FareedKhan-dev/glm-5.2-in-c

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.

语言：C · GitHub 星标：75 · Fork：20

话题：c · consumer-hardware · cpu-inference · cuda · deep-learning · edge-ai · glm · inference-engine

在 GitHub 上查看原仓库