PulseAugur
中
实时 14:15:20
English(EN) RT @chenzeling4: 744B parameters. On a laptop. With 25GB RAM. Colibri runs GLM-5.2 (744B MoE) in pure C with zero dependencies. The trick: only ~40B params acti

Colibri 语言模型在 25GB RAM 的笔记本电脑上运行 744B 参数

一款名为 Colibri 的新语言模型,基于 GLM-5.2,已被开发出来,仅需 25GB RAM 即可在笔记本电脑上运行。该模型拥有 7440 亿参数,采用混合专家(MoE)架构,通过每次仅激活约 400 亿参数来实现效率。该实现使用纯 C 语言编写,没有任何外部依赖,使其高度易于访问。 AI

影响 这一发展可能显著降低运行大型语言模型的门槛,从而在消费级硬件上实现更广泛的实验和部署。

排序理由 该集群描述了一个新模型发布,其中包含有关其架构和资源要求的技术细节。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Colibri 语言模型在 25GB RAM 的笔记本电脑上运行 744B 参数

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一个新模型发布,其中包含有关其架构和资源要求的技术细节。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
88 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    RT @chenzeling4: 7440亿参数。在笔记本电脑上。配备25GB内存。Colibri以纯C语言运行GLM-5.2 (744B MoE),零依赖。诀窍是:仅约400亿参数激活

    RT @chenzeling4: 744B parameters. On a laptop. With 25GB RAM. Colibri runs GLM-5.2 (744B MoE) in pure C with zero dependencies. The trick: only ~40B params activate per token, so it keeps the dense part resident and streams experts from disk on demand. A single 2,400-line C file.…

  2. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    RT @chenzeling4: 7440亿参数。在笔记本电脑上。配备25GB内存。Colibri纯C语言运行GLM-5.2(744B MoE),零依赖。诀窍是:仅约400亿参数激活

    RT @chenzeling4: 744B parameters. On a laptop. With 25GB RAM. Colibri runs GLM-5.2 (744B MoE) in pure C with zero dependencies. The trick: only ~40B params activate per token, so it keeps the dense part resident and streams experts from disk on demand. A single 2,400-line C file.…