Instructions to use inclusionAI/Ring-2.6-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/Ring-2.6-1T with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/Ring-2.6-1T", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("inclusionAI/Ring-2.6-1T", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use inclusionAI/Ring-2.6-1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "inclusionAI/Ring-2.6-1T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "inclusionAI/Ring-2.6-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/inclusionAI/Ring-2.6-1T

SGLang

How to use inclusionAI/Ring-2.6-1T 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 "inclusionAI/Ring-2.6-1T" \
    --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": "inclusionAI/Ring-2.6-1T",
		"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 "inclusionAI/Ring-2.6-1T" \
        --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": "inclusionAI/Ring-2.6-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/Ring-2.6-1T with Docker Model Runner:
```
docker model run hf.co/inclusionAI/Ring-2.6-1T
```

Ring Mini / Ring Flash (either Linear or Sparse models)?

by TomLucidor - opened May 14

Discussion

TomLucidor

May 14

Could we get local models that are a distill of the 1T so that at least it can be somewhat smart? https://huggingface.co/inclusionAI/Ring-2.5-1T/discussions/6

RichardBian

inclusionAI org May 21

Thanks for the feedback @TomLucidor , at this moment we have no plan to update the ring mini/flash model. Do you have a specific use case that we could learn more and help with?

TomLucidor

May 22

•

edited May 22

Local usage with portable machines are the general case (vs Gemma 4 and Qwen 3.5).

aquiffoo

12 days ago

i expect them to update mini, flash and 1T gradually in V3.

and V3 could also unify Ling and Ring into a single hybrid reasoning series.

Ling-3.0-mini (21B A2B, non-thinking, high, xhigh)
Ling-3.0-flash (130B A10B, non-thinking, high, xhigh)
Ling-3.0-1T (1.1T 43B, non-thinking, high, xhigh)

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