vram.run Models Hardware Providers Cloud State of Inference
API provider data is live · Hardware & cloud pricing curated 2026-02-23

GLM-5.2-FP8

by zai-org

753B params · text-generation · 119 likes · 217.4k downloads

GLM-5.2-FP8 is a 753B parameter model. At Q4 quantization it requires 377GB of VRAM. It requires a GPU with at least 377GB of VRAM.

Inference providers

Provider$/1M in$/1M outThroughput
Z.ai37 tok/s
Install CLI [email protected] Raw data · MIT · API data: live · HW/Cloud data: curated 2026-02-23 · v0.6.0