Instructions to use spele1100/Ornith-1.0-9B-AWQ-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use spele1100/Ornith-1.0-9B-AWQ-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="spele1100/Ornith-1.0-9B-AWQ-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("spele1100/Ornith-1.0-9B-AWQ-INT4")
model = AutoModelForCausalLM.from_pretrained("spele1100/Ornith-1.0-9B-AWQ-INT4", device_map="auto")
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 Settings

vLLM

How to use spele1100/Ornith-1.0-9B-AWQ-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "spele1100/Ornith-1.0-9B-AWQ-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "spele1100/Ornith-1.0-9B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/spele1100/Ornith-1.0-9B-AWQ-INT4

SGLang

How to use spele1100/Ornith-1.0-9B-AWQ-INT4 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 "spele1100/Ornith-1.0-9B-AWQ-INT4" \
    --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": "spele1100/Ornith-1.0-9B-AWQ-INT4",
		"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 "spele1100/Ornith-1.0-9B-AWQ-INT4" \
        --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": "spele1100/Ornith-1.0-9B-AWQ-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use spele1100/Ornith-1.0-9B-AWQ-INT4 with Docker Model Runner:
```
docker model run hf.co/spele1100/Ornith-1.0-9B-AWQ-INT4
```

Ornith-1.0-9B-AWQ-INT4

AWQ INT4 (pack-quantized) conversion of Ornith-1.0-9B, optimized for vLLM AWQ kernel inference.

Details

	Value
Base model	ornith-ai/Ornith-1.0-9B (Qwen3.5 9B Dense)
Quant method	GPTQ (llmcompressor)
Precision	W4A16 (INT4 weights, FP16 activations)
Format	pack-quantized
Group size	128
Observer	memoryless_minmax
Calibration	128 samples (UltraChat 200k)
Model size	5.8 GB (vs 19 GB BF16)
Compression ratio	~3.3x

Compatibility

✅ vLLM (AWQ kernel, pack-quantized format)
✅ SGLang
✅ Transformers (with compressed-tensors)

Usage

from vllm import LLM, SamplingParams

llm = LLM(model=spele1100/Ornith-1.0-9B-AWQ-INT4, quantization=awq)
sampling = SamplingParams(temperature=0.6, top_p=0.95, top_k=20)
output = llm.generate([Hello!], sampling)
print(output[0].outputs[0].text)

Quantization Script

from llmcompressor import oneshot
from llmcompressor.modifiers.quantization import GPTQModifier
from transformers import AutoTokenizer
from datasets import load_dataset

model = ornith-ai/Ornith-1.0-9B
tok = AutoTokenizer.from_pretrained(model, trust_remote_code=True)
ds = load_dataset(HuggingFaceH4/ultrachat_200k, split=train_sft).select(range(512))

recipe = GPTQModifier(
    targets=Linear,
    scheme=W4A16,
    ignore=[model.visual.*],
)

oneshot(
    model=model,
    recipe=recipe,
    output_dir=./Ornith-1.0-9B-AWQ-INT4,
    tokenizer=tok,
    dataset=ds,
    max_seq_length=512,
    num_calibration_samples=128,
)

Hardware

Quantized on a single NVIDIA A100-80GB-SXM4 via RunPod.

License

MIT — inherits from Ornith-1.0-9B.

Acknowledgements

Ornith-1.0 by Deep Reinforce AI
llmcompressor by vLLM Project
cyankiwi/Ornith-1.0-9B-AWQ-INT4 for reference

Downloads last month: 168

Safetensors

Model size

9B params

Tensor type

I32

BF16

Model tree for spele1100/Ornith-1.0-9B-AWQ-INT4

Base model

ornith-ai/Ornith-1.0-9B

Quantized

(101)

this model