24B, THOX-Configured)

Your AI. Your Data. Your Rules.™

Thox-Pro-24B is a THOX configuration and distribution of Mistral AI’s Devstral Small 2 24B, an agentic coding model, published for local software-engineering work. The weight layer in this model’s Ollama manifest is byte-identical to the upstream provider’s Ollama weight layer (devstral-small-2:24b). 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 presented the base model’s published SWE-Bench Verified and Terminal Bench figures as this release’s own achievements, claimed ITAR compliance, and quoted per-scenario dollar gains. The benchmark figures are Mistral’s for the base model and are not THOX measurements (they are attributed as upstream figures in Evaluation below); the compliance claim was unsubstantiated; and the dollar figures have been removed. No benchmark, throughput, latency, concurrency, uptime, cost-saving, or compliance figure is claimed by THOX 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; THOX cannot grant MIT terms over Mistral’s weights, and that statement has been removed (see License).

Run it

Ollama (published model)

ollama pull Thox-ai/thox-pro-24b
ollama run Thox-ai/thox-pro-24b

Summary

A THOX configuration and distribution of Devstral Small 2 24B for local software-engineering work: agentic coding workflows with function calling and tool use, as supported by the base model and your tool integration. Configuration-derived: THOX did not train these weights. All code stays on infrastructure you control when run locally.

The published Ollama model Thox-ai/thox-pro-24b is 15 GB.

Intended use

Local inference through Ollama for software-engineering work, on hardware that fits a 24B Q4-class model:

• Full-stack, mobile, and DevOps development assistance on private codebases
• Multi-file refactoring and automated test generation with human review
• Repository-scale analysis within the served context above

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/Devstral-Small-2-24B-Instruct-2512 by Mistral AI, via Ollama tag devstral-small-2:24b. 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. Upstream figures, reported by Mistral for the base model and reproduced from the original catalog (not THOX measurements): SWE-Bench Verified 65.8%, Terminal Bench 32.0%. 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 24 GB RAM, 20 GB storage, NVIDIA Jetson Orin AGX class GPU (16GB VRAM), 8+ CPU cores. Recommended 64 GB RAM, 50 GB NVMe SSD, Jetson Orin AGX class GPU (32GB 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 code-focused tasks, not general chat. Agentic features require proper tool integration and permission scoping. AI-generated code requires human review and full test suites before production deployment.
• All processing is local by design; the model has no access to online information or external services unless the operator wires them in.

License

This model’s Ollama manifest contains no license layer. The weights are the upstream devstral-small-2:24b distribution of Mistral AI’s Devstral Small 2 24B; Mistral specifies the Apache License 2.0 for Devstral Small 2 on its official model card, and those upstream terms govern the weights. Consult the official Mistral model page for the current license text before use or redistribution. Earlier versions of this page stated MIT; THOX cannot grant MIT terms over Mistral’s weights, and that statement has been removed. THOX claims no license over the weights.

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/Devstral-Small-2-24B-Instruct-2512, Ollama tag devstral-small-2:24b; 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-24b. Correction history: base-model benchmark figures re-attributed to Mistral as upstream figures, the ITAR compliance claim and per-scenario dollar gains removed, and the MIT license statement removed, as recorded in the correction notice above. Enterprise: enterprise@thox.ai.