Instructions to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG",
	filename="Qwen3.5-0.8B-GEC-KAZ-RUS-ENG.Q4_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG 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 loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
# Run inference directly in the terminal:
llama cli -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
# Run inference directly in the terminal:
llama cli -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_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 loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_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 loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Use Docker

docker model run hf.co/loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

LM Studio
Jan

vLLM

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Ollama
How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Ollama:
```
ollama run hf.co/loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
```

Unsloth Studio

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG to start chatting

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_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 loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_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 "loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_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"

Docker Model Runner
How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Docker Model Runner:
```
docker model run hf.co/loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0
```

Lemonade

How to use loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull loqira/Qwen3.5-0.8B-GEC-KAZ-RUS-ENG:Q4_0

Run and chat with the model

lemonade run user.Qwen3.5-0.8B-GEC-KAZ-RUS-ENG-Q4_0

List all available models

lemonade list

Qwen3.5-0.8B-GEC-KAZ-RUS-ENG / Modelfile

kkolomeitsev

Set Ollama num_ctx to 2048 to match the training context window

ced4697 3 days ago

Raw

History Blame Contribute Delete

1.33 kB

	FROM ./Qwen3.5-0.8B-GEC-KAZ-RUS-ENG.Q4_0.gguf

	# Ollama Go-template (ollama does not read the Jinja chat template embedded in the
	# GGUF — it needs its own). This reproduces the deploy contract byte-for-byte:
	# <\|im_start\|>system\n{system}<\|im_end\|>\n<\|im_start\|>user\n{prompt}<\|im_end\|>\n
	# <\|im_start\|>assistant\n<think>\n\n</think>\n\n{response}<\|im_end\|>\n
	# The empty <think> block is think-off: a formatter with no reasoning.
	# Single-turn use only — one request, one response. Do not chain turns.
	TEMPLATE """{{ if .System }}<\|im_start\|>system
	{{ .System }}<\|im_end\|>
	{{ end }}<\|im_start\|>user
	{{ .Prompt }}<\|im_end\|>
	<\|im_start\|>assistant
	<think>

	</think>

	{{ .Response }}<\|im_end\|>
	"""

	# The single unified system prompt (deploy contract, verbatim). Same for every
	# input and every language (kk / ru / en). Written in Russian by design.
	SYSTEM """Отформатируй текст голосового ввода: расставь пунктуацию и заглавные буквы, разбей на абзацы, исправь опечатки и орфографические ошибки. Сохрани язык, слова и смысл, ничего не добавляй от себя."""

	PARAMETER stop "<\|im_end\|>"
	PARAMETER temperature 0
	PARAMETER repeat_penalty 1.0
	PARAMETER num_ctx 2048