Ripple-65B Preview is an open-weight, 65B-parameter model from Ricursive for general-purpose, coding, and agentic workloads. It is a general-purpose variant of the proprietary model powering the Ricursive AI chip design platform, pretrained on 12 trillion tokens. Ricursive reports a score of 80.52 on TerminalBench 2.1. Checkpoint context length: up to 1M tokens; currently validated Fireworks shape: 128K tokens. Input: text. Output: text. License: Apache 2.0.
On-demand deployments allow you to use Ripple-65B Preview on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.