glm-5:cloud

Upstream reference: GLM-5 upstream release

Publisher: Z.ai

Z.ai describes GLM-5 as a mixture-of-experts language model developed for systems-engineering and extended agent workflows. These are the publisher’s stated design targets.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Total parameters

744 billion Source

Active parameters

40 billion Source

Attention design named by publisher

DeepSeek Sparse Attention Source

Upstream license label

MIT Source

Publisher-described uses

• Systems-engineering and extended agent workflows described by the publisher. Source

Reference limitations

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• GLM-5 model card — Z.ai. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• Z.AI / Zhipu AI — official site
• Ollama

Where glm-5:cloud comes from

Named in 6 observation pages

• Academic observation — 32 cloud models × Cline and Pi · V1
• Aider — 169 runs across 83 models · V1
• Cloud Models — three-judge autoresearch observation set · V1
• Function-calling — 9 cloud models × 30 prompts · V1
• The agentic wrapper observatory · V1
• Tool-call format compatibility across 31 cloud models · V1