9 Downloads Updated 3 days ago
ollama run Thox-ai/thoxkey-9m-role:9m

ThoxKey Device Model — the device-role model for ThoxKey, fine-tuned from a THOX model trained from scratch (no external base)
Safetensors weights · GGUF: Q8_0, TQ1_0, TQ2_0
Find your model: THOX Model Factory · Collection: Flagship & Edge Device Models
Your AI. Your Data. Your Rules.™
ThoxKey-9M-role is the device-role model for ThoxKey, fine-tuned from a THOX model trained from scratch (no external base). It is a BitNet b1.58 ternary model (weights in {-1, 0, +1}, int8 activations) with 8,917,248 parameters. This is the model baked into the ThoxKey firmware. It handles local device commands, names itself when asked, and defers everything else rather than inventing it: it holds no company facts by design, and recorded zero fabrications on held-out company-fact prompts.
| Base model | Thox-ai/ThoxMicro-1bit-9M |
| Parameters | 9M |
| Formats | Safetensors weights · GGUF: Q8_0, TQ1_0, TQ2_0 · Ollama Modelfile |
| License | Apache-2.0 |
| This repository contains | Full weights and tokenizer in this repo |
| File | Size | Purpose |
|---|---|---|
hf/model.safetensors |
17,842,448 B | Model weights (safetensors) |
thoxkey-9m-role-Q8_0.gguf |
9,771,104 B | GGUF model build |
thoxkey-9m-role-TQ2_0.gguf |
6,252,640 B | GGUF model build |
thoxkey-9m-role-TQ1_0.gguf |
5,933,152 B | GGUF model build |
thoxkey-9m-role.tern1 |
4,420,028 B | Device build (TERN1) |
hf/tokenizer.json |
561,388 B | Tokenizer files |
manifest.json |
20,700 B | Release manifest |
.gitattributes |
1,765 B | Repository file |
hf/config.json |
536 B | JSON metadata |
Modelfile |
532 B | Ollama model definition |
hf/tokenizer_config.json |
180 B | Tokenizer files |
hf |
0 B | Repository file |
| File | Use |
|---|---|
thoxkey-9m-role.tern1 |
The firmware artifact (TERN1 device runtime) |
thoxkey-9m-role-TQ1_0.gguf |
llama.cpp ternary |
thoxkey-9m-role-Q8_0.gguf |
llama.cpp / Ollama host validation |
hf download Thox-ai/ThoxKey-9M-role thoxkey-9m-role-Q8_0.gguf --local-dir ./ThoxKey-9M-role
llama-cli -m ./ThoxKey-9M-role/thoxkey-9m-role-Q8_0.gguf -p "Hello" -n 128
Ollama cannot load ternary GGUF (TQ1_0 / TQ2_0); use the Q8_0 file on a host. Ternary files need a recent llama.cpp build.
| Platform / device | Run path |
|---|---|
| Hugging Face | Download the builds listed under Files from this repo (see Run it) |
THOX fine-tune of Thox-ai/ThoxMicro-1bit-9M. 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.
No THOX GATE49 result is published for this model. Its recorded behaviour check: zero fabrications on held-out company-fact prompts, by design (the corpus contains no company facts to repeat).
Published by THOX.ai as Thox-ai/ThoxKey-9M-role. Upstream base: Thox-ai/ThoxMicro-1bit-9M. 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.
Apache License 2.0. This model is fine-tuned from Thox-ai/ThoxMicro-1bit-9M, a THOX model trained from scratch and also released under Apache-2.0. Training data note: training included TinyStories, distributed under CDLA-Sharing-1.0; that license governs the dataset itself.
THOX.ai — Your AI. Your Data. Your Rules.™
@misc{thoxai2026thoxkey9mrole,
title={ThoxKey-9M-role},
author={THOX.ai},
year={2026},
url={https://huggingface.co/Thox-ai/ThoxKey-9M-role}
}