> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nexa.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# CLI Reference
> This page documents all available CLI commands with usage examples.
Run nexa commands from the nexa executable directory.
## **nexa pull**
Download a model and store it locally.
After entering the pull command, you will be guided through a setup process to choose the model type, main model file, tokenizer (optional), and extra files (optional).
### **General Behavior**
After running `nexa pull `, the CLI will prompt:
1. **Quant version selection**\
If the model supports multiple quantized versions, you will see a menu like this:
```bash Quant version selection theme={"dark"}
Choose a quant version to download
> Q4_K_M [1.2 GiB] (default)
Q8_0 [2.0 GiB]
F16 [3.8 GiB]
```
Select a quant version you prefer.
2. **Download begins**\
After selection, the model files will start downloading automatically.
### **LLM**
```bash bash theme={"dark"}
nexa pull NexaAI/Qwen3-0.6B-GGUF
```
### **VLM**
```bash bash theme={"dark"}
nexa pull NexaAI/Qwen2.5-Omni-3B-GGUF
```
### **Function Call**
```bash bash theme={"dark"}
nexa pull NexaAI/Qwen3-0.6B-GGUF
```
### **Omni Model**
```bash bash theme={"dark"}
nexa pull NexaAI/Qwen2.5-Omni-3B-GGUF
```
### **ASR**
```bash bash theme={"dark"}
nexa pull mlx-community/whisper-tiny
```
### **TTS**
```bash bash theme={"dark"}
nexa pull nexaml/Kokoro-82M-bf16-MLX
```
### **Embedder**
```bash bash theme={"dark"}
nexa pull djuna/jina-embeddings-v2-small-en-Q5_K_M-GGUF
```
### **Reranker**
```bash bash theme={"dark"}
nexa pull pqnet/bge-reranker-v2-m3-Q8_0-GGUF
```
## **nexa list**
Display all downloaded models in a table with their names and sizes.
```bash bash theme={"dark"}
nexa list
```
## **nexa remove**
Remove a specific local model by name.
For example, remove the locally downloaded model NexaAI/Qwen3-0.6B-GGUF from the cache directory. This will free up disk space and make the model unavailable for future inference unless re-downloaded.
```bash bash theme={"dark"}
nexa remove NexaAI/Qwen3-0.6B-GGUF
```
## **nexa clean**
Delete all locally cached models.
```bash bash theme={"dark"}
nexa clean
```
## **nexa infer**
Run inference with a specified model. The model must be downloaded and cached locally.
### **Helper menu**
```bash bash theme={"dark"}
nexa infer -h
```
Show help menu for `nexa infer`.
### **LLM**
Launch an interactive chat session with the language model.
```bash bash theme={"dark"}
nexa infer NexaAI/Qwen3-0.6B-GGUF
```
Use the `--think` option to control whether the model outputs its internal reasoning process.
* `--think=false` : The model responds directly without showing reasoning.
* `--think=true` : The model displays its reasoning steps before the final response.
Example with reasoning enabled:
```bash bash theme={"dark"}
nexa infer NexaAI/Qwen3-0.6B-GGUF --think=true
```
### **VLM**
Text-only or response from image file (interactive image input):
```bash bash theme={"dark"}
nexa infer NexaAI/Qwen2.5-Omni-3B-GGUF
```
If you only want text input, simply launch the command and begin chatting.\
If you'd like the model to response from an image, provide the **absolute path** to an image at the end of your message.\
Example prompt: `Describe this picture `
### **Omni Models**
Text-only or response from audio file (interactive audio output):
```bash bash theme={"dark"}
nexa infer ggml-org/Qwen2.5-Omni-3B-GGUF
```
If you only want text output, start chatting as usual.
If you'd like the model to response from an audio, provide an **absolute path** to an audio at the end of your message.\
Example prompt: `Convert this audio into text `
### **ASR**
Currently, ASR is only supported on macOS using the mlx runtime.
Use ASR models to transcribe speech from audio files into text.
```bash bash theme={"dark"}
nexa infer -m asr mlx-community/whisper-tiny --input < /path/to/audio.wav > --language en
```
* `-m asr` : Sets the model type to ASR.
* `--input` : Specifies the input audio file.
* `--language` : Sets the language code (e.g., en for English, zh for Chinese).
### **TTS**
Currently, TTS is only supported on macOS using the mlx runtime.
Use TTS models to convert input text into spoken audio.
```bash bash theme={"dark"}
nexa infer nexaml/Kokoro-82M-bf16-MLX -m tts --voice-identifier zm_yunyang -p "Hello world this is a text to speech test" -o < /path/to/audio.wav >
```
* `-m TTS` : Sets the model type to TTS.
* `--voice-identifier`: Specifies the speaker's voice.
When no `--voice-identifier` is provided, NexaCLI will return a full list of supported voices in the error message. This is useful for discovering all available voice options.
* `-p`: The text prompt to synthesize.
* `-o`: Output file for the generated .wav audio.
### **Embedder**
Generate embeddings for multiple pieces of text using an embedding model.
```bash bash theme={"dark"}
nexa infer djuna/jina-embeddings-v2-small-en-Q5_K_M-GGUF -m embedder --prompt "translate to text" --prompt "second"
```
* `-m embedder` : Sets the model type to Embedder.
* `--prompt` : Provide one or more pieces of text to embed.
### **Reranker**
Use a reranker model to score and sort documents based on relevance to a query.
```bash bash theme={"dark"}
nexa infer pqnet/bge-reranker-v2-m3-Q8_0-GGUF -m reranker --query "query" --document "a" --document "query"
```
* `-m reranker` : Sets the model type to Reranker.
* `--query` : The main query string used to evaluate document relevance.
* `--document` : One or more documents to score against the query.
## **nexa serve**
Launch the Nexa inference server using REST API.
### **Helper menu**
```bash bash theme={"dark"}
nexa serve -h
```
Show help menu for `nexa serve`.
### **Start serve**
For example, start a local inference server bound to 127.0.0.1:8080. The server supports OpenAI-compatible APIs, and --keepalive 600 keeps models in memory for 10 minutes between requests.
```bash bash theme={"dark"}
nexa serve --host 127.0.0.1:8080 --keepalive 600
```
You can test it via:
```bash Windows (cmd) theme={"dark"}
curl -X POST http://127.0.0.1:8080/v1/chat/completions -H "Content-Type: application/json" -d "{\"model\": \"NexaAI/Qwen3-0.6B-GGUF\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"max_tokens\": 64}"
```
```bash MacOS theme={"dark"}
curl -X POST http://127.0.0.1:8080/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "NexaAI/Qwen3-0.6B-GGUF",
"messages": [{"role":"user","content":"Hello!"}],
"max_tokens": 64
}'
```
This will send a POST request to the local /v1/completions endpoint to prompt the NexaAI/Qwen3-0.6B-GGUF model with “What is the capital of France?” and return a response with up to 100 tokens.
## **nexa run**
Connect to a running Nexa server (via OpenAI-compatible API) and start a chat interface. You should start server first.
### **Helper menu**
```bash bash theme={"dark"}
nexa run -h
```
Show help menu for `nexa run`.
### **Run model**
For example: launch an interactive streaming chat session with the NexaAI/Qwen3-0.6B-GGUF model. The model generates and displays output incrementally as tokens are produced.
```bash bash theme={"dark"}
nexa run NexaAI/Qwen3-0.6B-GGUF
```
`--disable-stream|-s`: disable streaming and respond the entire json back.