Instructions to use tommytracx/Thox1-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tommytracx/Thox1-27b 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 tommytracx/Thox1-27b:Q1_0
# Run inference directly in the terminal:
llama cli -hf tommytracx/Thox1-27b:Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tommytracx/Thox1-27b:Q1_0
# Run inference directly in the terminal:
llama cli -hf tommytracx/Thox1-27b:Q1_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf tommytracx/Thox1-27b:Q1_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf tommytracx/Thox1-27b:Q1_0

Use Docker

docker model run hf.co/tommytracx/Thox1-27b:Q1_0

Llama new
LM Studio
Jan

vLLM

How to use tommytracx/Thox1-27b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tommytracx/Thox1-27b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tommytracx/Thox1-27b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tommytracx/Thox1-27b:Q1_0

Ollama
How to use tommytracx/Thox1-27b with Ollama:
```
ollama run hf.co/tommytracx/Thox1-27b:Q1_0
```
Unsloth Desktop

How to use tommytracx/Thox1-27b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tommytracx/Thox1-27b:Q1_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tommytracx/Thox1-27b:Q1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tommytracx/Thox1-27b with Docker Model Runner:
```
docker model run hf.co/tommytracx/Thox1-27b:Q1_0
```

Lemonade

How to use tommytracx/Thox1-27b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tommytracx/Thox1-27b:Q1_0

Run and chat with the model

lemonade run user.Thox1-27b-Q1_0

List all available models

lemonade list

Hermes Agent

How to use tommytracx/Thox1-27b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tommytracx/Thox1-27b:Q1_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tommytracx/Thox1-27b:Q1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tommytracx/Thox1-27b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tommytracx/Thox1-27b:Q1_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tommytracx/Thox1-27b:Q1_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Thox1-27b

⚠️ Safety review flag (Wren pass 2026-10-23). This repo redistributes a community uncensored / abliterated model. It is not part of the default ThoxOS or MeshStack catalog and is not promoted for THOX devices. It has reduced refusal behaviour and must not be deployed to end users without your own safety layer. Gating / visibility is under review by the owner.

Your AI. Your Data. Your Rules.

THOX flagship 1-bit (Q1_0) GGUF quant of a 27B Qwen3.5-family abliterated model — the most-downloaded THOX repo.

What this is

Real quantized-weights repo: single Thox1-27b-Q1_0.gguf (~4.67 GB) + config/tokenizer.
Base: s3nh/Bonsai-27B-unpacked-abliterated-uncensored (Qwen3.5 VLM). base_model_relation=quantized.
config max_position_embeddings 262144; card serves at 8192 — align the card's context claim.
License chain: card asserts Apache-2.0 over an abliterated base — verify the full chain. Uncensored — content-policy sensitive.
Config is a full VLM (vision tower) but it is served text-only via llama.cpp.

Architecture (from config)

Field	Value
Architecture	qwen3_5 (Qwen3_5ForConditionalGeneration, VLM base; served text-only)
Layers	64
Hidden size	5120
Attention heads	24
KV heads	4 (GQA)
FFN / intermediate	17408
Vocab	248,320
Max context	262144
dtype	bfloat16

Intended use

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

Prompt / chat template

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Usage

llama.cpp

hf download tommytracx/Thox1-27b --include '*.gguf' --local-dir ./Thox1-27b
llama-cli -m ./Thox1-27b/Thox1-27b-Q1_0.gguf -p "Hello"

Files

File	Size	SHA-256
`Thox1-27b-Q1_0.gguf`	4.67 GB (4,667,606,336 B)	`47536d403990fff9650200928a48c2c51a16c72aa26c26a6f84eef7f21451d38`

Use

Not listed in the ThoxOS / MeshStack catalog (safety review pending). If you accept the risks above, it can be run locally with llama.cpp:

hf download tommytracx/Thox1-27b Thox1-27b-Q1_0.gguf --local-dir ./Thox1-27b
llama-server -m ./Thox1-27b/Thox1-27b-Q1_0.gguf -c 4096

Q1_0 is a 1-bit format; it needs a llama.cpp build that supports it and may not load in Ollama or LM Studio.

Device fit (by file size only)

Thox1-27b-Q1_0.gguf (4.67 GB): Large (<6 GB): hosts with ≥8 GB RAM (16 GB recommended) or a GPU with ≥6 GB VRAM.

Licence and attribution

Declared Apache-2.0 via s3nh/Bonsai-27B-unpacked-abliterated-uncensored (Apache-2.0 on the Hub). Intermediate lineage not independently verified.

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: 446

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

1-bit

Model tree for tommytracx/Thox1-27b

Base model

s3nh/Bonsai-27B-unpacked-abliterated-uncensored

Quantized

(1)

this model

tommytracx
/

Thox1-27b

Thox1-27b

What this is

Architecture (from config)

Intended use

Prompt / chat template

Usage

Links

Files

Use

Device fit (by file size only)

Licence and attribution

Out of scope

Limitations and bias

Model tree for tommytracx/Thox1-27b