Products10月26日 01:12

Microduck 机器人接入本地模型，Mac 上实现可中断的任务规划

@atomic_chat_hq@atomic_chat_hq

Post

Why we picked it

有人在 Mac 上用本地跑的 Nemotron 3.5 Bolt E4B 控制 Microduck 机器人，请求变成工具调用，中途打断它还会改计划，本地就能跑机器人智能体。

Atomic Chat 演示了用本地模型控制虚拟 Microduck 机器人。他们接入了 Nemotron 3.5 Bolt E4B 模型，运行在 Mac 上。模型把用户请求转换成工具调用，驱动机器人执行动作。任务执行中途被用户打断时，模型会改变原定计划。

Original · @atomic_chat_hq

Microduck controlled with a local model on a Mac 🦆

We connected a virtual @pollenrobotics Microduck to Nemotron 3.5 Bolt E4B in Atomic Chat that turns requests into tool calls and changes plan when you interrupt it mid-move

Run AI models locally -> https://t.co/RbcCOIgVkj https://t.co/mNWgwhePm9

#Nemotron #Microduck #Atomic Chat #MCP/工具 #本地部署

Keep reading

Recent stories with the same tag or section

Models BuildersOfficial13:13

Chinese contentNVIDIA 发布开源小模型 Nemotron 3.5 Bolt E4B 4GB，面向本地语音与机器人

NVIDIA 出了个 4GB 显存就能跑的开源小模型，从 Gemma 4 E4B 改的，能做本地语音助手和游戏 NPC，家里 RTX 或 Jetson 就能玩。

#NVIDIA #Nemotron #Gemma #开源模型

Event

官方一手marktechpost@Asif Razzaq11 sourcesSource

Products Builders03:52

Chinese contentCline 接入 5 款免费模型：Nemotron 3.5、Poolside Laguna S 2.1 等

Cline 上线了 5 个免费模型，Nemotron 3.5 和 Poolside Laguna S 都能直接用，写代码不用自己掏 API 费了。

#Cline #Nemotron #Poolside #编程助手

Cline@clineSource

Models BuildersMulti-source14:58

Chinese contentNVIDIA 发布面向智能体工作负载的端到端硬件栈

NVIDIA 不只卖卡，还按任务配好了模型家族，Nemotron 后训练后能超过前沿模型，小模型路线挺省钱。

#NVIDIA #Nemotron #智能体 #推理模型

Event

Merve Noyan@mervenoyann11 sourcesSource

Models Builders11:44

Chinese content英伟达开源检索系列模型 Nemotron 3.5 Parse、Embed 与 Rerank

英伟达把检索三件套 Parse、Embed、Rerank 全开源了，扫描 PDF 和图表都能解析，准确率上去了成本还降了 14%，做 RAG 的可以试试。

#Nemotron #英伟达 #RAG #开源模型

Gorden Sun@Gorden_SunSource

Models BuildersMulti-sourceSelected00:13

Scale AI Post-Trains NVIDIA Nemotron 3.5 Super VL

Post-training a smaller open NVIDIA model to match frontier accuracy at 1/40 the inference cost is a concrete signal that domain-specific fine-tuning can undercut flagship APIs for production agent workloads. Teams running high-volume ticket or support agents should benchmark Nemotron 3.5 Super VL against their current frontier model on cost and latency. The Skydance collaboration shows enterprises bringing their own production data to post-training partners.

#NVIDIA #Nemotron #Scale AI #fine-tuning

Event

官方账号Scale AI@scale_AI11 sourcesSource

Products BuildersMulti-sourceSelected00:05

Databricks expands NVIDIA collaboration for open model fine-tuning

The integration compresses the path from raw enterprise data to a served, fine-tuned open model into a single governed platform, cutting out the usual glue work between training stacks and production inference. Teams building domain-specific models on open weights can prototype on serverless NVIDIA GPUs without managing infrastructure. Compared with stitching together separate tooling, the Nemotron cookbooks plus NeMo on Databricks offer a ready-made pipeline to production.

#Databricks #NVIDIA #Nemotron #fine-tuning

Event

官方账号Databricks@databricks11 sourcesSource