Instructions to use srmftech/Torqen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use srmftech/Torqen 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 srmftech/Torqen
# Run inference directly in the terminal:
llama cli -hf srmftech/Torqen

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf srmftech/Torqen
# Run inference directly in the terminal:
llama cli -hf srmftech/Torqen

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 srmftech/Torqen
# Run inference directly in the terminal:
./build/bin/llama cli -hf srmftech/Torqen

Use Docker

docker model run hf.co/srmftech/Torqen

Llama new
LM Studio
Jan

vLLM

How to use srmftech/Torqen with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/srmftech/Torqen

Ollama
How to use srmftech/Torqen with Ollama:
```
ollama run hf.co/srmftech/Torqen
```
Unsloth Desktop

How to use srmftech/Torqen with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf srmftech/Torqen

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": "srmftech/Torqen"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use srmftech/Torqen with Docker Model Runner:
```
docker model run hf.co/srmftech/Torqen
```

Lemonade

How to use srmftech/Torqen with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull srmftech/Torqen

Run and chat with the model

lemonade run user.Torqen-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use srmftech/Torqen with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf srmftech/Torqen

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 srmftech/Torqen

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use srmftech/Torqen with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf srmftech/Torqen

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 "srmftech/Torqen" \
  --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"

⚡ Torqen-1-beta (0.8B) — by srmf.tech

Torqen-1-beta-0.8b — это ультра-компактная экспериментальная языковая модель с поддержкой цепочек рассуждений (Reasoning), разработанная проектом srmf.tech.

Модель создана путем тонкого дообучения (SFT) в 16-битном режиме и скомпилирована в формат GGUF (Q8_0) практически без потери точности.

🧠 Особенности версии 1-beta

Собственная самоидентификация: Модель обучена как ассистент Torqen от проекта srmf.tech.
Режим размышлений (Thinking Mode): Перед генерацией ответа модель выстраивает логическую цепочку рассуждений.
Сверхнизкие требования к железу: Вес файла Torqen-1-beta-0.8b.gguf составляет ~812 МБ — модель мгновенно работает даже на офисных ПК без видеокарты, ноутбуках и смартфонах.

⚙️ Рекомендуемые настройки запуска (LM Studio / Ollama)

Из-за малого размера параметров (0.8B) для предотвращения галлюцинаций рекомендуется использовать строгие параметры сэмплирования:

Temperature: 0.0 – 0.2
Top_P: 0.85
Repetition Penalty: 1.1

Системный промпт (System Prompt):

Ты — Torqen, компактный ИИ-ассистент от проекта srmf.tech. Отвечай кратко, строго по делу и на русском языке.

Developed by srmf.tech (2026). Готовится к выходу старшая версия Torqen на базе 9B параметров.

Downloads last month: 61

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for srmftech/Torqen

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

unsloth/Qwen3.5-0.8B

Quantized

(18)

this model

srmftech
/

Torqen

⚡ Torqen-1-beta (0.8B) — by srmf.tech

🧠 Особенности версии 1-beta

⚙️ Рекомендуемые настройки запуска (LM Studio / Ollama)

Системный промпт (System Prompt):

Model tree for srmftech/Torqen

Datasets used to train srmftech/Torqen