Thox-Cluster-Code — Software Engineering Configuration (Qwen2.5-Coder 32B, THOX-Configured)

Your AI. Your Data. Your Rules.™

Thox-Cluster-Code is a THOX configuration and distribution of Alibaba Cloud’s Qwen2.5-Coder 32B, published for local software-engineering work and MeshStack deployments. The weight layer in this model’s Ollama manifest is byte-identical to the upstream provider’s Ollama weight layer (qwen2.5-coder: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 model as “GPT-4o competitive” and quoted an Aider score and team ROI figures; those were inherited catalog claims with no THOX-run evaluation behind them and 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 of this page also stated the license as MIT; that was incorrect (see License).

The published Ollama model Thox-ai/thox-cluster-code is 20 GB and reuses the upstream weight layer plus the THOX configuration layers from this model’s Ollama manifest.

Run it

Ollama (published model)

ollama pull Thox-ai/thox-cluster-code
ollama run Thox-ai/thox-cluster-code

Summary

A THOX configuration and distribution of Qwen2.5-Coder 32B for local software-engineering work and MeshStack deployments. Configuration-derived: THOX did not train these weights. Qwen2.5-Coder is Alibaba’s code-specialized model family; per Alibaba’s model record it covers 92 programming languages.

Intended use

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

• Software teams analysing repositories and reviewing code locally
• Startups and DevOps teams prototyping and working with infrastructure-as-code
• QA and test-automation assistance on private codebases

Code generation, repository analysis, code review, test generation, debugging, and refactoring assistance, within the base model’s abilities. Local inference keeps proprietary code on infrastructure you control. 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/Qwen2.5-Coder-32B-Instruct by Alibaba Cloud, via Ollama tag qwen2.5-coder: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. THOX claims no benchmark, throughput, latency, or concurrency figure for this release. The only capability figure stated is upstream: 92 programming languages, per Alibaba’s model record for Qwen2.5-Coder. 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, per device: minimum 32 GB RAM, 30 GB storage, NVIDIA Jetson Orin AGX class GPU (32GB VRAM), 10 Gbps network for clustered use. Recommended 64 GB RAM, 50 GB NVMe SSD.

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.
• Specialized for software engineering; not a general-purpose chat model. Generated code requires human review before production use.
• 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 qwen2.5-coder:32b distribution; the layer’s appendix carries Alibaba Cloud’s copyright notice). 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 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/Qwen2.5-Coder-32B-Instruct, Ollama tag qwen2.5-coder: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-cluster-code. Correction history: inherited catalog claims (GPT-4o comparison, Aider score, ROI and concurrency figures) removed and the license statement corrected from MIT to Apache-2.0, as recorded in the correction notice above. Enterprise: enterprise@thox.ai.