🚨 AI News | TestingCatalog· @testingcatalog · X·· 3 小时前AI 评分57
AI 导读
Recursive 发布首个开源权重编码模型 Flint，采用 Apache 2.0 协议。Flint 是 40B 参数的 MoE 本地编码模型，号称比同类模型快 2 倍，在 64GB RTX Spark 上超过 220 tokens/秒，在 MacBook Pro 上达 125+ tokens/秒。其 Eureka Machine 自动研究系统通过编写自定义 GPU 代码，在不改权重的情况下将 Flint 在 RTX Spark 上提速 55%，权重已在 Hugging Face 开放。
正文 · 原文
Recursive has released Flint, its first open-weight coding model under the Apache 2.0 license, which is 2x faster than comparable alternatives.
Flint is a 40B parameter mixture-of-experts model for local coding.
Recursive reports achieving more than 220 tokens per second on a 64GB RTX Spark.
Recursive's Eureka Machine, a system for running AI research experiments, wrote custom GPU code that sped Flint up by 55% on RTX Spark without changing the weights.
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. • Best-in-class fast local coding • Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark • Built from scratch in under 4 months Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.在 X 查看被引用的帖子
来源：🚨 AI News | TestingCatalog · x.com