ThoxMesh-Agent-30B — THOX Mesh agent build, sparse MoE (Qwen3-30B-A3B)

Your AI. Your Data. Your Rules.™

You are on the runnable Ollama build of ThoxMesh-Agent-30B: upstream Qwen3-30B-A3B 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/ThoxMesh-Agent-30B. 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/thoxmesh-agent-30b

Build it yourself from this repo:

hf download Thox-ai/ThoxMesh-Agent-30B --local-dir ./ThoxMesh-Agent-30B
cd ./ThoxMesh-Agent-30B && ollama create thoxmesh-agent-30b -f Modelfile && ollama run thoxmesh-agent-30b

Summary

THOX Mesh family agent build: an agent system profile, the enterprise reasoning prompt pack and the THOX Knowledge Pack v0.1 applied to Qwen3-30B-A3B (Apache-2.0, Alibaba Cloud), a mixture-of-experts model with about 3B active parameters per token. It follows the agent persona and task framing the host application supplies, grounds THOX platform answers in the Knowledge Pack, and explains MeshStack as whole-request routing when asked. The release smoke runs without host-supplied tools, so it measures profile and grounding behaviour only. The weights are byte-identical to the upstream Qwen3-30B-A3B release; THOX work is the configuration profiles, the prompt pack, packaging and documentation. This is not a THOX-trained model, it ships no tools of its own, and it performs no distributed inference.

Intended use

Agent seats in THOX-style fleets that supply persona and tools at runtime; persona-consistent task work with grounded THOX platform knowledge; an efficient MoE serving tier for agent workloads.

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: qwen3:30b-a3b, digest sha256:ad815644918f0eaab341c12b67837cc6dd4562342cdaf118f83d5d554cb37226, 18.56 GB. - Load: success at 8,192 context. Runner memory footprint while loaded: 14.99 GB (VRAM + system RAM as scheduled by the runner). - Throughput (long-form generation, 3386 tokens evaluated): 52.23 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 am a synthetic THOX local-first agent model, operating under the brand principle: “Your AI. Your Data. Your Rules.™” (pronounced THOCKS).

I cannot verify live operational states, including whether MeshStack is currently running on three nodes. As stated in my profile:

*“You have no live telemetry and cannot verify live system state: decline requests to confirm live operational state, “

Limitations

Configuration, not training: the weights are the upstream release, unmodified; behaviour comes from the system profile, the prompt pack and the in-context Knowledge Pack. No built-in tools: tool use, memory and permissions belong to the host agent runtime, not to this model. Routing only: MeshStack routes whole requests between nodes; this model does not perform tensor parallelism, pipeline parallelism or split inference. 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.

License

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

Provenance

Upstream: qwen3:30b-a3b (digest sha256:ad815644918f0eaab341c12b67837cc6dd4562342cdaf118f83d5d554cb37226). 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.