ThoxMicro-1bit-9M

From-Scratch THOX Ternary Model — a THOX model trained from scratch: a BitNet b1.58 ternary decoder (9M parameters, 76.4% of weights in {-1, 0, +1}) trained on TinyStories

GGUF: Q8_0, TQ2_0 · Ollama Modelfile

Your AI. Your Data. Your Rules.™

Status: PUBLISHED — RESEARCH MODEL. A THOX model trained from scratch: a BitNet b1.58 ternary decoder (9M parameters) trained on TinyStories. See Files for exactly what this repo contains.

Summary

ThoxMicro-1bit-9M is a THOX model trained from scratch: a BitNet b1.58 ternary decoder (9M parameters, 76.4% of weights in {-1, 0, +1}) trained on TinyStories. It is a story-completion and edge research model, not an assistant, and it is the base for the THOX 9M device-role models. Its deeper sibling is ThoxMicro-1bit-16M; neither supersedes the other.

Highlights

• ThoxMicro-1bit-9M is a THOX model trained from scratch: a BitNet b1.58 ternary decoder (9M parameters, 76.4% of weights in {-1, 0, +1}) trained on TinyStories.
• bash hf download Thox-ai/ThoxMicro-1bit-9M --include '*.gguf' --local-dir ./ThoxMicro-1bit-9M llama-cli -m ./ThoxMicro-1bit-9M/thoxmicro-1bit-9m.TQ2_0.gguf -p "Hello" Ternary files need a recent llama.cpp build; Ollama and LM Studio load only the Q8_0 file.

Specifications

Base model	See card body
Parameters	See card body
Formats	GGUF: Q8_0, TQ2_0 · Ollama Modelfile
License	Apache-2.0
This repository contains	GGUF build(s) in this repo: thoxmicro-1bit-9m.Q8_0.gguf, thoxmicro-1bit-9m.TQ2_0.gguf

Files

File	Size	SHA-256
thoxmicro-1bit-9m.Q8_0.gguf	9,771,104 B	d33cea1fc8234de024934f88cf6a6298d2dfc61d0150dc3bdbd2e77e0be1c26a
thoxmicro-1bit-9m.TQ2_0.gguf	6,252,640 B	bbc3ef3e1a9125ff6a9f1ad7e57181d2311c4fc48f9a1cb9054f4dbd5fc2ffc0
.gitattributes / Modelfile	—	Supporting files (see repo)

Architecture

Field	Value
Architecture	BitNet b1.58 ternary decoder
Layers	8
Hidden size	256
Attention heads	8
KV heads	8
FFN / intermediate	768
Vocab	8,192 (own byte-level BPE)
Max context	512
Tied embeddings	yes

Run it

hf download Thox-ai/ThoxMicro-1bit-9M --include '*.gguf' --local-dir ./ThoxMicro-1bit-9M
llama-cli -m ./ThoxMicro-1bit-9M/thoxmicro-1bit-9m.TQ2_0.gguf -p "Hello"

Ternary files need a recent llama.cpp build; Ollama and LM Studio load only the Q8_0 file.

Platforms

Platform / device	Run path
Hugging Face	Download the builds listed under Files from this repo (see Run it)

Intended use

• On-device and edge text generation within the THOX stack, and research on ternary-weight models.
• Not a safety-aligned public assistant unless deployed behind THOX guardrails.
• Out of scope: medical, legal, financial, safety-critical, or other high-stakes decisions without human review.

Training data and procedure

Trained by THOX from scratch as part of the THOX small-model research line. The corpus and procedure are as described in this card at release; no external base model was used.

Evaluation

No THOX GATE49 result is published for this model.

Limitations

• A 9M research model: story completion only, no instruction following or factual reliability.
• Behaviour and bias reflect the training data; quality outside short English story text is low.
• Quantization trades accuracy for size.

License

Apache License 2.0. This model was trained by THOX from scratch and is released under the Apache License 2.0. Training data note: the training corpus is TinyStories, distributed under CDLA-Sharing-1.0; that license governs the dataset itself.

THOX.ai — Your AI. Your Data. Your Rules.™

Provenance

Published by THOX.ai as Thox-ai/ThoxMicro-1bit-9M. THOX from-scratch research line; no upstream base model. 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.

Citation

@misc{thoxai2026thoxmicro1bit9m,
      title={ThoxMicro-1bit-9M},
      author={THOX.ai},
      year={2026},
      url={https://huggingface.co/Thox-ai/ThoxMicro-1bit-9M}
}