Z.ai releases GLM-4.7-Flash, a 30B-A3B MoE model for lightweight deployment
Original titlezai-org/GLM-4.7-Flash
AISummary
Z.ai has released GLM-4.7-Flash, a 30B-A3B MoE model that it positions as the strongest model in the 30B class. The model reports SWE-bench Verified 59.2 and τ²-Bench 79.5, and supports local deployment through vLLM and SGLang.
AIWhy it matters
The source lists benchmark scores against Qwen3-30B-A3B-Thinking-2507 and GPT-OSS-20B, letting readers compare the 30B-class MoE model directly with its named rivals.
Source: Z.ai (GLM) · new models on Hugging Face · huggingface.co