ricursiveAI/Ripple-65B-Preview

Ricursive's Ripple-65B Preview, a dense 65B model for reasoning and agentic coding with hybrid sliding-window and NoPE full attention, tool calling, and a DFlash2 speculative drafter.

View on HuggingFace

dense65B2,097,152 ctxvLLM 0.33.0+text

Default configuration: 8× B300 · Tensor Parallel · NVFP4

vllm serve ricursiveAI/Ripple-65B-Preview-NVFP4 \
  --tensor-parallel-size 1 \
  --reasoning-parser ripple \
  --enable-auto-tool-choice \
  --tool-call-parser ripple

The interactive builder loads with JavaScript. Append .md to this page's URL, query string included, for any configuration's command as Markdown — e.g. /ricursiveAI/Ripple-65B-Preview.md.

Guide

Overview

Ripple-65B Preview is a dense 65B model from Ricursive Intelligence. Its 80 layers alternate four 1024-token sliding-window layers with one NoPE full-attention layer, and it supports a 2M-token context. The NVFP4 checkpoint fits on one B200/B300.

Ripple decides per turn whether to reason, so reasoning_content is empty when it answers directly.

Client usage

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ricursiveAI/Ripple-65B-Preview-NVFP4",
    "messages": [{"role": "user", "content": "Write a Python function that reverses a linked list."}]
  }'

Overview

Client usage

References