Instructions to use tarruda/Rio-3.5-Open-397B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tarruda/Rio-3.5-Open-397B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tarruda/Rio-3.5-Open-397B-GGUF",
	filename="IQ2_XS/Rio-3.5-Open-397B-IQ2_XS-00001-of-00004.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tarruda/Rio-3.5-Open-397B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama cli -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama cli -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
# Run inference directly in the terminal:
./llama-cli -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Use Docker

docker model run hf.co/tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

LM Studio
Jan

vLLM

How to use tarruda/Rio-3.5-Open-397B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tarruda/Rio-3.5-Open-397B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tarruda/Rio-3.5-Open-397B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Ollama
How to use tarruda/Rio-3.5-Open-397B-GGUF with Ollama:
```
ollama run hf.co/tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
```

Unsloth Studio

How to use tarruda/Rio-3.5-Open-397B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tarruda/Rio-3.5-Open-397B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tarruda/Rio-3.5-Open-397B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tarruda/Rio-3.5-Open-397B-GGUF to start chatting

How to use tarruda/Rio-3.5-Open-397B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tarruda/Rio-3.5-Open-397B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use tarruda/Rio-3.5-Open-397B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use tarruda/Rio-3.5-Open-397B-GGUF with Docker Model Runner:
```
docker model run hf.co/tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS
```

Lemonade

How to use tarruda/Rio-3.5-Open-397B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tarruda/Rio-3.5-Open-397B-GGUF:IQ2_XS

Run and chat with the model

lemonade run user.Rio-3.5-Open-397B-GGUF-IQ2_XS

List all available models

lemonade list

Intro

Rio 3.5 Open 397B is a merge of Nex-N2-Pro and Qwen3.5-397B-A17B. In a public discussion, Nex-AGI reports that the released Rio weights are approximately an element-wise 0.6 x Nex-N2-Pro + 0.4 x Qwen3.5-397B-A17B blend. I haven't verified this myself, but the report can be found here:

https://github.com/nex-agi/Nex-N2/issues/4#issuecomment-4702181710

Nex-N2-Pro is itself built on Qwen3.5-397B-A17B. Because attribution around Rio has been confusing, this quant explicitly credits both Nex-AGI and Qwen.

License metadata is set to Apache-2.0 to match the named upstream components: Qwen3.5-397B-A17B and Nex-N2-Pro are both listed as Apache-2.0 on Hugging Face.

The chat template from Rio had misleading information about the model training, so I replaced it with the original one from Qwen 3.5 397B.

Recipes

There are two quants in this repo:

A 2.46 BPW IQ2_XS GGUF which uses @ubergarm's smol-IQ2_XS mainline recipe,
A 2.54 BPW IQ3_XXS GGUF which uses the my same Qwen 397B recipe

The imatrix.gguf file was copied from bartowski's GGUF repo.

Why

Despite all the confusing information presented by the team behind Rio, they created a good model that has become one of my favorite local coding assistants.

Some people dismiss this model because of its inferior benchmark numbers compared to N2, but I found that it improves on N2 Pro in some ways. This is anecdotal, but it is my experience:

Mixed reasoning style. It normally has N2's "caveman" reasoning style, but it seems to think less while producing similar results.
At the same time, it sometimes uses Qwen's style, which can be good for some non-coding tasks.
It doesn't get stuck in reasoning loops.

Running

This is the script I use to run it locally:

#!/bin/sh -e

reasoning_budget_message=". Need answer.
Let's draft final."

llama-server --no-warmup --no-mmap \
  --model IQ2_XS/Rio-3.5-Open-397B-IQ2_XS-00001-of-00004.gguf \
  --mmproj Rio-3.5-Open-397B-mmproj-F16.gguf \
  --chat-template-kwargs '{"enable_thinking": true}' \
  --ctx-size 262144 -np 1 \
  --temp 1.0 --top-p 0.95 --top-k 20 \
  --reasoning-budget-message "$reasoning_budget_message"

Credits

Qwen team for the excellent Qwen3.5-397B-A17B foundation
Nex-AGI for building on top of it with Nex-N2-Pro
Prefeitura do Rio / IplanRIO for publishing Rio-3.5-Open-397B
Nex-AGI / 00INDEX for the public Rio merge-ratio analysis
@ubergarm for the smol-IQ2_XS recipe
@bartowski for the Rio 3.5 GGUF imatrix

Downloads last month: 892

GGUF

Model size

396B params

Architecture

qwen35moe

Hardware compatibility

2-bit

3-bit

View +1 variant

Model tree for tarruda/Rio-3.5-Open-397B-GGUF

Base model

Qwen/Qwen3.5-397B-A17B

Finetuned

prefeitura-rio/Rio-3.5-Open-397B

Quantized

(4)

this model