Winner of the 24GB VRAM agentic coding challenge. A 355B MoE model that fits a single consumer GPU by activating only 30B parameters. LiveCodeBench 89% — the most capable coding model per dollar of VRAM.
This model requires a specialized High-VRAM environment. Ensure you have the latest CUDA Drivers or Metal Framework installed.
Minimum VRAM: 26GB VRAM Recommended
The GLM-4.7-Flash model by Zhipu AI is a 355B (MoE) parameter architecture optimized for code tasks. It requires approximately 24GB of VRAM to comfortably run locally using a Q4_K_M quantization. Extending the context window up to 200,000 tokens will dynamically allocate further VRAM, meaning high-bandwidth memory hardware is strictly advised.
For running GLM-4.7-Flash 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 26GB 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 glm4-flash' directly in your command line. Alternatively, you can search for the model via LM Studio's interface.