AITOPAI热报
Products

Ripple 65-B Preview 上架 Ollama：面向智能体编程，支持 1M 上下文

ollama@ollama
Post
View the post
Why we picked it

想在本地跑编程智能体的可以试试，Ripple 65-B 上了 Ollama，1M 上下文能塞下整个代码库，数据完全不外传。比起把代码扔给云端模型，对隐私要求高的团队多了一个选择。

RicursiveAI 的 Ripple 65-B Preview 模型已上架 Ollama，开发者可以在本地直接运行。该模型定位于 agentic coding（智能体编程）场景，支持最高 1M token 的上下文窗口。

Body

通过 Ollama 本地运行意味着数据全程不离开本机，实现零数据保留（zero data retention）。对于需要处理大型代码库、长文件链路的编程智能体任务，1M 上下文让模型能一次性读入更多项目代码。

对关注代码隐私的企业开发者和想在本地搭建编程智能体的个人开发者来说，这是一个新的开源本地选项，可以与 Claude Code、Qwen-Coder 等云端或开源方案比较后再做选择。

Original · ollama

Ripple 65-B Preview from @RicursiveAI is on Ollama. Built for agentic coding, with up to 1M tokens of context. Run it locally with full zero data retention.📊 12 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Ollama, Ripple 65-B, RicursiveAI, 编程助手.

Source attribution: curated from ollama (@ollama).

#Ollama#Ripple 65-B#RicursiveAI#编程助手#开源模型

Keep reading

Recent stories with the same tag or section
ProductsBuildersMulti-sourceSelected11:06
Market Map Tracks 119 Companies Across On-Device AI Stack

The valuation split is the interesting part: money flows to small-model startups rather than chip vendors, signalling that software layers of edge AI are capturing value first. Builders choosing between Ollama, llama.cpp and LM Studio, or comparing NPU specs like Snapdragon X2's 80 TOPS, get a single reference for the whole stack. The map also shows Chinese phone makers running on-device models alongside Apple Intelligence and Galaxy AI.

#on-device AI#edge AI#Mistral#Ollama
Event
AI Will@FinanceYF5Source
ModelsUS vs ChinaSelected01:22
Kimi K3.1 Pro rolls out on Ollama Cloud with zero data retention

The zero-data-retention and US-hosting terms matter for teams that couldn't previously route sensitive workloads to a Chinese open-weight model. Developers can now self-host or run K3.1 Pro through Ollama Cloud as an alternative to renting closed APIs from OpenAI or Anthropic. Weight availability on Hugging Face also means inference providers beyond Ollama can deploy it.

#Kimi K3.1 Pro#Moonshot#Ollama#open-source models
ollama@ollamaSource