Instructions to use tngtech/DeepSeek-R1T-Chimera with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tngtech/DeepSeek-R1T-Chimera with Transformers:

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

pipe = pipeline("text-generation", model="tngtech/DeepSeek-R1T-Chimera", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tngtech/DeepSeek-R1T-Chimera", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("tngtech/DeepSeek-R1T-Chimera", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tngtech/DeepSeek-R1T-Chimera with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tngtech/DeepSeek-R1T-Chimera"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tngtech/DeepSeek-R1T-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tngtech/DeepSeek-R1T-Chimera

SGLang

How to use tngtech/DeepSeek-R1T-Chimera 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 "tngtech/DeepSeek-R1T-Chimera" \
    --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": "tngtech/DeepSeek-R1T-Chimera",
		"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 "tngtech/DeepSeek-R1T-Chimera" \
        --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": "tngtech/DeepSeek-R1T-Chimera",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tngtech/DeepSeek-R1T-Chimera with Docker Model Runner:
```
docker model run hf.co/tngtech/DeepSeek-R1T-Chimera
```

This model is the best for writing, period

by Gobleteer - opened Jun 21, 2025

Discussion

Gobleteer

Jun 21, 2025

I don't know where to write how much I like this model. I tried it on openrouter and it was the best at following complex writing prompts. I'll miss it now that isn't up on openrouter.

Gobleteer

Jun 21, 2025

For added context I gave the same prompt to every single model on openrouter and this model preformed the best

TNGHK

TNG Technology Consulting GmbH org Jun 21, 2025

•

edited Jun 21, 2025

Thanks for your kind words! The model appears to be still up on the chutes.ai backends and seems to process about 2.5B tokens/day there.

At this moment, we don't know why it isn't up on OpenRouter. The Chimera was processing 900M to 1B tokens/day there during the last week, except when OR had its outages, which affected several models.

TNGHK

TNG Technology Consulting GmbH org Jun 21, 2025

Update: It seems to be back and working again at OpenRouter.

Gobleteer

Jul 2, 2025

It works again! Also, I would be willing to pay tokens for running the model if that means it's more sustainble to have it kept running

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