英伟达发布Nemotron 3.5 Bolt E4B 4GB：一款适用于本地语音助手、游戏角色和机器人的开源小型语言模型

NVIDIA 发布了 Nemotron 3.5 Bolt E4B 4GB，这是一款基于 Gemma 4 E4B 进行后训练的开源小型语言模型，适用于本地语音助手、游戏角色和机器人，目标是在 RTX 和 Jetson 平台上占用约 4GB 的显存。文章《NVIDIA 发布 Nemotron 3.5 Bolt E4B 4GB：一款面向本地语音助手、游戏角色和机器人的开源小型语言模型》首发于 MarkTechPost。

NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots

NVIDIA released Nemotron 3.5 Bolt E4B 4GB, an open small language model post-trained from Gemma 4 E4B for local voice assistants, game characters and robots, targeting about 4GB of VRAM on RTX and Jetson. The post NVIDIA Releases Nemotron 3.5 Bolt E4B 4GB: An Open Small Language Model for Local Voice Agents, Game Characters and Robots appeared first on MarkTechPost.

资料来源

MarkTechPost