Chinese models US hosted & Private
There is a method of using Chinese models like: Qwen, MiniMax, Zai, Moonshot, etc. That are hosted in the US on the latest NVIDIA B300 datacenter GPUs, where your data stays private and is never trained on.
This is where Ollama, the self hosted go to source for local models comes in. Ollama offers a selection of cloud based models. Simply append your model call with :cloud
What's your favorite model?
Moonshot AI (Kimi): kimi-k2.7-code:cloud (latest coding/agentic), kimi-k2.6:cloud, kimi-k2.5:cloud
MiniMax: minimax-m3:cloud (latest frontier coding/agentic), minimax-m2.7:cloud, minimax-m2.5:cloud, minimax-m2.1:cloud
Z.ai (GLM / Zhipu): glm-5.1:cloud (latest agentic/coding flagship), glm-5:cloud, glm-4.7:cloud
Alibaba (Qwen): qwen3.5:cloud (latest multimodal family), qwen3-coder-next:cloud
DeepSeek: deepseek-v4-pro:cloud (latest frontier MoE), deepseek-v4-flash:cloud
4 votes
9
18 comments
David Vogel
7
Chinese models US hosted & Private
Clief Notes
skool.com/cliefnotes
What we give away free beats most paid courses. Build durable AI systems with a Marine vet and Edinburgh researcher. 40+ lessons, growing.
Leaderboard (30-day)
Powered by