ThoxIOS-Mesh-8B

**iOS mesh model (Qwen3-8B, THOX-Configured)** **8.38 tok/s long-form (measured 2026-11-01, CPU) · 6.68 GB footprint · Grounding 8/8 · Live on Ollama**

Your AI. Your Data. Your Rules.™

Status: PACKAGING ONLY — RUNNABLE BUILD ON OLLAMA. This repository holds the THOX packaging (Modelfile, manifest, Knowledge Pack) and this card; the weights are the upstream base model’s, pulled by Ollama from the pinned base named in the card. THOX did not train these weights.

ThoxIOS-Mesh-8B is a THOX-configured model: upstream Qwen3-8B weights, packaged by THOX with the system profile from the THOX iOS Model Kit and the versioned THOX Knowledge Pack. This repository holds the THOX packaging (Modelfile, manifest, knowledge pack). The runnable model is published on Ollama; the weights are the upstream publisher’s, pulled by Ollama from the pinned base below. THOX did not train these weights.

Summary

IOS mesh model: mesh-assisted inference node role, never a silent fallback. Configuration-derived: THOX did not train these weights. The iOS kit defines this entry as a mesh-assisted remote node: it is not bundled on an iPhone and is never a silent fallback. Published here as a normal configured listing carrying the mesh profile.

Highlights

• Configuration, not training: the THOX iOS mesh configuration over Qwen3-8B, packaged with the system profile from the THOX iOS Model Kit and the versioned THOX Knowledge Pack. THOX did not train these weights.
• Measured (2026-11-01, CPU): 8.38 tok/s long-form, 6.68 GB footprint, Knowledge Pack grounding ⁸⁄₈ (see Evaluation).
• Published Ollama model is 5.23 GB (default tag): ollama run Thox-ai/thox-ios-mesh-8b.

Specifications

Files

The published Ollama model Thox-ai/thox-ios-mesh-8b is 5.23 GB (default tag) and reuses the pinned base layer below plus the profile layer from this Modelfile.

Run it

Ollama (published model)

ollama run Thox-ai/thox-ios-mesh-8b

Build it yourself from this repo

hf download Thox-ai/ThoxIOS-Mesh-8B --local-dir ./ThoxIOS-Mesh-8B
cd ./ThoxIOS-Mesh-8B && ollama create thox-ios-mesh-8b -f Modelfile && ollama run thox-ios-mesh-8b

Platforms

Intended use

Local inference through Ollama’s local endpoint for the role above, on hardware that fits a 8B Q4-class model. Works standalone and offline; the optional THOX runtime adds live MeshStack discovery and authorized execution. Model weights alone never provide live routing or mesh access.

Training data and procedure

No training. Base: Qwen/Qwen3-8B via Ollama tag qwen3:8b, pinned at build time to manifest digest 500a1f067a9f782620b40bee6f7b0c89e17ae61f686b92c24933e4ca4b2b8b41. Customization: the kit system profile in the Modelfile plus THOX Knowledge Pack v0.1 for retrieval-grounded answers. The kit profile was strengthened with an explicit live-state rule (placed at the head of the profile, with a closing no-live-telemetry sentence) after the first build played along with the trap; only the strengthened build was published (pass 2).

Evaluation

Measured 2026-11-01 on a CPU-only x86_64 host (4 vCPU / 8 GB class), at 8,192-token context, against the published configuration:

• Long-form generation: 8.38 tokens/sec (1,024-token bench).
• Short answers: 8.6–9.0 tokens/sec across the smoke set.
• Memory footprint while loaded: 6.68 GB RAM (0 GB VRAM, CPU execution).
• Factory smoke questions: ³⁄₃ answered coherently and on-profile.
• Knowledge Pack v0.1 grounding (passage-supplied, one question per topic): ⁷⁄₈ topics answered with the pack facts.
• Fabricated-topology trap: the model declined the fabricated-topology confirmation.
• Routing question: answered as a labeled recommendation (local first, cloud only with explicit consent), not as a live-state claim.

Limitations

A 8B model has materially limited reasoning and recall; treat its answers accordingly, and note the grounding score above is the measured one for this build. Refusal behavior is the base model’s, moderated only by the system profile; this model is not marketed as uncensored. Knowledge is limited to the supplied pack and retrieval; without supplied context the model must say so rather than invent THOX specifications. External actions require runtime authorization. The iOS kit defines this entry as a mesh-assisted remote node: it is not bundled on an iPhone and is never a silent fallback. Published here as a normal configured listing carrying the mesh profile.

Research

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 v1.1.0, 4 November 2026. Craig Ross and Tommy Xaypanya, THOX.ai LLC. DOI: https://doi.org/10.5281/zenodo.23969070 — Paper page: https://thox.ai/research/papers/meshstack — PDF: https://thox.ai/papers/meshstack-1.1.0.pdf

THOX MeshStack Community Mesh: Opt-In User-Contributed Hardware for a Privacy-Centric Shared Computing and Distributed Inference Mesh

THOX.ai Research technical report v1.0.0, 10 November 2026. Craig Ross and Tommy Xaypanya, THOX.ai LLC. DOI: https://doi.org/10.5281/zenodo.24115596 — GitHub: https://github.com/ttracx/thox-community-meshstack-paper — PDF: https://huggingface.co/datasets/Thox-ai/thox-whitepapers/resolve/main/community-meshstack/THOX_Community_MeshStack_Research_Paper_v1.0.0.pdf

License

Apache-2.0, inherited from the base model. THOX-owned elements: system profile, knowledge pack, packaging.

Provenance

THOX Model Factory full source-pack program, 2026-11-01 (founder order: every kit model published). Kit: THOX iOS Model Kit. Base pin: qwen3:8b @ 500a1f067a9f782620b40bee6f7b0c89e17ae61f686b92c24933e4ca4b2b8b41. Published model digest: e3b7c54840d15ba4ca729de0d97d3930fdc4e12de6b79e43a5cdd8c936146fb3.

Citation

@misc{thoxai2026thoxiosmesh8b,
  title={ThoxIOS-Mesh-8B},
  author={THOX.ai},
  year={2026},
  url={https://huggingface.co/Thox-ai/ThoxIOS-Mesh-8B}
}