Ollama's cloud is updated to use NVIDIA's latest data center hardware: B300 for Kimi K2.5 and GLM-5 models. This significantly improves the model performance with faster throughput and lower latency while maintaining reliable tool calls for integrations.
All this works with Ollama's integrations via Ollama's launch command and over 45,000 custom integrations from GitHub.
32 Replies
26 Retweets
430 Likes
21.5K Views 
One Sentence Summary
Ollama upgrades its cloud infrastructure with NVIDIA B300 hardware to boost performance for Kimi K2.5 and GLM-5 models.
Summary
Ollama has announced a significant infrastructure upgrade to its cloud service, now utilizing NVIDIA's latest B300 data center hardware. This update specifically targets Kimi K2.5 and GLM-5 models, promising higher throughput and lower latency. The upgrade maintains full compatibility with Ollama's extensive ecosystem of over 45,000 integrations and its standard launch commands.
AI Score
84
Influence Score 77
Published At Today
Language
English
Tags
Ollama
NVIDIA B300
Kimi K2.5
GLM-5
AI Infrastructure