Instructions to use metanthropic/arvi-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use metanthropic/arvi-20b with Transformers:

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

pipe = pipeline("text-generation", model="metanthropic/arvi-20b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("metanthropic/arvi-20b")
model = AutoModelForCausalLM.from_pretrained("metanthropic/arvi-20b")
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 metanthropic/arvi-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "metanthropic/arvi-20b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "metanthropic/arvi-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/metanthropic/arvi-20b

SGLang

How to use metanthropic/arvi-20b 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 "metanthropic/arvi-20b" \
    --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": "metanthropic/arvi-20b",
		"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 "metanthropic/arvi-20b" \
        --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": "metanthropic/arvi-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use metanthropic/arvi-20b with Docker Model Runner:
```
docker model run hf.co/metanthropic/arvi-20b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Arvi-20B

Arvi-20B is a foundational reasoning model developed by Metanthropic Research.

Model Card | Website | Citation

🚀 Model Summary

Arvi-20B represents a paradigm shift in efficient intelligence. Built on a specialized Mixture-of-Experts (MoE) architecture, it delivers the knowledge density of a 20-billion parameter system while maintaining the inference speed of a much smaller model.

Designed specifically for complex reasoning protocols, Arvi-20B excels at chain-of-thought generation, agentic tool usage, and high-fidelity instruction following. It serves as the flagship model for Metanthropic's open-weight initiative.

📊 Technical Specifications

Feature	Specification
Developer	Metanthropic Research
Model Architecture	Sparse Mixture-of-Experts (MoE)
Total Parameters	20.9 Billion
Active Parameters	3.6 Billion (per token)
Context Window	128,000 Tokens
Precision	BFloat16 (Native)
License	Apache 2.0

⚡ Capabilities

Deep Reasoning: Native capability to deconstruct complex queries into logical steps before generating a final answer.
Agentic Workflow: Optimized for function calling and tool interaction, allowing integration into autonomous systems.
Efficiency: Activates only ~17% of parameters per token, enabling deployment on standard enterprise hardware without sacrificing intelligence.
Long Context: Capable of ingesting and analyzing massive documents up to 128k tokens in length.

🛠️ Installation & Usage

Arvi-20B utilizes a specialized MoE architecture. To run the model, you must install the required backend kernels and libraries.

1. Install Dependencies

# Install required backend support for Arvi's architecture
pip install gpt-oss transformers peft accelerate torch

2. Python Inference

import torch
import gpt_oss  # Registers the Arvi MoE architecture
from transformers import AutoModelForCausalLM, AutoTokenizer

# 1. Configuration
model_id = "metanthropic/arvi-20b"

print(f"🚀 Loading {model_id}...")

# 2. Load Model
# We recommend BFloat16 for the best balance of speed and precision
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,  # Required for Arvi architecture
    device_map="auto"
)

# 3. Load Tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)

# 4. Generate
prompt = "Explain the grandfather paradox and potential resolutions."
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(
        **inputs, 
        max_new_tokens=256, 
        temperature=0.7,
        do_sample=True
    )

print(tokenizer.batch_decode(outputs, skip_special_tokens=True)[0])

📜 License & Citation

Arvi-20B is released under the Apache 2.0 license, allowing for broad commercial use, modification, and redistribution.

If you utilize this model in your research or products, please cite Metanthropic Research:

@misc{arvi2025,
      title={Arvi-20B: High-Efficiency Reasoning Model}, 
      author={Metanthropic, Ekjot Singh},
      year={2025},
      publisher={Hugging Face}
}

Downloads last month: 9

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for metanthropic/arvi-20b

Quantizations

2 models