Event ·Official first-hand

AWS SageMaker AI评测小型LLM推理性能

AWS在SageMaker AI上评测了Qwen3-Coder-30B和NVIDIA Nemotron-3-Nano-30B两个30B专家混合模型。测试对比了G5、G6、G6e和G7 GPU实例的吞吐量、延迟和每token成本。G7搭载的NVIDIA Blackwell GPU在实时LLM推理中展现出明显的价格性能优势。

Current read

AWS实测了两种30B模型在四种GPU上的表现，帮你算清楚哪种实例性价比最高。

7 sources58° AI heatLast updated 2026/9/8 16:21:57

Evidence

7 sources

Primary sourceAWS Machine Learning Blog

2026/9/8 16:21:57View source

Related source 1Aravind Srinivas

2026/9/8 17:10:38View source

Related source 2NVIDIA AI

2026/9/8 11:00:07View source

Related source 3IT之家

2026/9/10 00:10:48View source

Related source 4Gary Marcus

2026/9/7 17:09:04View source

Related source 5Tech in Asia

2026/9/10 05:10:34View source

Related source 6Decoder

2026/9/10 12:23:16View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story