Instructions to use Thox-ai/ThoxMicro-1bit-9M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Thox-ai/ThoxMicro-1bit-9M with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
llama cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Thox-ai/ThoxMicro-1bit-9M:Q8_0

Use Docker

docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use Thox-ai/ThoxMicro-1bit-9M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thox-ai/ThoxMicro-1bit-9M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thox-ai/ThoxMicro-1bit-9M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0

Ollama
How to use Thox-ai/ThoxMicro-1bit-9M with Ollama:
```
ollama run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use Thox-ai/ThoxMicro-1bit-9M with Docker Model Runner:
```
docker model run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0
```

Lemonade

How to use Thox-ai/ThoxMicro-1bit-9M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Thox-ai/ThoxMicro-1bit-9M:Q8_0

Run and chat with the model

lemonade run user.ThoxMicro-1bit-9M-Q8_0

List all available models

lemonade list

Atomic Chat
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ThoxMicro-1bit-9M

Your AI. Your Data. Your Rules.

From-scratch BitNet b1.58 ternary Llama (9M) trained on TinyStories — a story-completion / edge research artifact, not an assistant.

What this is

Trained from scratch — no upstream base model.
76.4% of weights are ternary {-1,0,+1} (BitNet b1.58).
License is unresolved: TinyStories (CDLA-Sharing-1.0) share-alike not yet cleared — treat as pending review, not open for redistribution until THOX confirms.
Sibling: ThoxMicro-1bit-16M (deeper, not a replacement).

Architecture (from config)

Field	Value
Architecture	BitNet b1.58 ternary Llama 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

Intended use

On-device / edge text generation within the THOX stack. Not a safety-aligned public assistant unless deployed behind THOX guardrails.

Usage

llama.cpp

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"

Files

File	Size	SHA-256
`thoxmicro-1bit-9m.Q8_0.gguf`	9.77 MB (9,771,104 B)	`d33cea1fc8234de024934f88cf6a6298d2dfc61d0150dc3bdbd2e77e0be1c26a`
`thoxmicro-1bit-9m.TQ2_0.gguf`	6.25 MB (6,252,640 B)	`bbc3ef3e1a9125ff6a9f1ad7e57181d2311c4fc48f9a1cb9054f4dbd5fc2ffc0`

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/ThoxMicro-1bit-9M thoxmicro-1bit-9m.Q8_0.gguf --local-dir ./ThoxMicro-1bit-9M
llama-cli -m ./ThoxMicro-1bit-9M/thoxmicro-1bit-9m.Q8_0.gguf -p "Hello" -n 128

Ollama (pulls straight from the Hub):

ollama run hf.co/Thox-ai/ThoxMicro-1bit-9M:Q8_0

Ternary TQ1_0 / TQ2_0 files need a recent llama.cpp build; Ollama and LM Studio may only load the Q8_0 file.

LM Studio: search Thox-ai/ThoxMicro-1bit-9M in the model browser (or lms get Thox-ai/ThoxMicro-1bit-9M), pick thoxmicro-1bit-9m.Q8_0.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 ./ThoxMicro-1bit-9M/thoxmicro-1bit-9m.Q8_0.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"}]}'

Use the prompt format documented above; small/role models may need -c 512 and a plain completion prompt.

Device fit (by file size only)

thoxmicro-1bit-9m.TQ2_0.gguf (6.25 MB): Tiny (<50 MB): runs on any host; also small enough for constrained edge targets that have a GGUF-capable runtime.
thoxmicro-1bit-9m.Q8_0.gguf (9.77 MB): Tiny (<50 MB): runs on any host; also small enough for constrained edge targets that have a GGUF-capable runtime.

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

Licence pending review: trained on TinyStories (CDLA-Sharing-1.0, share-alike). Treat redistribution terms as unresolved until THOX confirms; do not bundle commercially in the meantime.

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: tommy@thox.ai

Downloads last month: 137

GGUF

Model size

8.92M params

Architecture

llama

Hardware compatibility

2-bit

8-bit

Model tree for Thox-ai/ThoxMicro-1bit-9M

Quantizations

2 models

Thox-ai
/

ThoxMicro-1bit-9M