Instructions to use Sigrex/Qwen3-0.6B-tg-signal-extract with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Sigrex/Qwen3-0.6B-tg-signal-extract 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 Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

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 Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

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 Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

Use Docker

docker model run hf.co/Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

LM Studio
Jan

vLLM

How to use Sigrex/Qwen3-0.6B-tg-signal-extract with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sigrex/Qwen3-0.6B-tg-signal-extract"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sigrex/Qwen3-0.6B-tg-signal-extract",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

Ollama
How to use Sigrex/Qwen3-0.6B-tg-signal-extract with Ollama:
```
ollama run hf.co/Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
```
Unsloth Desktop

How to use Sigrex/Qwen3-0.6B-tg-signal-extract with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

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": "Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Sigrex/Qwen3-0.6B-tg-signal-extract with Docker Model Runner:
```
docker model run hf.co/Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M
```

Lemonade

How to use Sigrex/Qwen3-0.6B-tg-signal-extract with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3-0.6B-tg-signal-extract-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Sigrex/Qwen3-0.6B-tg-signal-extract with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

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 Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Sigrex/Qwen3-0.6B-tg-signal-extract with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M

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 "Sigrex/Qwen3-0.6B-tg-signal-extract:Q4_K_M" \
  --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"

Telegram Signal Extract — Qwen3 0.6B

A fine-tuned Qwen3 0.6B model for extracting a compact trading-signal payload from Telegram channel messages. It is intended to return either a payload such as:

{"symbol":"ONEUSDT","side":"BUY"}

or the literal JSON value:

null

The model was trained with supervised examples pairing Telegram messages with a signal payload or null. For best observed output, use temperature 0 and the task system prompt below. Fine-tuning alone does not guarantee valid JSON or correct classifications; validate model output before using it.

System prompt

You extract trade signals from Telegram channel messages. For an actionable open/close signal, reply with ONLY a JSON object like {"symbol": "BTCUSDT", "side": "BUY"} where symbol is the uppercase trading pair and side is BUY or SELL. If the message is not an actionable signal, reply with exactly: null

Files

File	Quantization / precision	Approx. size
`Qwen3-0.6B.Q4_K_M.gguf`	Q4_K_M	378 MiB
`Qwen3-0.6B.Q5_K_M.gguf`	Q5_K_M	424 MiB
`Qwen3-0.6B.Q6_K.gguf`	Q6_K	472 MiB
`Qwen3-0.6B.Q8_0.gguf`	Q8_0	610 MiB
`Qwen3-0.6B.F16.gguf`	F16	1.12 GiB
`Qwen3-0.6B.BF16.gguf`	BF16	1.12 GiB
Other `IQ*` and `Q2`/`Q3` GGUFs	Smaller quantizations	See file sizes on the Files tab

The repository is large because it includes all exported variants. For most local use, start with Q4_K_M; use a higher precision variant if you have enough memory and want to compare quality.

Task and output

Input: one raw Telegram message.
Positive output: {"symbol":"<UPPERCASE_PAIR>","side":"BUY"} or {"symbol":"<UPPERCASE_PAIR>","side":"SELL"}.
Negative output: null.
The payload contains symbol and side only. It does not estimate trade size, profitability, or risk.

Training

Qwen3 supports a reasoning/"thinking" mode. This fine-tune was trained without reasoning traces, so run it with thinking disabled; otherwise the model may emit a reasoning block instead of the bare payload.

Intended use and limitations

This is an experimental information-extraction model, not a trading system or investment recommendation. It can miss signals, misread tickers/direction, or return invalid output. Do not automatically place orders from its responses. Parse the output as JSON, reject anything outside the expected schema, and independently validate symbols and trading actions.

Base model and license

This model is derived from unsloth/Qwen3-0.6B-unsloth-bnb-4bit, which is a 4-bit quantization of Qwen/Qwen3-0.6B. Qwen3-0.6B is released under the Apache License 2.0, and this fine-tune is distributed under the same license — apache-2.0, not Meta's Llama license. See the Qwen3-0.6B model page.