Blog ·

Ripple-65B online: try Ricursive's open coding model without a 40 GB GPU

Ripple-65B Preview is a new Apache-2.0 dense model for agentic coding that scores 80.5 on Terminal-Bench 2.1. What it is, its benchmarks, how to try it in your browser and how to run it locally.

On 4 November a small lab called Ricursive Intelligence released Ripple-65B Preview: a dense 65-billion-parameter model trained from scratch on 12 trillion tokens, post-trained for agentic coding, and published under Apache-2.0. Its headline number, 80.5 on Terminal-Bench 2.1, is ahead of open mixture-of-experts models with ten times more parameters. Running it yourself takes a GPU with 40 GB or more, so we host it: you can try it in your browser.

Ripple-65B PreviewRicursive Intelligence · Apache-2.0A new 65B dense model trained from scratch for agentic coding: 80.5 on Terminal-Bench 2.1, ahead of open models ten times its size.Try it online →

What Ripple-65B is

  • 65B dense (not mixture-of-experts): every token uses all the weights, which makes it simple to serve and quantize.
  • Thin and deep: 80 layers with a narrow 5,120 width, mostly sliding-window attention with a few global layers, in a Gemma-3n-like design.
  • Long context: trained up to 1M tokens (on LiveWeights each chat uses a 16K window).
  • Reasoning model: on harder questions it thinks before answering. On LiveWeights you can open its reasoning under each answer.
  • Built by a team of five, starting from the open Olmo 3 recipe.

Benchmarks, as reported by Ricursive

BenchmarkRipple-65B Preview
Terminal-Bench 2.180.5
SWE-bench Verified76.5
SWE-bench Pro v2.0 Hard79.1
GPQA Diamond85.2
AIME 202598.3
MMLU-Pro84.2

These are the lab's own numbers at full BF16 precision. It is a "Preview", with light post-training focused on coding: expect it to be strongest on code, terminal tasks and reasoning, and weaker on general knowledge than much bigger models.

How to try it online

  1. Open the Ripple-65B page and sign in, then pick a small credit pack (no subscription).
  2. Ask a coding question, paste a bug or ask for a script.
  3. The first message after a pause needs about 40 seconds to load the model on our 96 GB GPU; after that it writes about 34 tokens per second.

We run a 4.6-bit GGUF build with llama.cpp, which added Ripple's architecture on 5 November. Quality is close to the original, but not identical: for benchmarking, use the official BF16 weights.

Run it locally

You need about 40 GB of GPU memory (or unified memory on a Mac or a DGX Spark) for a 4-bit build. Options: the official NVFP4 checkpoint for NVIDIA Blackwell, GGUF builds for llama.cpp (use a release from 6 November 2026 or later, and a GGUF converted after the merge), or MLX builds for Apple Silicon. For other new open chat models, see this week's roundup.

LiveWeights is not affiliated with the model authors or with the AI Search channel. Facts come from the official pages linked on each model page.