Last refreshed 2026-05-01. Next refresh: weekly.
Why use ChatGLM3 6B on NVIDIA NIM?
NVIDIA NIM offers ChatGLM3 6B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: chatglm3-6bchatglm3-6bRequest example
chatglm3-6b.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About ChatGLM3 6B
ChatGLM3-6B is an open-source large language model created by Zhipu AI and Tsinghua University, designed for a variety of natural language processing tasks. Operating with a transformer-based architecture and fewer than 10 billion parameters, it excels in multi-turn dialogue, function invocation, long-form text understanding, and supports both Chinese and English. Additionally, its open-source nature fosters innovation and collaboration in the AI community, while its robust performance surpasses many models on tasks like semantics and coding.
FAQ
What is the context window for ChatGLM3 6B on NVIDIA NIM?
ChatGLM3 6B supports a 8,000 token context window on NVIDIA NIM.
Who created ChatGLM3 6B?
ChatGLM3 6B was created by Tsinghua Knowledge Engineering Group (THUDM) as part of the ChatGLM3 model family.
Is ChatGLM3 6B open source?
ChatGLM3 6B's open source status is unknown in the seed data.