PulseAugur
中
实时 06:50:08
English(EN) NVIDIA has released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B that runs in roughly 4GB of VRAM on RTX, Jetson and DG

NVIDIA发布Nemotron 3.5 Bolt E4B,要求4GB显存

NVIDIA推出了Nemotron 3.5 Bolt E4B,这是一个源自Gemma 4 E4B的开源小型语言模型。该模型设计用于在最小的显存下运行,大约需要4GB,使其适用于RTX、Jetson和DGX Spark等硬件设备。Nemotron 3.5 Bolt E4B具有增强的功能,包括多轮工具调用、64k上下文窗口以及对35种语言的支持,所有这些都在OpenMDW许可下,有效参数量为4B。 AI

影响 通过低显存要求实现设备端AI应用,可能扩大先进语言模型的覆盖范围。

排序理由 NVIDIA发布了带有系统卡的Frontier-lab模型。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 Mastodon — fosstodon.org 阅读 →

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

NVIDIA发布Nemotron 3.5 Bolt E4B,要求4GB显存

本文如何被排名

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
NVIDIA发布了带有系统卡的Frontier-lab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, 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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

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

    NVIDIA 发布 Nemotron 3.5 Bolt E4B 4GB,一款开源小型语言模型,基于 Gemma 4 E4B 进行后训练,可在 RTX、Jetson 和 DG 的约 4GB 显存中运行

    NVIDIA has released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B that runs in roughly 4GB of VRAM on RTX, Jetson and DGX Spark hardware. It adds multi-turn tool calling, a 64k context window and support for 35 languages, with 8B total para…