GLM-5.2 is now faster on Ollama's cloud hosted in US & Europe

ollama.com/library/glm-5.2

GLM-5.2 on Ollama's cloud is now accelerated by additional NVIDIA Blackwell capacity in the US & Europe, available on Ollama's Pro
and Max plans:

Upgrade Ollama [ollama.com/pricing]

Looking to use GLM-5.2 as a team? Let us know [ollama.typeform.com/to/FFV2AVPu#email=…tmail.com]

Fast, reliable performance

Ollama consistently delivers between 80 to 120 output tokens per second (tok/s), even during peak hours, compared to 30-40 tok/s
on other providers.

ollama.com/library/glm-5.2

US & Europe hosting

Ollama's cloud provides access to GLM-5.2 in the US & Europe with a zero data retention policy. Your prompts and responses are
never stored, and data is never used for training.

Get started

To use GLM-5.2 with popular coding apps, first download Ollama:

Download Ollama [ollama.com/download]

To launch Claude Code, run:

ollama launch claude

For use with VS Code (via the new official Ollama extension [marketplace.visualstudio.com/items?ite…ma.ollama]),
run:

ollama launch vscode

For use with Codex:

ollama launch codex

For use with Hermes or OpenClaw:

ollama launch hermes

ollama launch openclaw

For more information on integrations, see Ollama's documentation [docs.ollama.com/integrations].

❤️ Ollama

You are receiving this email because you opted in to receive updates from Ollama
Ollama, 744 High Street, Palo Alto, CA 94301
Unsubscribe [app.loops.so/unsubscribe/cmranrtq9jv23…c71e3f268]