Instructions to use QCRI/Fanar-2-27B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QCRI/Fanar-2-27B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QCRI/Fanar-2-27B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QCRI/Fanar-2-27B-Instruct")
model = AutoModelForCausalLM.from_pretrained("QCRI/Fanar-2-27B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use QCRI/Fanar-2-27B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QCRI/Fanar-2-27B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QCRI/Fanar-2-27B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QCRI/Fanar-2-27B-Instruct

SGLang

How to use QCRI/Fanar-2-27B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "QCRI/Fanar-2-27B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QCRI/Fanar-2-27B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "QCRI/Fanar-2-27B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QCRI/Fanar-2-27B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QCRI/Fanar-2-27B-Instruct with Docker Model Runner:
```
docker model run hf.co/QCRI/Fanar-2-27B-Instruct
```

Please bring Fanar-Aura-STT-LF-1 and Fanar-Aura-STT-1 models

by adeel-a-dev - opened Apr 3

Discussion

adeel-a-dev

Apr 3

Hello,

Please update Fanar-Aura-STT-LF-1 and Fanar-Aura-STT-1 models.

fdalvi

Qatar Computing Research Institute org Apr 6

Thank you Adeel for your interest! We hope to open source more models in the future, for now you can access them through our API (https://api.fanar.qa). Feel free to reach out if you have any trouble accessing the API.

fdalvi changed discussion status to closed Apr 6

adeel-a-dev

Apr 6

Thank you for your response. Actually, your API comes with very limited requests per day usage allowed. That is why we are unable to use it on the production level. However, the results very promising. Also, we are unable to offer any paid plan. We will need at least 10,000 or more per day usage on production. Please let us know how you can help us in this regard. Thank you!

shammur

Qatar Computing Research Institute org Apr 6

•

edited Apr 6

Thank you Adeel for the interest. For your information, you can reach out to the fanar team for increase the usage for initial testing and your requirement.

fdalvi

Qatar Computing Research Institute org Apr 6

As Shammur mentioned, please reach out to support@fanar.qa with some information regarding your usecase and your team, we are happy to discuss further!

adeel-a-dev

Apr 6

•

edited Apr 6

Already sent an email on 8th March 2026, but did not get any response with the "Inquiry about Increasing Speech-to-Text Capacity and Access to Models" subject.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment