# How to run Ripple-65B Preview: OpenRouter, Hugging Face, DGX Spark

> Three ways to use Ricursive's open-weight coding model, with the OpenRouter call, prices and the license.

URL: https://claudegpt.si/news/how-to-run-ripple-65b-preview  
Published: 2026-11-05T02:53:12.523Z  
Author: ClaudeGPT Si Newsroom  
Section: Guides  
Topics: Ricursive Intelligence, Ripple, Open-weight models, OpenRouter, How to  
Publisher: ClaudeGPT Si

## Key takeaways

- OpenRouter serves ricursiveai/ripple-65b-preview through GMI Cloud at $0.20 per million input tokens and $0.60 per million output tokens as of November 5, 2026.
- The weights are Apache 2.0 on Hugging Face, with an NVFP4 checkpoint for smaller machines.
- The repository uses custom code, and no Hugging Face inference provider hosts it yet.

You can run Ripple-65B Preview three ways: call it through OpenRouter, download the weights from Hugging Face, or load the smaller NVFP4 checkpoint on a machine like the NVIDIA DGX Spark. The model is the 65B open-weight coding model that Ricursive Intelligence [released on November 4](https://www.ricursive.com/ripple), and our [news article](https://claudegpt.si/news/ripple-65b-preview-open-weight) covers what it is. This guide covers how to use it.

None of the commands below were run for this article. They come from the OpenRouter and Hugging Face pages as read on November 5, 2026, so check the pages if something fails.

## Option 1: Call Ripple-65B Preview through OpenRouter

This is the quickest route, with no hardware needed. [OpenRouter's model page](https://openrouter.ai/ricursiveai/ripple-65b-preview) lists the model id `ricursiveai/ripple-65b-preview`, served by GMI Cloud, through the standard chat completions endpoint.

1. Create an OpenRouter account and an API key.
2. Send a request to `https://openrouter.ai/api/v1/chat/completions` with the model id above.

```bash
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ricursiveai/ripple-65b-preview",
    "messages": [{"role": "user", "content": "Write a Python function that parses ISO dates."}]
  }'
```

Streaming works, and the page lists support for tools, `tool_choice`, `response_format`, `seed`, `temperature`, `top_p` and `logprobs`. As of November 5, 2026, the price is $0.20 per million input tokens and $0.60 per million output tokens, with no markup from OpenRouter. GMI Cloud is the only provider named, and EU in-region routing is not available for this model.

## Option 2: Download the weights from Hugging Face

The [model card](https://huggingface.co/ricursiveAI/Ripple-65B-Preview) says the weights are BF16 Safetensors under the Apache 2.0 license, so you can use them commercially. The repository also has an NVFP4 checkpoint, a base model and a DFlash2 variant. Two cautions from the card:

- The repository is tagged `custom_code`, so loading it may require trusting remote code in your inference library.
- No Hugging Face inference provider currently hosts it.

## Option 3: Run it locally

Ricursive says the model is small enough to run on an NVIDIA DGX Spark, and the card points to an NVFP4 checkpoint and a Colab notebook for getting started. The card gives no minimum hardware requirements. Its speed figure, 250 tokens per second, is for two B200 GPUs at batch size 8, which is far more than a desktop machine.

## Which option to pick

| Option | Needs | Cost | Good for |
| --- | --- | --- | --- |
| OpenRouter | API key | $0.20 in, $0.60 out per 1M tokens | Trying it on real tasks today |
| Hugging Face BF16 | Server-class GPUs (no minimum stated) | Your hardware | Serving at scale |
| NVFP4 locally | DGX Spark class machine | Your hardware | Private, offline use |

## Limits to know before you rely on it

This is a preview with light post-training, aimed at agentic coding, and its training data is mostly English. Its 80.5 on Terminal-Bench 2.1 is the lab's own number, and the authors say scores are lower under the official Terminus 2 harness at 128K context.

## Frequently asked questions

### Is Ripple-65B Preview free?

The weights are free to download under Apache 2.0. Hosted use on OpenRouter costs $0.20 per million input tokens and $0.60 per million output tokens as of November 5, 2026.

### Can Ripple-65B Preview run locally?

Ricursive says it is small enough for an NVIDIA DGX Spark and provides an NVFP4 checkpoint and a Colab notebook. The model card gives no minimum hardware requirements.

### What is the Ripple-65B Preview OpenRouter model id?

The id is ricursiveai/ripple-65b-preview, served by GMI Cloud through the chat completions endpoint.

### What license is Ripple-65B Preview under?

The Hugging Face model card lists Apache 2.0.

## Sources

- [Ripple-65B Preview](https://www.ricursive.com/ripple), Ricursive Intelligence
- [ricursiveAI/Ripple-65B-Preview](https://huggingface.co/ricursiveAI/Ripple-65B-Preview), Hugging Face
- [Ripple-65B Preview on OpenRouter](https://openrouter.ai/ricursiveai/ripple-65b-preview), OpenRouter