The THOX four-device family

ThoxClip-Agent-4B

ThoxClip (6 GB) target agent configuration (Qwen3-4B, THOX-Configured)

15.28 tok/s long-form (measured 2026-11-01, CPU) · 3.89 GB footprint · Grounding 8/8 · Live on Ollama

License Params Base Access

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.

ThoxClip-Agent-4B is a THOX-configured model: upstream Qwen3-4B weights, packaged by THOX with the system profile from the THOX Device Model Catalog and Build 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

ThoxClip (6 GB) target agent configuration. Configuration-derived: THOX did not train these weights. ThoxClip (6 GB) target configuration. Not qualified on device hardware.

Highlights

  • Configuration, not training: the ThoxClip (6 GB) target agent configuration over Qwen3-4B. THOX did not train these weights.
  • Measured (2026-11-01, CPU): 15.28 tok/s long-form, 3.89 GB footprint, Knowledge Pack grounding 8/8 (see Evaluation).
  • Published Ollama model is 2.50 GB (default tag): ollama run Thox-ai/thoxclip-agent-4b.

Specifications

Base model Qwen/Qwen3-4B
Parameters 4B
Formats Ollama Modelfile
License Apache-2.0, inherited from the base model; retain the Apache notice. THOX-owned elements: system profile, knowledge pack, packaging.
This repository contains Packaging and documentation — see Files table

Files

File Size SHA-256 Purpose
Modelfile 447 B 432219faa43d5c5e7379c9271822d8b180c5787e11e3779267d299f14a248da3 Ollama model definition: pinned base + kit system profile
manifest.json 356 B fa8a649ca0c74db48d69df90ffd6f5ef9e708b747b00b80d8b1314637be8c0f0 Release manifest: base pin, profile, knowledge pack version
thox-knowledge-v0.1.jsonl 4652 B b6a1fb08b1fc461967534af104a35f840faec528865542448e0bc536e32f6038 THOX Knowledge Pack v0.1 (8 verified public entries, JSONL)

The published Ollama model Thox-ai/thoxclip-agent-4b is 2.50 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/thoxclip-agent-4b

Build it yourself from this repo

hf download Thox-ai/ThoxClip-Agent-4B --local-dir ./ThoxClip-Agent-4B
cd ./ThoxClip-Agent-4B && ollama create thoxclip-agent-4b -f Modelfile && ollama run thoxclip-agent-4b

Platforms

Platform / device Run path
Ollama (laptop / desktop) ollama run Thox-ai/thoxclip-agent-4b
Hugging Face Download the packaging listed under Files from this repo (see Run it)

Intended use

Local inference through Ollama's local endpoint for the role above, on hardware that fits a 4B 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/Qwen3-4B via Ollama tag qwen3:4b, pinned at build time to manifest digest 359d7dd4bcdab3d86b87d73ac27966f4dbb9f5efdfcc75d34a8764a09474fae7. Customization: the kit system profile in the Modelfile plus THOX Knowledge Pack v0.1 for retrieval-grounded answers.

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: 15.28 tokens/sec (1,024-token bench).
  • Short answers: 15.2–16.4 tokens/sec across the smoke set.
  • Memory footprint while loaded: 3.89 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): 8/8 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 4B 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. ThoxClip (6 GB) target configuration. 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, 2026-11-01 (founder order: every kit model published). Kit: THOX Device Model Catalog and Build Kit. Base pin: qwen3:4b @ 359d7dd4bcdab3d86b87d73ac27966f4dbb9f5efdfcc75d34a8764a09474fae7. Published model digest: 855cfdb35137e84573a8501ecea2826c07bec7b7364815a68606656d400e09f4.

Citation

@misc{thoxai2026thoxclipagent4b,
      title={ThoxClip-Agent-4B},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxClip-Agent-4B}
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Thox-ai/ThoxClip-Agent-4B

Finetuned
Qwen/Qwen3-4B
Finetuned
(1221)
this model

Collection including Thox-ai/ThoxClip-Agent-4B