小米发布MiMo-V2.5-Pro-FP4-DFlash以实现高效AI推理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-08 04:32

小米发布了MiMo-V2.5-Pro-FP4-DFlash，这是一款为高效推理而优化的新模型。它采用了专家级FP4量化，以减小内存占用和带宽压力，同时保持质量。该模型还集成了BF16 DFlash草稿器，用于推测性解码，通过每次前向传播提出token块来实现更快的token生成。 AI

影响能够更高效地部署大型语言模型，可能降低推理成本并提高可访问性。

排序理由知名科技公司发布模型。 [lever_c_demoted from frontier_release: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

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: Significant; 知名科技公司发布模型。 [lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, product, 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: 114 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。

Hugging Face Trending Models TIER_1 Português(PT) · XiaomiMiMo · 2026-06-08 04:32

XiaomiMiMo/MiMo-V2.5-Pro-FP4-DFlash

text-generation · 48 downloads · 57 likes