Instructions to use Agnes-AI/Agnes-3.0-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Agnes-AI/Agnes-3.0-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="Agnes-AI/Agnes-3.0-Flash", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Agnes-AI/Agnes-3.0-Flash", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Agnes-AI/Agnes-3.0-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Agnes-AI/Agnes-3.0-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Agnes-AI/Agnes-3.0-Flash",
		"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/Agnes-AI/Agnes-3.0-Flash

SGLang

How to use Agnes-AI/Agnes-3.0-Flash 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 "Agnes-AI/Agnes-3.0-Flash" \
    --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": "Agnes-AI/Agnes-3.0-Flash",
		"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 "Agnes-AI/Agnes-3.0-Flash" \
        --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": "Agnes-AI/Agnes-3.0-Flash",
		"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 Agnes-AI/Agnes-3.0-Flash with Docker Model Runner:
```
docker model run hf.co/Agnes-AI/Agnes-3.0-Flash
```

Agnes-3.0-Flash / serve.sh

Agnes-AI

Add files using upload-large-folder tool

3599318 verified 16 days ago

Raw

History Blame

1.45 kB

	#!/bin/bash
	# Serve Agnes 3.0 Flash with a stock sglang image.
	#
	# Tested image: lmsysorg/sglang:nightly-dev-20260908-20ca564b
	#
	# docker run --gpus all --shm-size 64g -p 30001:30002 \
	# -v /path/to/agnes-3.0-flash:/model \
	# lmsysorg/sglang:nightly-dev-20260908-20ca564b \
	# bash /model/serve.sh [extra sglang arguments, e.g. --tp 2]
	#
	# The script overlays three files from sglang_patch/ onto the image's sglang
	# package (a prebuilt variant when one matches the installed version, else
	# apply_patch.py patches the installed files in place) and starts the server
	# on port 30002 inside the container.
	set -euo pipefail
	D="$(cd "$(dirname "$0")" && pwd)"
	PKG="$(python3 -c 'import sglang, os; print(os.path.dirname(sglang.__file__))')"
	VER="$(python3 -c 'import sglang; print(getattr(sglang, "__version__", ""))' 2>/dev/null \|\| true)"

	case "$VER" in
	20ca564b) VARIANT="nightly-dev-20260908-20ca564b" ;;
	0.5.19*) VARIANT="v0.5.19" ;;
	*) VARIANT="" ;;
	esac

	if [ -n "$VARIANT" ] && [ -d "$D/sglang_patch/$VARIANT/sglang" ]; then
	echo "[serve.sh] sglang $VER -> prebuilt patch $VARIANT"
	cp -r "$D/sglang_patch/$VARIANT/sglang/." "$PKG/"
	else
	echo "[serve.sh] sglang $VER -> patching installed package in place"
	python3 "$D/sglang_patch/apply_patch.py" "$PKG"
	fi

	export AGNES_MODEL_PATH="$D"
	exec python3 -m sglang.launch_server --model-path "$D" --trust-remote-code --host 0.0.0.0 --port 8080 "$@"