Instructions to use NuJan/qwev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NuJan/qwev 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 NuJan/qwev:Q4_K_M # Run inference directly in the terminal: llama cli -hf NuJan/qwev:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NuJan/qwev:Q4_K_M # Run inference directly in the terminal: llama cli -hf NuJan/qwev: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 NuJan/qwev:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf NuJan/qwev: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 NuJan/qwev:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf NuJan/qwev:Q4_K_M
Use Docker
docker model run hf.co/NuJan/qwev:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use NuJan/qwev with Ollama:
ollama run hf.co/NuJan/qwev:Q4_K_M
- Unsloth Desktop
- Pi
How to use NuJan/qwev with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NuJan/qwev: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": "NuJan/qwev:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use NuJan/qwev with Docker Model Runner:
docker model run hf.co/NuJan/qwev:Q4_K_M
- Lemonade
How to use NuJan/qwev with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NuJan/qwev:Q4_K_M
Run and chat with the model
lemonade run user.qwev-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use NuJan/qwev with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NuJan/qwev: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 NuJan/qwev:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use NuJan/qwev with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf NuJan/qwev: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 "NuJan/qwev: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"
Qwev
Qwev is the tool router inside NuJan, an AI agent app for Android.
What it does
Qwev decides which tool families a request needs, so a small on-device chat model is offered a short tool list instead of all of them. The base model is Qwen/Qwen3.5-0.8B-Base, fine-tuned with LoRA (rank 32), merged, and quantised to GGUF Q4_K_M, about 529 MB. It runs on llama.cpp.
Given a request in a fixed prompt, Qwev outputs a probability for each of 17 route letters at one position. Those routes are 15 tool families, "core tools only", and "just answer". It does not generate text in normal use. qwev.router.json holds the prompt prefix and suffix, the route names, and the token id of each route letter, so a client can read the 17 probabilities directly.
Files
| File | Contents |
|---|---|
| qwev-v1-Q4_K_M.gguf | GGUF Q4_K_M weights, about 529 MB |
| qwev.router.json | Prompt prefix and suffix, route names, and the token id of each route letter |
How NuJan uses it
NuJan offers at most 2 families per request: the most likely ones until they cover 90% of the probability, none below 0.15, within the space left in the context window.
Results
With Qwev, a 2B on-device model completed 10 of 12 test tasks on two phones, against 7 to 8 of 12 without it. A routing decision takes about 0.2 to 0.3 seconds on a recent flagship phone and about 1 second on a 2019 mid-range phone once warm.
Limits
Qwev is for English requests. The 17 routes are NuJan's own tool families, so other apps would need their own mapping. It picks families, not individual tools. Tasks that need a sub-agent are a common miss.
License
Apache-2.0, the same license as the base model.
- Downloads last month
- 38
4-bit
Model tree for NuJan/qwev
Base model
Qwen/Qwen3.5-0.8B-Base