THOX on-device assistant for small edge devices: 873M Qwen3.5-0.8B fine-tune on THOX chat and tool-use corpora; Q4_K_M GGUF 529 MB. EXPERIMENTAL: no published benchmark or training log yet. Apache-2.0.

ThoxUSB-Edge

**On-Device Assistant for Small Edge Devices — a THOX on-device model (873M parameters) fine-tuned on THOX chat and agent/tool-use corpora for the THOX device program, published as safetensors plus a Q4_K_M GGUF (529 MB) for small edge device** **Safetensors weights · GGUF: Q4_K_M**

Your AI. Your Data. Your Rules.™

Status: EXPERIMENTAL. No training log, measured benchmark, or on-device validation is published for this build yet; treat outputs accordingly. The card states this in full under Summary, Evaluation, and Limitations.

Summary

ThoxUSB-Edge is a THOX on-device model (873M parameters) fine-tuned on THOX chat and agent/tool-use corpora for the THOX device program, published as safetensors plus a Q4_K_M GGUF (529 MB) for small edge devices. Status: experimental. No training log, measured benchmark, or on-device validation is published for this build yet.

Highlights

ThoxUSB-Edge is a THOX on-device model (873M parameters) fine-tuned on THOX chat and agent/tool-use corpora for the THOX device program, published as safetensors plus a Q4_K_M GGUF (529 MB) for small edge devices.
bash hf download Thox-ai/ThoxUSB-Edge ThoxUSB-Edge.Q4_K_M.gguf --local-dir ./ThoxUSB-Edge llama-cli -m ./ThoxUSB-Edge/ThoxUSB-Edge.Q4_K_M.gguf -p "Hello" -n 128 bash ollama run hf.co/Thox-ai/ThoxUSB-Edge:Q4_K_M Requires a llama.cpp / Ollama build with support for this architecture.

Specifications


Base model	Qwen/Qwen3.5-0.8B
Parameters	873M
Formats	Safetensors weights · GGUF: Q4_K_M · Ollama Modelfile
License	Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; the Apache-2.0 licence and NOTICE carry forward. See the license text for terms.
This repository contains	Full weights and tokenizer in this repo

Files

File	Size	SHA-256
`model.safetensors`	1,504,827,608 B	`de70364e1ac633e52a4b08feec3088312f4a9a2993bccd09a7314ee36a9165c1`
`ThoxUSB-Edge.Q4_K_M.gguf`	529,288,992 B	`28681810070680e5e10fd7faff0e2ac3604e9fa47170a6bcc5187d34edff7d44`
`tokenizer.json`	19,989,325 B	`06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523`
`chat_template.jinja` / `config.json` / `.gitattributes` / `tokenizer_config.json` / `Modelfile` / `generation_config.json`	—	Supporting files (see repo)

Run it

hf download Thox-ai/ThoxUSB-Edge ThoxUSB-Edge.Q4_K_M.gguf --local-dir ./ThoxUSB-Edge
llama-cli -m ./ThoxUSB-Edge/ThoxUSB-Edge.Q4_K_M.gguf -p "Hello" -n 128

ollama run hf.co/Thox-ai/ThoxUSB-Edge:Q4_K_M

Requires a llama.cpp / Ollama build with support for this architecture. Sized for hosts with at least 1 GB RAM.

Platforms

Platform / device	Run path
Hugging Face	Download the builds listed under Files from this repo (see Run it)

Intended use

On-device assistant and tool-routing for the THOX device program.
Out of scope: safety-critical, medical, or legal decisions without a human in the loop; unattended control of physical devices without a confirmation step.

Training data and procedure

THOX fine-tune of Qwen/Qwen3.5-0.8B. The corpus and procedure are described in this card as published at release (see Summary and Evaluation); no training beyond what this card describes is claimed for this repository.

Evaluation

No THOX GATE49 result or benchmark is published for this model. Treat it as experimental.

Limitations

Unvalidated build: behaviour on device has not been measured; verify outputs before relying on them.
Small models make factual mistakes and can produce confident but wrong output.
Behaviour and bias reflect the training data, which is mostly English; quality in other languages is lower.
Quantization trades accuracy for size.

License

Apache-2.0. The THOX fine-tune and additions in this repo are covered under Apache-2.0; the Apache-2.0 licence and NOTICE carry forward. See the license text for terms.

THOX.ai — Your AI. Your Data. Your Rules.™

Provenance

Published by THOX.ai as Thox-ai/ThoxUSB-Edge. Upstream base: Qwen/Qwen3.5-0.8B. This card was conformed to THOX Model Card Standard v1.0 on 2026-10-31 (frontmatter, tags, header, files, and section structure); the technical content is as published at release.

Citation

@misc{thoxai2026thoxusbedge,
      title={ThoxUSB-Edge},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxUSB-Edge}
}