Instructions to use cagataydev/cosmos-reason2-2b-fp8-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cagataydev/cosmos-reason2-2b-fp8-hf with Transformers:

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

pipe = pipeline("image-text-to-text", model="cagataydev/cosmos-reason2-2b-fp8-hf")
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("cagataydev/cosmos-reason2-2b-fp8-hf")
model = AutoModelForMultimodalLM.from_pretrained("cagataydev/cosmos-reason2-2b-fp8-hf", 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]:]))

TensorRT

How to use cagataydev/cosmos-reason2-2b-fp8-hf with TensorRT:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cagataydev/cosmos-reason2-2b-fp8-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cagataydev/cosmos-reason2-2b-fp8-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cagataydev/cosmos-reason2-2b-fp8-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/cagataydev/cosmos-reason2-2b-fp8-hf

SGLang

How to use cagataydev/cosmos-reason2-2b-fp8-hf 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 "cagataydev/cosmos-reason2-2b-fp8-hf" \
    --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": "cagataydev/cosmos-reason2-2b-fp8-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "cagataydev/cosmos-reason2-2b-fp8-hf" \
        --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": "cagataydev/cosmos-reason2-2b-fp8-hf",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use cagataydev/cosmos-reason2-2b-fp8-hf with Docker Model Runner:
```
docker model run hf.co/cagataydev/cosmos-reason2-2b-fp8-hf
```

Cosmos-Reason2-2B FP8 (HF checkpoint via ModelOpt)

Source: nvidia/Cosmos-Reason2-2B (Qwen3-VL) Quantization: FP8 on language_model (vision tower bf16) Toolchain: NVIDIA ModelOpt 0.43.0 export_hf_checkpoint Calibration: 8 multimodal (image+text) samples

For TensorRT-LLM / TensorRT-Edge-LLM engine build on Jetson Thor, this checkpoint is the input to trtllm-build --model_dir <this>.

Provenance

AWS EC2 NVIDIA L40S, Ubuntu 24.04
torch==2.6.0+cu124, transformers==4.57.6, nvidia-modelopt==0.43.0, tensorrt==10.16.1
Produced by DevDuck auto-pipeline 2026-05-07

Downloads last month: 17

Safetensors

Model size

2B params

Tensor type

BF16

F8_E4M3

Model tree for cagataydev/cosmos-reason2-2b-fp8-hf

Base model

Qwen/Qwen3-VL-2B-Instruct

Finetuned

nvidia/Cosmos-Reason2-2B

Quantized

(14)

this model