Model ID
zai-org/GLM-4.6
Capabilities
GLM 4.6
GLM 4.6 is a Mixture-of-Experts (MoE) large language model developed by Z.ai designed for advanced coding, reasoning, and agentic workflows. The model features a 357B parameter architecture built on a 92-layer transformer with 96 attention heads and a 5,120 hidden size, utilizing 160 routed experts with 8 experts activated per token for efficient scaling. It supports a ~200K token context window, enabling long-horizon reasoning and complex multi-step agent interactions.
About this model
GLM 4.6 is a Mixture-of-Experts (MoE) large language model developed by Z.ai designed for advanced coding, reasoning, and agentic workflows. The model features a 357B parameter architecture built on a 92-layer transformer with 96 attention heads and a 5,120 hidden size, utilizing 160 routed experts with 8 experts activated per token for efficient scaling. It supports a ~200K token context window, enabling long-horizon reasoning and complex multi-step agent interactions.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (zai-org/GLM-4.6). Released under MIT. Further reading: Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
MI325X
2,048 GB
B200
1,440 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on MI325X · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
AMD Instinct MI325X
Unlock Next-Generation AI Power on Vultr Cloud GPU