ThoxMini-125M-role

ThoxMini-125M-role

Device-lock note (2026-10-23): under the current THOX device lock, ThoxAir and ThoxClip do not host a language model, and ThoxMini on-device model support is held until a test pass is recorded. Role models are trained for these device personas and run on a paired host (phone, laptop or MeshStack node). Throughput claims were removed pending a recorded measurement. Owner wording required before merge.

Capability status (2026-09-29): Public weights. Device mapping is recorded in ttracx/thox-device-models and certified only as public + mapped + no blocked marketing claims. This is not a tok/s, AIME, or HIPAA certificate. ThoxNova names on this org are a model family, not a campaign SKU.

Device-role model for the ThoxMini persona. ThoxMini on-device model support is held until a test pass is recorded; until then run it on a paired host.

Thox-ai/thox-micro-125m role-tuned so it can actually be used as an assistant.

Why this exists

The base is a base LM with no instruct tuning. Measured on the exact file that had been dropped to the image lane:

Hello, who are you? → <mup> PR snapd#7621 closed: tests: check that the test fails with an error <Created by mvo5>

That is raw training-scrape leaking. It could not ship as an assistant. After tuning, the same prompt returns a coherent deferral.

Measured behaviour

Prompts held out of the training corpus:

Zero fabrications, and no scrape leakage. In-corpus commands work: status → "Key online. Storage sealed. No pending transfers."

Two known defects — read before shipping

1. It says "the key", not "the mini." The role corpus was authored for ThoxKey-S3 and reused verbatim, so device-specific strings are wrong for this board: do you send my data anywhere → "No. I run on the key. Nothing leaves it." Correct in substance, wrong in noun. Fix is a ThoxMini variant of datasets/device/thoxkey-role.jsonl, not a retrain of the recipe.

2. It over-defers on identity. Hello, who are you? returns "I cannot answer that locally. The host has it." It should name itself. The corpus trains deferral hard and contains no identity turn for this device; adding one fixes it.

Neither is a fabrication, which is the failure mode that actually blocks shipping. Both are corpus gaps.

Training

v5 and not v4 deliberately. v4 carries tag: correction rows that quote a falsehood so the assistant can deny it; those rows taught fabrication rather than preventing it — a 7B trained on them invented "a Partner at Insight Partners" for a real named person. v5 quarantines them.

EOS is appended explicitly during training. Omitting it is a defect this factory already paid for: adapters trained without it emitted EOS zero times across 12 gate answers and ran to the token cap every time.

<!-- THOX-STANDARD:BEGIN -->

Files

Use with ThoxOS

Download the file once and run it fully offline on a ThoxOS host (or any Linux/macOS/Windows machine):

pip install -U "huggingface_hub[cli]"
hf download Thox-ai/ThoxMini-125M-role ThoxMini-125M-role.Q4_K_M.gguf --local-dir ./ThoxMini-125M-role
llama-cli -m ./ThoxMini-125M-role/ThoxMini-125M-role.Q4_K_M.gguf -p "Hello" -n 128

Ollama (pulls straight from the Hub):

ollama run hf.co/Thox-ai/ThoxMini-125M-role:Q4_K_M

A same-named entry also exists in the Ollama library: ollama.com/Thox-ai/thoxmini-125m-role (contents not re-verified in this pass; prefer the hf.co/ pull above for a pinned file).

LM Studio: search Thox-ai/ThoxMini-125M-role in the model browser (or lms get Thox-ai/ThoxMini-125M-role), pick ThoxMini-125M-role.Q4_K_M.gguf, and load it.

Use with MeshStack

Serve the model as an OpenAI-compatible endpoint on any MeshStack node, then register that endpoint with your MeshStack coordinator (protocol openai, base URL http://<node-ip>:8080/v1; or protocol ollama at http://<node-ip>:11434 if you serve it with Ollama).

llama-server -m ./ThoxMini-125M-role/ThoxMini-125M-role.Q4_K_M.gguf --host 0.0.0.0 --port 8080 -c 512
curl http://<node-ip>:8080/v1/chat/completions -H 'Content-Type: application/json' \
  -d '{"messages":[{"role":"user","content":"Hello"}]}'

Device fit (by file size only)

• ThoxMini-125M-role.Q4_K_M.gguf (84.66 MB): Small (<600 MB): single-board computers with ≥1 GB RAM, phones, any laptop/desktop.

RAM needed ≈ file size + context (KV cache) + runtime overhead. These tiers are derived from file size alone; no throughput, TOPS or battery figures are claimed here.

Licence and attribution

Fine-tuned from Thox-ai/thox-micro-125m (THOX.ai LLC, Apache-2.0).

Out of scope

• Medical, legal, financial, safety-critical or other high-stakes decisions without human review.
• Unattended control of physical devices or actuators without a confirmation step.
• Any use prohibited by the upstream licence or acceptable-use policy.

Limitations and bias

• Small and quantized models make factual mistakes and can produce confident but wrong output; verify important answers.
• Behaviour and bias reflect the training data, which is mostly English web/instruction text; quality in other languages is lower unless stated above.
• Quantization trades accuracy for size; lower-bit files degrade more.

---

THOX.ai LLC — Your AI. Your Data. Your Rules.™ · thox.ai · Contact: [email protected]

<!-- THOX-STANDARD:END -->