Thox-ai/ thoxmini-chat-3b:latest

8 2 days ago

ThoxMini chat configuration (4 GB target). THOX-configured Qwen2.5-3B, not THOX-trained. 11.66 tok/s long-form, 2.42 GB RAM on CPU at 8,192 ctx; grounding 6/8, trap declined. Qwen Research License (non-commercial).

tools 
ollama run Thox-ai/thoxmini-chat-3b

Details

2 days ago

9846bb55ae37 · 1.9GB

model
qwen2
·
3.09B
·
Q4_K_M
template
{{- if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{- if .System }} {{ .System }} {{
license
Qwen RESEARCH LICENSE AGREEMENT Qwen RESEARCH LICENSE AGREEMENT Release Date: September 19, 2024 By
system
You are a THOX device assistant for ThoxMini. Prioritize privacy and clear, accurate responses. Use
params
{ "num_ctx": 2048, "temperature": 0.3 }

Readme

ThoxMini-Chat-3B — ThoxMini (4 GB) target chat configuration (Qwen2.5-3B, THOX-Configured)

License Params Base Access

Your AI. Your Data. Your Rules.™

NON-COMMERCIAL — Qwen Research License. The base model for this configuration (Qwen2.5-3B) is published by its upstream under the Qwen Research License, which permits research and non-commercial use only. This listing is published for research and evaluation; it must not be used or marketed commercially. The license terms of the base model govern.

ThoxMini-Chat-3B is a THOX-configured model: upstream Qwen2.5-3B 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.

Files

File Size SHA-256 (first 16) Purpose
Modelfile 449 B 3d0676374ebbd14c Ollama model definition: pinned base + kit system profile
manifest.json 369 B 6b3a1cfd411336d3 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/thoxmini-chat-3b is 1.93 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/thoxmini-chat-3b

Build it yourself from this repo

hf download Thox-ai/ThoxMini-Chat-3B --local-dir ./ThoxMini-Chat-3B
cd ./ThoxMini-Chat-3B && ollama create thoxmini-chat-3b -f Modelfile && ollama run thoxmini-chat-3b

Summary

ThoxMini (4 GB) target chat configuration. Configuration-derived: THOX did not train these weights. ThoxMini (4 GB) target configuration. Distinct from the trained ThoxMini-Phi4Mini. Not qualified on device hardware.

Intended use

Local inference through Ollama’s local endpoint for the role above, on hardware that fits a 3B 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/Qwen2.5-3B-Instruct via Ollama tag qwen2.5:3b, pinned at build time to manifest digest 357c53fb659c5076de1d65ccb0b397446227b71a42be9d1603d46168015c9e4b. 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: 11.66 tokens/sec (1,024-token bench).
  • Short answers: 11.8–23.6 tokens/sec across the smoke set.
  • Memory footprint while loaded: 2.42 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): 6⁄8 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 3B 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. ThoxMini (4 GB) target configuration. Distinct from the trained ThoxMini-Phi4Mini. Not qualified on device hardware.

License

Qwen Research License, inherited from the base model — the Qwen Research License permits research and non-commercial use only; commercial use and commercial marketing of this listing are not permitted. 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: qwen2.5:3b @ 357c53fb659c5076de1d65ccb0b397446227b71a42be9d1603d46168015c9e4b. Published model digest: 5b021ff5bc702223c74375dbecb3e8ddb97898f98f0c381807caeff98c20e861.