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-AI commited on 11 days ago

Commit

22c68a8

verified ·

1 Parent(s): 82b86c9

Replace benchmark chart with supplied Preview image

Browse files

Files changed (1) hide show

README.md +5 -10

README.md CHANGED Viewed

@@ -23,19 +23,15 @@ tags:
 </p>
 # Agnes-3.0-Flash Preview
 ## Model version clarification
 This repository contains an earlier open-weight **Preview checkpoint** of Agnes 3.0 Flash. It is distinct from the newer **production/API checkpoint** listed on [Artificial Analysis](https://artificialanalysis.ai/models/agnes-3-0-flash).
 The Preview release has **33B parameters** and a context window of **262,144 tokens**. The production/API model uses a different checkpoint and configuration, with a **1M-token context window**. Its benchmark results should not be attributed to the Preview weights released here.
 This repository was initially published as `Agnes-3.0-Flash` without the `Preview` suffix. The model card now explicitly identifies this release as **Agnes-3.0-Flash Preview** to clarify the distinction between the open-weight release and the production/API model.
 The specifications and Agnes benchmark results below refer to the **Preview checkpoint**.
 Hello! 👋 Today we are introducing **Agnes-3.0-Flash Preview**, an **open-weights multimodal preview model** built for people who want flagship-class reasoning without flagship-class hardware.
 Highlights:
 - **Competitive across core capabilities.** Agnes-3.0-Flash Preview posts competitive results across reasoning, coding, and instruction-following evaluations.
@@ -43,16 +39,13 @@ Highlights:
 ### Benchmarks
 > **Benchmark scope:** The Agnes results in the chart and table below belong to the **Agnes-3.0-Flash Preview open-weight checkpoint** released in this repository. They are not results for the production/API Agnes 3.0 Flash model listed on Artificial Analysis.
 <p align="center">
-  <img style="width:100%;max-width:1100px" src="assets/agnes_benchmarks.svg" alt="Agnes-3.0-Flash Preview benchmark reference results">
 </p>
-The label "Agnes-3.0-Flash" in the benchmark image refers to this Preview checkpoint.
 Reference results across contemporary models are shown below. The figures were compiled from different sources, harnesses, and model snapshots and do not constitute a controlled head-to-head comparison.
 <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;width:100%;margin:0 auto;padding:16px 0;overflow-x:auto">
 <table style="width:100%;table-layout:fixed;border-collapse:collapse;font-size:11px;min-width:1180px">
@@ -81,6 +74,7 @@ Higher is better for every row. Header parameter figures mix total and active co
 </p>
 ## Architecture
 Agnes-3.0-Flash Preview is a hybrid-attention decoder: three of every four layers run a gated delta rule (recurrent, with per-layer state independent of sequence length), and the fourth runs standard global attention. Only 18 of the 72 layers therefore hold a KV cache that grows with context.
 | | |
@@ -104,6 +98,7 @@ Agnes-3.0-Flash Preview is a hybrid-attention decoder: three of every four layer
 </div>
 ### Requirements
 ```bash
 pip install "transformers>=5.12" torch torchvision accelerate

 </p>
 # Agnes-3.0-Flash Preview
 ## Model version clarification
 This repository contains an earlier open-weight **Preview checkpoint** of Agnes 3.0 Flash. It is distinct from the newer **production/API checkpoint** listed on [Artificial Analysis](https://artificialanalysis.ai/models/agnes-3-0-flash).
 The Preview release has **33B parameters** and a context window of **262,144 tokens**. The production/API model uses a different checkpoint and configuration, with a **1M-token context window**. Its benchmark results should not be attributed to the Preview weights released here.
 This repository was initially published as `Agnes-3.0-Flash` without the `Preview` suffix. The model card now explicitly identifies this release as **Agnes-3.0-Flash Preview** to clarify the distinction between the open-weight release and the production/API model.
 The specifications and Agnes benchmark results below refer to the **Preview checkpoint**.
 Hello! 👋 Today we are introducing **Agnes-3.0-Flash Preview**, an **open-weights multimodal preview model** built for people who want flagship-class reasoning without flagship-class hardware.
 Highlights:
 - **Competitive across core capabilities.** Agnes-3.0-Flash Preview posts competitive results across reasoning, coding, and instruction-following evaluations.
 ### Benchmarks
 > **Benchmark scope:** The Agnes results in the chart and table below belong to the **Agnes-3.0-Flash Preview open-weight checkpoint** released in this repository. They are not results for the production/API Agnes 3.0 Flash model listed on Artificial Analysis.
 <p align="center">
+  <img style="width:100%;max-width:1100px" src="assets/benchmark-preview.png" alt="Agnes-3.0-Flash Preview benchmark reference results">
 </p>
+The Agnes-3.0-Flash Preview scores in the chart correspond to the open-weight checkpoint released in this repository.
 Reference results across contemporary models are shown below. The figures were compiled from different sources, harnesses, and model snapshots and do not constitute a controlled head-to-head comparison.
 <div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;width:100%;margin:0 auto;padding:16px 0;overflow-x:auto">
 <table style="width:100%;table-layout:fixed;border-collapse:collapse;font-size:11px;min-width:1180px">
 </p>
 ## Architecture
 Agnes-3.0-Flash Preview is a hybrid-attention decoder: three of every four layers run a gated delta rule (recurrent, with per-layer state independent of sequence length), and the fourth runs standard global attention. Only 18 of the 72 layers therefore hold a KV cache that grows with context.
 | | |
 </div>
 ### Requirements
 ```bash
 pip install "transformers>=5.12" torch torchvision accelerate