The #1 model on Artificial Analysis Intelligence Index with a score of 50. Trained entirely on Huawei Ascend 910B chips — zero US hardware dependency. Achieves SWE-bench 77.8% and leads on multi-turn long-context tasks.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 162GB VRAM Recommended
The GLM-5 model by Zhipu AI is a 744B (MoE) parameter architecture optimized for chat tasks. It requires approximately 160GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 204,800 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running GLM-5 at maximum tokens-per-second, we recommend using LM Studio or Ollama with a GGUF quantization (Q4_K_M or Q6_K). If you are multi-GPU, use vLLM to distribute the layers across your VRAM pool for optimal throughput.
You will need a GPU with at least 162GB of VRAM to run the Q4_K_M quantized version smoothly with a moderate context window.
The simplest method is utilizing Ollama by executing 'ollama run glm5' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.