Instructions to use VohoAI/voho-saudi-speak-0.6b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use VohoAI/voho-saudi-speak-0.6b-GGUF 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 VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf VohoAI/voho-saudi-speak-0.6b-GGUF: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 VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VohoAI/voho-saudi-speak-0.6b-GGUF: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 VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use VohoAI/voho-saudi-speak-0.6b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VohoAI/voho-saudi-speak-0.6b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VohoAI/voho-saudi-speak-0.6b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

Ollama
How to use VohoAI/voho-saudi-speak-0.6b-GGUF with Ollama:
```
ollama run hf.co/VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
```
Unsloth Desktop

How to use VohoAI/voho-saudi-speak-0.6b-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VohoAI/voho-saudi-speak-0.6b-GGUF: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": "VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VohoAI/voho-saudi-speak-0.6b-GGUF with Docker Model Runner:
```
docker model run hf.co/VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M
```

Lemonade

How to use VohoAI/voho-saudi-speak-0.6b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.voho-saudi-speak-0.6b-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use VohoAI/voho-saudi-speak-0.6b-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VohoAI/voho-saudi-speak-0.6b-GGUF: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 VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use VohoAI/voho-saudi-speak-0.6b-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf VohoAI/voho-saudi-speak-0.6b-GGUF: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 "VohoAI/voho-saudi-speak-0.6b-GGUF: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"

Voho Saudi Speak 0.6B — GGUF

GGUF builds of Voho Saudi Speak 0.6B, for llama.cpp, Ollama, LM Studio and anything else that reads GGUF.

Turns formal Arabic into Arabic the way Saudis actually say it, in Najdi, Hijazi or Khaleeji. Give it a formal sentence and a dialect, and it returns what a person from Riyadh, Jeddah or the Eastern Province would say on a phone call.

Files

File	Size	Use
`voho-saudi-speak-0.6b-Q4_K_M.gguf`	397 MB	Smallest; recommended for CPU and phones
`voho-saudi-speak-0.6b-Q5_K_M.gguf`	444 MB	Balanced
`voho-saudi-speak-0.6b-Q6_K.gguf`	495 MB	Near-lossless
`voho-saudi-speak-0.6b-Q8_0.gguf`	639 MB	Practically identical to the original
`voho-saudi-speak-0.6b-F16.gguf`	1.2 GB	Full precision, for re-quantising

Q4_K_M and Q8_0 were checked against the original model before upload: on an Apple M-series laptop a sentence takes under 0.1 seconds.

The prompt

The model was trained on one instruction. Use it exactly, swapping the dialect name:

Dialect	Name in the prompt
Najdi (Riyadh, central)	`النجدية`
Hijazi (Jeddah, Makkah)	`الحجازية`
Khaleeji (Eastern Province)	`الخليجية الشرقية`

أعد صياغة هذه الجملة باللهجة السعودية النجدية كما يقولها شخص في مكالمة، بدون أي شرح:
أين أنت الآن؟ أريد أن أحجز موعداً غداً.

→ وينك الحين أبغى أحجز موعد بكرة

Use greedy decoding (temperature 0) and turn thinking off.

llama.cpp

llama-cli -hf VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M --temp 0 --reasoning-budget 0 \
  -p "أعد صياغة هذه الجملة باللهجة السعودية النجدية كما يقولها شخص في مكالمة، بدون أي شرح:
أين أنت الآن؟ أريد أن أحجز موعداً غداً."

Or as a server with an OpenAI-compatible API:

llama-server -hf VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M --temp 0 --reasoning-budget 0

Ollama

ollama run hf.co/VohoAI/voho-saudi-speak-0.6b-GGUF:Q4_K_M

LM Studio

Search for VohoAI/voho-saudi-speak-0.6b-GGUF, download Q4_K_M, set temperature to 0.

Examples

Dialect	Formal input	Output
Najdi	أين أنت الآن؟ أريد أن أحجز موعداً غداً.	وينك الحين أبغى أحجز موعد بكرة
Hijazi	سنرسل لك رمز التحقق الآن، من فضلك أخبرني به.	بنرسلك رمز التحقق دحين من فضلك خبرني فيه
Khaleeji	الآن فقط فهمت قصدك وسر اهتمامك.	الحين بس فهمت قصدك وسر اهتمامك.

Results, training details and limitations are on the main model card.

Licence

Non-commercial, CC BY-NC-SA 4.0, inherited from the SADA training data. For production Saudi Arabic voice, use the Voho API.

Please cite SADA: Saudi Audio Dataset for Arabic (SADA), Saudi Data and AI Authority (SDAIA), 2022.

Downloads last month: 187

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for VohoAI/voho-saudi-speak-0.6b-GGUF

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

VohoAI/voho-saudi-speak-0.6b

Quantized

(3)

this model

VohoAI
/

voho-saudi-speak-0.6b-GGUF

Voho Saudi Speak 0.6B — GGUF

Files

The prompt

llama.cpp

Ollama

LM Studio

Examples

Licence

Model tree for VohoAI/voho-saudi-speak-0.6b-GGUF

Dataset used to train VohoAI/voho-saudi-speak-0.6b-GGUF