Instructions to use lucataco/Ornith-1.0-35B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lucataco/Ornith-1.0-35B-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="lucataco/Ornith-1.0-35B-NVFP4")
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("lucataco/Ornith-1.0-35B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("lucataco/Ornith-1.0-35B-NVFP4", 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 lucataco/Ornith-1.0-35B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lucataco/Ornith-1.0-35B-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lucataco/Ornith-1.0-35B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lucataco/Ornith-1.0-35B-NVFP4

SGLang

How to use lucataco/Ornith-1.0-35B-NVFP4 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 "lucataco/Ornith-1.0-35B-NVFP4" \
    --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": "lucataco/Ornith-1.0-35B-NVFP4",
		"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 "lucataco/Ornith-1.0-35B-NVFP4" \
        --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": "lucataco/Ornith-1.0-35B-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lucataco/Ornith-1.0-35B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/lucataco/Ornith-1.0-35B-NVFP4
```

Ornith-1.0-35B-NVFP4

This is an NVFP4/FourOverSix quantized checkpoint of deepreinforce-ai/Ornith-1.0-35B.

Quantization

Source revision: 5df2ed3f675c7beaa490328cc70bb573b65fb660
Format: transformers + fouroversix
Weight dtype: nvfp4
Scale rule: static_6
Output dtype: bfloat16
lm_head plus 154 shape-incompatible linear modules are kept in the original BF16 format and listed in modules_to_not_convert.

The checkpoint was converted by streaming the original safetensor shards into FourOverSix-compatible quantized tensors, so it can be loaded with recent transformers builds that include FourOverSixConfig support and the fouroversix package installed.

Loading Note

This checkpoint was smoke-tested with transformers==5.12.1, torch==2.10.0+cu130, and fouroversix==1.0.5. The local FourOverSix install also included the Qwen3.5 MoE compatibility fix for DataType property access inside fouroversix/model/modules/qwen.py. If loading raises an error such as DataType object is not callable, a missing scale_dtype, or missing get_weight_scale_rule / get_activation_scale_rule, update FourOverSix to a release containing that fix or patch that Qwen module.

Local Decode Benchmark

Tested on an NVIDIA GB10 with transformers==5.12.1, torch==2.10.0+cu130, and the patched fouroversix==1.0.5 runtime. The test used batch size 1, greedy manual decoding, synthetic repeated-token context, 1024-token chunked prefill, and logits_to_keep=1.

Context tokens	Decode speed
1,024	8.95 tok/s
8,192	9.08 tok/s
32,768	6.64 tok/s
100,000	7.06 tok/s

The 100k context run completed, but used about 120.6 GiB of the GB10's 121.7 GiB visible CUDA memory, leaving roughly 1.1 GiB free.

Downloads last month: 134

Safetensors

Model size

20B params

Tensor type

F32

I32

BF16

F8_E4M3

Model tree for lucataco/Ornith-1.0-35B-NVFP4

Base model

deepreinforce-ai/Ornith-1.0-35B

Quantized

(169)

this model