Instructions to use Doszhan-M/qlex-packages with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Doszhan-M/qlex-packages 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 Doszhan-M/qlex-packages
# Run inference directly in the terminal:
llama cli -hf Doszhan-M/qlex-packages

Install from WinGet (Windows)

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

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 Doszhan-M/qlex-packages
# Run inference directly in the terminal:
./build/bin/llama cli -hf Doszhan-M/qlex-packages

Use Docker

docker model run hf.co/Doszhan-M/qlex-packages

Llama new
LM Studio
Jan
Ollama
How to use Doszhan-M/qlex-packages with Ollama:
```
ollama run hf.co/Doszhan-M/qlex-packages
```
Unsloth Desktop

How to use Doszhan-M/qlex-packages with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Doszhan-M/qlex-packages

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": "Doszhan-M/qlex-packages"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Doszhan-M/qlex-packages with Docker Model Runner:
```
docker model run hf.co/Doszhan-M/qlex-packages
```

Lemonade

How to use Doszhan-M/qlex-packages with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Doszhan-M/qlex-packages

Run and chat with the model

lemonade run user.qlex-packages-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Doszhan-M/qlex-packages with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Doszhan-M/qlex-packages

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 Doszhan-M/qlex-packages

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Doszhan-M/qlex-packages with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Doszhan-M/qlex-packages

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 "Doszhan-M/qlex-packages" \
  --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"

Qlex language packages

Language packages for Qlex, an offline on-screen translator for games. Qlex downloads them itself when the user picks a language; files are checked against SHA-256 sums in catalog.json.

A translation language is a translation model and a dictionary; a game language other than English adds a text recognition model and a model translating it into English:

opus-* — OPUS-MT models by Helsinki-NLP (Language Technology Research Group, University of Helsinki), converted to CTranslate2 (int8). License: CC BY 4.0.
gemma4-e2b-qat-* — Gemma 4 E2B by Google, the Q4_0 QAT GGUF build (google/gemma-4-E2B-it-qat-q4_0-gguf), unmodified — translation into Chinese, Japanese and Korean. License: Apache 2.0.
llama-* — llama-server and its libraries from llama.cpp release builds, unmodified. License: MIT (Windows: LLVM OpenMP — Apache 2.0 with LLVM exceptions).
ocr-* — text recognition models PP-OCRv5 (rec, mobile) by PaddleOCR in ONNX format by RapidOCR, unmodified — games in languages other than English. License: Apache 2.0.
dict-* — English dictionaries built from Wiktionary dumps by kaikki.org (wiktextract, Tatu Ylonen). License: CC BY-SA 4.0.

Every package folder contains its own LICENSE. See LICENSE for details.

Downloads last month: 496

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants