Instructions to use arcee-ai/Trinity-Large-Thinking-W4A16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/Trinity-Large-Thinking-W4A16 with Transformers:

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

pipe = pipeline("text-generation", model="arcee-ai/Trinity-Large-Thinking-W4A16", 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("arcee-ai/Trinity-Large-Thinking-W4A16", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("arcee-ai/Trinity-Large-Thinking-W4A16", 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 arcee-ai/Trinity-Large-Thinking-W4A16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arcee-ai/Trinity-Large-Thinking-W4A16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arcee-ai/Trinity-Large-Thinking-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arcee-ai/Trinity-Large-Thinking-W4A16

SGLang

How to use arcee-ai/Trinity-Large-Thinking-W4A16 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 "arcee-ai/Trinity-Large-Thinking-W4A16" \
    --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": "arcee-ai/Trinity-Large-Thinking-W4A16",
		"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 "arcee-ai/Trinity-Large-Thinking-W4A16" \
        --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": "arcee-ai/Trinity-Large-Thinking-W4A16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arcee-ai/Trinity-Large-Thinking-W4A16 with Docker Model Runner:
```
docker model run hf.co/arcee-ai/Trinity-Large-Thinking-W4A16
```

Trinity-Large-Thinking-W4A16

Introduction

Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token, post-trained with extended chain-of-thought reasoning and agentic RL.

This repository contains the W4A16 quantized weights of Trinity-Large-Thinking (INT4 weights, 16-bit activations).

For full model details, benchmarks, and usage guidance, see the main Trinity-Large-Thinking model card.

Quantization Details

Scheme: W4A16 (INT4 weights, 16-bit activations)
Intended use: Quality-preserving 4-bit deployment of Trinity-Large-Thinking

Usage

Inference tested on

8x NVIDIA H100 80GB (tensor parallel = 8)
vLLM 0.15.1+

vLLM

Supported in vLLM 0.15.1+.

vllm serve arcee-ai/Trinity-Large-Thinking-W4A16 \
  --trust-remote-code \
  --tensor-parallel-size 8 \
  --enable-reasoning \
  --reasoning-parser deepseek_r1 \
  --enable-auto-tool-choice \
  --tool-call-parser qwen3_coder

Transformers

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "arcee-ai/Trinity-Large-Thinking-W4A16"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    trust_remote_code=True
)

messages = [{"role": "user", "content": "Who are you?"}]

input_ids = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

outputs = model.generate(input_ids, max_new_tokens=4096, do_sample=True, temperature=0.6, top_k=50, top_p=0.95)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

API

Works out of the box on OpenRouter as arcee-ai/trinity-large-thinking.

License

Trinity-Large-Thinking-W4A16 is released under the Apache License, Version 2.0.

Citation

If you use this model, please cite:

@misc{singh2026arceetrinity,
  title        = {Arcee Trinity Large Technical Report},
  author       = {Varun Singh and Lucas Krauss and Sami Jaghouar and Matej Sirovatka and Charles Goddard and Fares Obied and Jack Min Ong and Jannik Straube and Fern and Aria Harley and Conner Stewart and Colin Kealty and Maziyar Panahi and Simon Kirsten and Anushka Deshpande and Anneketh Vij and Arthur Bresnu and Pranav Veldurthi and Raghav Ravishankar and Hardik Bishnoi and DatologyAI Team and Arcee AI Team and Prime Intellect Team and Mark McQuade and Johannes Hagemann and Lucas Atkins},
  year         = {2026},
  eprint       = {2602.17004},
  archivePrefix= {arXiv},
  primaryClass = {cs.LG},
  doi          = {10.48550/arXiv.2602.17004},
  url          = {https://arxiv.org/abs/2602.17004}
}