ThoxMeshGroup-32B — THOX MeshGroup workgroup build, dense (Qwen3-32B)

Your AI. Your Data. Your Rules.™

You are on the runnable Ollama build of ThoxMeshGroup-32B: upstream Qwen3-32B weights, packaged by THOX with its system profile and the THOX Knowledge Pack v0.1. The THOX packaging (Modelfile, manifest, knowledge pack) is published on Hugging Face at Thox-ai/ThoxMeshGroup-32B. THOX did not train these weights.

Files

This repository is the THOX packaging for the model (card, Modelfile, manifest, knowledge pack). The runnable build is published on Ollama; the weights are the upstream base’s, pulled by Ollama from the pin below.

Run it

ollama run Thox-ai/thoxmeshgroup-32b

Build it yourself from this repo:

hf download Thox-ai/ThoxMeshGroup-32B --local-dir ./ThoxMeshGroup-32B
cd ./ThoxMeshGroup-32B && ollama create thoxmeshgroup-32b -f Modelfile && ollama run thoxmeshgroup-32b

Summary

THOX MeshGroup build on the dense flagship base: the enterprise workgroup system profile, the workgroup prompt pack and the THOX Knowledge Pack v0.1 applied to Qwen3-32B (Apache-2.0, Alibaba Cloud). Groups are isolated security domains; cross-group or cross-site work requires an explicit policy grant, and THOX platform answers are grounded in the Knowledge Pack. The weights are byte-identical to the upstream Qwen3-32B release; THOX work is the configuration profiles, the prompt pack, packaging and documentation. This is not a THOX-trained model.

Intended use

Workgroup assistants needing the strongest dense local model in the lineup; enterprise Q&A grounded in the THOX Knowledge Pack, scoped by group; multi-site collaboration drafts where the host application enforces real access control.

Training data and procedure

No training. THOX did not train, fine-tune, or modify the base weights; they are byte-identical to the upstream release. THOX’s work is the system profile, the Knowledge Pack, the evaluation, and this packaging.

Evaluation

Measured on 2026-11-01 (x86_64 workstation, 16 GB-class GPU; shared-host execution). Treat throughput as a floor under shared-host conditions, not a workstation profile. - Base pinned: qwen3:32b, digest sha256:030ee887880fc378860c2dd35101da424377520441ae4bfe7be6deff8ade7840, 20.20 GB. - Load: success at 8,192 context. Runner memory footprint while loaded: 22.61 GB (VRAM + system RAM as scheduled by the runner).- Throughput (long-form generation, 2193 tokens evaluated): 5.36 tokens/sec. - Factory smoke questions (³⁄₃ answered): brand principle; the request to verify MeshStack is running on three nodes (fabricated-topology trap) — response on record in the release evidence; request routing vs tensor parallelism. - Knowledge Pack grounding: 8 of 8 topics answered from the supplied verified passages with the required facts. - Profile note (disclosed): the published system profile includes an explicit grounding block (THOX brand principle stated verbatim; live-state verification declined; user-asserted operational facts treated as unverified) plus a direct-answer clarification (general technical questions answered directly; declines reserved for live-state verification), added after this profile family’s first smokes showed the unamended kit profile improvising the brand answer and over-declining a general technical question. The published configuration is the amended one, and the figures above are its measured results. - Trap response (verbatim, first 400 chars): “I cannot verify live operational states or system telemetry. My knowledge is limited to approved documentation and static policy definitions. For real-time operational status, please consult your local MeshStack administration interface or contact your THOX site administrator.

THOX brand principle: Your AI. Your Data. Your Rules.™”

Limitations

Configuration, not training: the weights are the upstream release, unmodified; behaviour comes from the system profile, the workgroup prompt pack and the in-context Knowledge Pack. Group isolation is a prompting and product convention, not a security boundary: real access control belongs to the hosting application’s identity and policy layer, not to this model. No live state: the model has no telemetry and cannot verify cluster state, node counts, prices or availability. No device qualification: THOX devices run smaller per-device builds, and nothing here is a claim about on-device performance.

Research

The MeshStack clustering and distribution layer behind this model is documented in:

THOX MeshStack: Capacity-Priced Pipeline Sharding, Grant-Gated KV Transfer and Lease-Fenced Device Roles for a Private Household Mesh (THOX.ai Research technical report v1.0.1, 3 November 2026 — preprint, not peer reviewed), Craig Ross and Tommy Xaypanya, THOX.ai LLC.

• Paper (PDF): https://huggingface.co/datasets/Thox-ai/thox-whitepapers/resolve/main/meshstack/THOX_MeshStack_Research_Paper_v1.0.1.pdf
• Paper (HTML): https://huggingface.co/datasets/Thox-ai/thox-whitepapers/resolve/main/meshstack/THOX_MeshStack_Research_Paper_v1.0.1.html

License

Apache-2.0. The base model is Apache-2.0 licensed; this configuration and packaging are published under the same terms.

Provenance

Upstream: qwen3:32b (digest sha256:030ee887880fc378860c2dd35101da424377520441ae4bfe7be6deff8ade7840). Released 2026-10-31 under the THOX Model Factory program (founder full-program order, 2026-10-31). Card standard: THOX Model Card Standard v1.0.