Instructions to use ornith-ai/Ornith-1.0-35B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ornith-ai/Ornith-1.0-35B with Transformers:

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

pipe = pipeline("text-generation", model="ornith-ai/Ornith-1.0-35B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ornith-ai/Ornith-1.0-35B")
model = AutoModelForMultimodalLM.from_pretrained("ornith-ai/Ornith-1.0-35B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ornith-ai/Ornith-1.0-35B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ornith-ai/Ornith-1.0-35B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ornith-ai/Ornith-1.0-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ornith-ai/Ornith-1.0-35B

SGLang

How to use ornith-ai/Ornith-1.0-35B 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 "ornith-ai/Ornith-1.0-35B" \
    --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": "ornith-ai/Ornith-1.0-35B",
		"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 "ornith-ai/Ornith-1.0-35B" \
        --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": "ornith-ai/Ornith-1.0-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ornith-ai/Ornith-1.0-35B with Docker Model Runner:
```
docker model run hf.co/ornith-ai/Ornith-1.0-35B
```

This model is way better than qwen 3.6 35b a3b

by Narutoouz - opened Jun 26

Discussion

Narutoouz

Jun 26

•

edited Jun 26

benchmarks can be deceiving at times, but I understood this model is legit by fixing a real bug that was previously unsolvable.
I had a bug in my project related to SQlite testing
the qwen 3.6 35b a3b's 8bit version couldn't solve it and was going to skip it, which is a failure...
but this model's oq5 variant (not even 8bit) was able to solve the bug in 7 minutes
I am waiting for someone to release the oq8 version of this model.
This is the best local coding model till date.
I am using this model in my m4 max macbook pro, without MTP I still get around 35 tokens/s. For Nvidia folks might get around 100 tokens/ s I guess. Anything beyond 10 tokens/s is useful for daily workflows.
Thanks for releasing this awesome model deepreinforce-ai team.

palladium107

29 days ago

I was also using Qwen3.6 35b, and 27b dense model for coding before.
In the last week I've been working with Ornith, and I can tell it feels much better than Qwen.
Regarding speed, I was getting better results with Qwen because I was using MTP models.
One recent update of llama.cpp improved Ornith input token generation by roughly 100%, before It was generating input tokens by 400-470t/s, now it is more like 850-900t/s.
Output token generation also become faster, but it comes out at parallel agent running, 3 agents in parallel are generating 50-70t/s each.
I'm using 5070Ti (16GB) + 3090(24GB), and I'm maxing out the 5070Ti whenever I can.

halonc

29 days ago

benchmarks can be deceiving at times, but I understood this model is legit by fixing a real bug that was previously unsolvable.

I had a bug in my project related to SQlite testing

the qwen 3.6 35b a3b's 8bit version couldn't solve it and was going to skip it, which is a failure...

but this model's oq5 variant (not even 8bit) was able to solve the bug in 7 minutes

I am waiting for someone to release the oq8 version of this model.

This is the best local coding model till date.

I am using this model in my m4 max macbook pro, without MTP I still get around 35 tokens/s. For Nvidia folks might get around 100 tokens/ s I guess. Anything beyond 10 tokens/s is useful for daily workflows.
Thanks for releasing this awesome model deepreinforce-ai team.

it is a fantastic model for sure if you have a large vram card, 27b Is good，but is slow even on 5090, Which is ridiculously expensive these days, So i got a AMD R9700, Using this model, i manage to get 58 tps, pp is between 2000-1200, it almost replaces Deepseek V4 flash. it's crazy!

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