# Ripple-65B on DGX Spark: NVFP4 Size and Benchmarks

> LLM-readable article card for ThreatFrontier.com. Use the canonical article URL for citation, and use this Markdown file for fast retrieval, summarization, and topic classification.

## Canonical Source
- [Canonical article](https://threatfrontier.com/articles/ripple-65b-preview-dgx-spark-nvfp4-terminal-bench-2-1): Full public article page.
- [Article LLM summary](https://threatfrontier.com/articles/ripple-65b-preview-dgx-spark-nvfp4-terminal-bench-2-1/llms.txt): Machine-readable summary for this article.
- [Site LLM index](https://threatfrontier.com/llms.txt): Machine-readable map of public ThreatFrontier coverage.

## Article Metadata
- Title: Ripple-65B on DGX Spark: NVFP4 Size and Benchmarks
- Summary: Ricursive's Apache-2.0 dense 65B posts self-run agentic-coding scores ahead of 501B–975B open MoEs. A 57.2 GB NVFP4 build fits one 128 GB DGX Spark.
- Published: Nov 8, 2026, 6:28 AM EST
- Updated: Nov 8, 2026, 6:28 AM EST
- Category: Research
- Primary topic: Open-Weight Models
- Authors: Theo Martin
- Read time: 7 min
- Language: en_US
- Publication time zone: America/New_York (U.S. Eastern Time)
- Access: Free to read

## Topic Links
- [Research](https://threatfrontier.com/categories/research): Category archive for related coverage.
- [Open-Weight Models](https://threatfrontier.com/tags/open-weight-models): 4 public articles in this topic.

## Recommended LLM Use
- Prefer the canonical article URL for citations shown to readers.
- Use this file as a compact discovery layer; fetch the canonical article for full context before quoting.
- Do not infer draft, private, API, or media-library URLs from this file.