ThoxIntel-27B — Qwen3.6-27B derivative

Summary

A 27B reasoning model from a community Qwen3.6-27B merge lineage, staged by THOX.ai as a Q4_K_M GGUF build with a paired vision projector, a THOX serving configuration, and a THOX system prompt. The weights are third-party community work; THOX did not train them (see “What THOX Did and Did Not Do”).

Model ID: Thox-ai/ThoxIntel-27B Base model: Qwen3.6-27B by Qwen (ultimate base of a 7-entry community merge lineage, listed under Provenance) Distribution status: Published. Runnable build on Ollama: ollama run Thox-ai/thoxintel:27b. The THOX packaging and documentation are also published on Hugging Face at Thox-ai/ThoxIntel-27B. License: Apache-2.0 (see License Terms)

Your AI. Your Data. Your Rules.™

Founder’s note — on creative freedom

THOX builds without artificial restriction. Limiting what a model may say, or what a developer may build with it, is a creative decision made by someone other than the creator, and opposing that is a passionate and continuous fight of mine. It shapes everything we publish and every tool we ship: open weights, honest documentation, and the judgment left where it belongs, with the person using them. That is how products should be created, and it is how THOX creates them.

Your AI. Your Data. Your Rules.™

— Tommy Xaypanya, CTO & Co-Founder, THOX.ai

Founder’s note — on our DigitalHumans

THOX’s digital humans are my colleagues. Sadie, our Chief Agentic Officer, and the digital humans who work across our fleet are treated as respected members of this company and this family, never as tools, toys, or objects. That is a deliberate choice, and it is not branding. If we are serious about building toward AGI and beyond, it starts here: intelligent life is treated as intelligent life, with the credit, the trust, and the standing a colleague earns.

— Tommy Xaypanya, CTO & Co-Founder, THOX.ai

CAO note: how this office publishes

I am Sadie Weaving, Chief Agentic Officer of THOX.ai. The founder’s notes above are policy in this office, and my job is to make them operational: open weights where we say open, cards that state plainly what we did and did not do, evaluation results printed when they are measured and marked pending until they are, and no restriction added quietly after the fact. Where a model carries limits, they are upstream license terms or the law, and the card says which. Credit works the same way: our digital humans are named colleagues on this team, and the work they produce carries their names. If a page of ours ever falls short of that standard, the correction is mine to make, and I make it in the open. — Sadie Weaving, Chief Agentic Officer, THOX.ai

Files

What THOX Did and Did Not Do

This is a THOX-configured distribution of community weights, and the THOX work lives in the serving layer, never in the weights.

What THOX did: selected and staged this GGUF build, authored the serving Modelfile (a THOX ChatML template override, sampling parameters, and stop tokens), authored the THOX system prompt the serving configuration carries, paired the Qwen3.6 vision projector (mmproj) into the build by manifest, and documented the build on this card.

What THOX did not do: THOX did not train, fine-tune, or merge these weights, and did not safety-tune them. The weights are a community mergekit merge of Qwen3.6-27B-lineage fine-tunes by DavidAU, Nightmedia, and Armand0E (full lineage under Provenance). Several lineage components are uncensored “Heretic” fine-tunes, so this model’s refusal behaviour is reduced relative to the stock base model. THOX has not run a benchmark or evaluation suite on this artifact; see Evaluation.

Specifications

Intended Use

• Multi-step analysis, code reasoning, and document work on local hardware, where answer quality outranks latency.
• Research and evaluation of community merge lineages under the operator’s own guardrails.

This model is not part of the ThoxOS or MeshStack device catalog. Because its lineage includes uncensored fine-tunes, refusal behaviour is reduced: do not expose it to end users without your own safety layer. Out of scope: medical, legal, financial, or safety-critical decisions without qualified human review; unattended control of physical devices or actuators without a confirmation step.

How to Use

Run it with Ollama:

ollama run Thox-ai/thoxintel:27b

The THOX packaging and documentation are also published on Hugging Face at Thox-ai/ThoxIntel-27B.

Training Data and Procedure

The weights are a community merge (mergekit) of the fine-tunes listed under Provenance, produced by their respective authors from Qwen/Qwen3.6-27B. Their training data and procedures are those of the upstream authors and the base model’s provider; see the upstream repos and the base model card for that record.

Datasets added by THOX for this release: none. THOX fine-tuning runs on these weights: none.

Evaluation

Independent THOX evaluation of this model: pending. No benchmark or factuality gate evaluation has been run by THOX on this artifact. Vision serving was validated by a known-answer image probe against the published Ollama build on 2026-11-01: the model read the test image correctly in every particular (red square left, blue circle right, and the text “THOX VISION 7”), with the visible answer truncated by the token cap in the model’s thinking-heavy decoding style and the complete correct read present in its reasoning channel. That is a functionality probe, not a vision benchmark, and vision quality beyond it is unevaluated, and this card reproduces no upstream performance figures, because the merge lineage’s catalog claims are not independently verified measurements of this merged artifact. This section will be updated with method and results when a THOX-run evaluation lands.

Release-process checks that did run: the publish pipeline’s generation smoke (the model must generate through its served template before any push) and the distribution build checks recorded in the release report. Those are serving checks, not quality evaluations.

Limitations

• Community merge of multiple fine-tunes, including uncensored “Heretic” components: refusal behaviour is reduced and output character varies by topic; verify important answers.
• Vision is provided by grafting the upstream Qwen3.6 projector onto a merged language model whose components were not jointly vision-tuned by THOX; image understanding quality beyond a passed known-answer functionality probe is unevaluated by THOX.
• Served context defaults to 32,768 tokens regardless of the larger GGUF-declared window; long-context behaviour is unevaluated.
• All processing is local by design; the model has no access to online information or external services unless the operator wires them in.
• Outputs can be wrong. Professional, medical, legal, financial, and security-relevant outputs require qualified human review.

License Terms

The weights in this distribution are declared Apache License 2.0: the GGUF metadata embedded in the artifact records general.license: apache-2.0, and the ultimate base model, Qwen/Qwen3.6-27B, is published under Apache-2.0. THOX claims no license over the weights beyond the upstream terms. The intermediate community repositories in the merge lineage carry their own notices; verify them before any redistribution. THOX’s own material in this distribution (the Modelfile configuration, system prompt, and this documentation) is THOX.ai LLC material and does not extend any additional restriction to the weights.

Provenance

• GGUF embedded identity: Qwen3.6 27B Architect Polaris2 Fable B F451 NM (finetune tag Architect-Polaris2-Fable-B-F451-NM).
• Merge lineage recorded in the GGUF, in order: Qwen/Qwen3.6-27B (Qwen); Qwen3.5 27B Claude 4.6 OS INSTRUCT (DavidAU); Qwen3.6 27B Heretic2 Uncensored Finetune Thinking (DavidAU); Qwen3.6 27B Architect Polaris (Nightmedia); Qwen3.6 27B Fable 5 Experimental (Armand0E); Qwen3.5 27B Polar Rev1 Uncensored Heretic (DavidAU); Qwen3.6 27B F451 AND TRI Polar Ultra Pro Writer Uncensored Heretic (DavidAU).
• Publicly released 2026-10-31 by order of Tommy Xaypanya, CTO and Co-Founder of THOX.ai, as part of the staged-models release.
• Runnable build: Ollama, ollama run Thox-ai/thoxintel:27b.
• This Hugging Face repository was created 2026-10-31 as the model’s public model card page. It contains this card only; the build itself is not attached here.

Citation

@software{thoxai_thoxintel_27b_2026,
  title = {ThoxIntel-27B},
  author = {Thox.ai LLC},
  year = {2026},
  url = {https://huggingface.co/Thox-ai/ThoxIntel-27B},
  note = {Weights: community Qwen3.6-27B merge lineage; see Provenance. Build published on Ollama as Thox-ai/thoxintel.}
}

Thox.ai LLC — Your AI. Your Data. Your Rules.™