AITOPAI热报
ModelsSelected

Smaug-Nemotron-3.5 released as open-source model for single-machine agents

Bindu Reddy@bindureddy
Post
View the post
Why we picked it

Local hardware requirements are the practical headline: one DGX Spark, H200 or GB200 means teams can keep agentic coding inside their own infrastructure instead of paying API costs. Builders running open-source agent stacks should compare it against Chinese open models like DeepSeek on agentic coding benchmarks before choosing a default.

Smaug-Nemotron-3.5 builds on Nvidia's latest open-source model and is available now on HuggingFace. The model is optimised for agentic coding and improves on Deep-SWE. It can run on a single machine, with support for one DGX Spark, one H200 or one GB200. The team positions it as the strongest US open-source model for local agent workloads.

Original · Bindu Reddy

🚨 Announcing Smaug-Nemotron-3.5 - The Best US Open-Source LLM That Can Run On Your Desktop

We are super excited to push the boundaries of US open-source.

Smaug-Nemotron improves on Nvidia's latest model that literally runs on a single machine; all you need is one DGX Spark, one H200, or one GB200!

The Smaug variant is optimized for agentic coding, improves Deep-SWE, and enables local agents.

It's the best US agentic open-source model that can run on a single machine. Weights are now available on HuggingFace

#Smaug-Nemotron#Nvidia#open-source models#agents#coding assistants

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected11:25
MiniMax M3.1 Flash Runs in Production on vLLM

Production-grade serving of a MiniMax model through vLLM signals that the open-source inference stack can now carry commercial workloads with SLA guarantees. Teams evaluating cheaper open-weight serving options can look at Inferact's vLLM-based offering as a reference setup. Upstream contributions also mean the wider vLLM community inherits the reliability hardening that came out of this deployment.

#MiniMax#vLLM#open-source models#inference
官方账号vLLM@vllm_projectSource
ModelsBuildersSelected11:15
Ant open-sources Ling-3.0-flash-Sante medical AI model

The benchmark mix matters: it beats larger frontier models on diagnosis-style multiple-choice tasks while staying slightly behind on expert-level text reasoning, so it is a specialist rather than a general replacement. Developers and medical researchers can self-deploy and fine-tune it for literature research, clinical guideline retrieval, drug fact-checking and evidence curation apps. As an open-weight 124B MoE model, it lowers the cost barrier for healthcare AI teams in ASEAN and Chinese-speaking markets.

#Ling-3.0-flash-Sante#Ant Group#open-source models#agents
AIGCLINK@aigclinkSource