ThoxIOS-Micro-0.5B

IOS micro model (Qwen2.5-0.5B, THOX-Configured) — IOS micro model: intent classification and small ThoxMind-style decisions in the THOX iOS configuration

61.97 tok/s long-form (measured 2026-10-31, conditions under Evaluation) · Ollama Modelfile · Live on Ollama

Run it: Ollama — Thox-ai/thox-ios-micro-0.5b · Find your model: THOX Model Factory · Collection: iOS, Browser & Device Knowledge Packs

Your AI. Your Data. Your Rules.™

ThoxIOS-Micro-0.5B is a THOX-configured model: upstream Qwen2.5-0.5B 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.

Highlights

• IOS micro model: intent classification and small ThoxMind-style decisions in the THOX iOS configuration.
• Ollama (published model) bash ollama run Thox-ai/thox-ios-micro-0.5b

Specifications

Base model	Qwen/Qwen2.5-0.5B-Instruct
Parameters	0.5B
Formats	Ollama Modelfile
License	Apache-2.0, inherited from the base model. THOX-owned elements: system profile, knowledge pack, packaging.
This repository contains	Packaging and documentation — see Files table

Files

File	Size	SHA-256 (first 16)	Purpose
Modelfile	1257 B	83eed6585b92355f	Ollama model definition: pinned base + kit system profile
manifest.json	424 B	47b20743d65fc9e8	Release manifest: base pin, profile, knowledge pack version
thox-knowledge-v0.1.jsonl	4652 B	b6a1fb08b1fc4619	THOX Knowledge Pack v0.1 (8 verified public entries, JSONL)

The published Ollama model Thox-ai/thox-ios-micro-0.5b is 0.40 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-micro-0.5b

Build it yourself from this repo

hf download Thox-ai/ThoxIOS-Micro-0.5B --local-dir ./ThoxIOS-Micro-0.5B
cd ./ThoxIOS-Micro-0.5B && ollama create thox-ios-micro-0.5b -f Modelfile && ollama run thox-ios-micro-0.5b

Platforms

Platform / device	Run path
Ollama (laptop / desktop)	ollama run Thox-ai/thox-ios-micro-0.5b
Hugging Face	Download the builds listed under Files from this repo (see Run it)

Summary

IOS micro model: intent classification and small ThoxMind-style decisions in the THOX iOS configuration. Configuration-derived: THOX did not train these weights. Kit delivery target is a mobile GGUF (Q4_K_M); the Ollama listing serves that same Q4_K_M build of the upstream model. Not qualified on device hardware.

Intended use

Local inference through Ollama's local endpoint for the role above, on hardware that fits a 0.5B 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/Qwen2.5-0.5B-Instruct via Ollama tag qwen2.5:0.5b, pinned at build time to manifest digest a8b0c51577010a279d933d14c2a8ab4b268079d44c5c8830c0a93900f1827c67. 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 2026-10-31 on a CPU-only x86_64 host (4 vCPU / 8 GB class), at 8,192-token context, against the published configuration:

• Long-form generation: 61.97 tokens/sec (1,024-token bench).
• Short answers: 55.9–71.2 tokens/sec across the smoke set.
• Memory footprint while loaded: 0.59 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): 5/8 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 0.5B 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. Kit delivery target is a mobile GGUF (Q4_K_M); the Ollama listing serves that same Q4_K_M build of the upstream model. Not qualified on device hardware.

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, 2026-10-31 (founder order: every kit model published). Kit: THOX iOS Model Kit. Base pin: qwen2.5:0.5b @ a8b0c51577010a279d933d14c2a8ab4b268079d44c5c8830c0a93900f1827c67. Published model digest: 3c97c00df65e62fb2eea1b3d765a2bca977db6ccb069be2bdb62bbf5cd70201e.

Citation

@misc{thoxai2026thoxiosmicro05b,
      title={ThoxIOS-Micro-0.5B},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxIOS-Micro-0.5B}
}