GLM-4.7

Name: GLM-4.7 local performance reports
Creator: llamaperf
License: https://creativecommons.org/licenses/by/4.0/

Zhipu AI · 1 report

Thin page (1 of 3 reports needed for indexing). Add yours.

GLM-4.7

AMD Strix Halo 128GB

reported speed:: 40.0 tokens/s generation

Reported by the source; GPU count, offloading and concurrent requests can change this figure. Check the full setup before comparing.

User reports running 3 local sessions of GLM 4.7 at about 40 tok/s each on an AMD Strix Halo mini PC with 128GB unified RAM. The model family is inferred as GLM-4.7 from the post title and text. The user is positive about the setup for budget local AI.