DiscoverThe Arm PodcastArm Viewpoints: Small language models, big ambitions
Arm Viewpoints: Small language models, big ambitions

Arm Viewpoints: Small language models, big ambitions

Update: 2025-04-14
Share

Description

In this episode of the Arm Viewpoints podcast, host Brian Fuller speaks with Julien Simon, Chief Evangelist at Arcee AI, about the evolution of small language models and the significance of CPU-based AI inference. They discuss Arcee AI's journey, the advantages of small models over large ones, the importance of inference, and the innovative techniques like quantization that enable efficient performance. Julian emphasizes the need for businesses to focus on cost performance and the future of AI as a collection of microservices that can be tailored to specific needs.
Comments 
In Channel
loading
00:00
00:00
x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

Arm Viewpoints: Small language models, big ambitions

Arm Viewpoints: Small language models, big ambitions

Arm