Thox-ai/ thoxclip-mind-1.5b:latest

6 2 days ago

ThoxClip (6 GB) target configuration (Qwen2.5-1.5B, THOX-Configured) — thoxClip (6 GB) target configuration: on-device decision support 20.87 tok/s long-form (measured 2026-10-31, conditions under Evaluation) · Ollama Modelfile · Live on Ollama

tools 
ollama run Thox-ai/thoxclip-mind-1.5b

Details

2 days ago

61f1971f4f25 · 986MB

model
qwen2
·
1.54B
·
Q4_K_M
template
{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
system
You are a THOX device assistant for ThoxClip. Prioritize privacy and clear, accurate responses. Use
params
{ "num_ctx": 2048, "temperature": 0.3 }

Readme

ThoxClip-Mind-1.5B

ThoxClip (6 GB) target configuration (Qwen2.5-1.5B, THOX-Configured) — thoxClip (6 GB) target configuration: on-device decision support

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

License Params Base Access

Run it: Ollama — Thox-ai/thoxclip-mind-1.5b · Find your model: THOX Model Factory · Collection: iOS, Browser & Device Knowledge Packs

Back THOX on Kickstarter

Your AI. Your Data. Your Rules.™

ThoxClip-Mind-1.5B is a THOX-configured model: upstream Qwen2.5-1.5B 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.

Highlights

  • ThoxClip (6 GB) target configuration: on-device decision support.
  • Ollama (published model) bash ollama run Thox-ai/thoxclip-mind-1.5b

Specifications
Base model Qwen/Qwen2.5-1.5B-Instruct
Parameters 1.5B
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 451 B 6a2cb96e025f6a02 Ollama model definition: pinned base + kit system profile
manifest.json 387 B 195e402f577747e0 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/thoxclip-mind-1.5b is 0.99 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-mind-1.5b

Build it yourself from this repo

hf download Thox-ai/ThoxClip-Mind-1.5B --local-dir ./ThoxClip-Mind-1.5B
cd ./ThoxClip-Mind-1.5B && ollama create thoxclip-mind-1.5b -f Modelfile && ollama run thoxclip-mind-1.5b

Platforms

Platform / device Run path
Ollama (laptop / desktop) ollama run Thox-ai/thoxclip-mind-1.5b
Hugging Face Download the builds listed under Files from this repo (see Run it)

Summary

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

Intended use

Local inference through Ollama’s local endpoint for the role above, on hardware that fits a 1.5B 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/Qwen2.5-1.5B-Instruct via Ollama tag qwen2.5:1.5b, pinned at build time to manifest digest 65ec06548149b04c096a120e4a6da9d4017ea809c91734ea5631e89f96ddc57b. Customization: the kit system profile in the Modelfile plus THOX Knowledge Pack v0.1 for retrieval-grounded answers.

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: 20.87 tokens/sec (1,024-token bench).
  • Short answers: 21.5–30.7 tokens/sec across the smoke set.
  • Memory footprint while loaded: 1.37 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 1.5B 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. 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, 2026-10-31 (founder order: every kit model published). Kit: THOX Device Model Catalog and Build Kit. Base pin: qwen2.5:1.5b @ 65ec06548149b04c096a120e4a6da9d4017ea809c91734ea5631e89f96ddc57b. Published model digest: 173e9cd01653b8acc55ad8fd0fb5ea1425a63af73a1e62ce061c535135448f94.

Citation

@misc{thoxai2026thoxclipmind15b,
      title={ThoxClip-Mind-1.5B},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxClip-Mind-1.5B}
}