GLM-4 models

6 GLM-4 models from Z.ai on Hugging Face, from 9.4B to 32.6B parameters, published by Z.ai in BF16, with contexts from 8K to 128K tokens. The smallest official model, glm-4-9b-hf, needs about 21.0 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.

Part of the GLM series · Next generation: GLM-4.5

Pick a size

One row per official GLM-4 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
GLM-4-9B-04149.4B21.0 GB10.5 GB5.3 GBRTX A5000$0.176/hr1.3 GB
GLM-4.1V-9B-Thinking10.3B23.0 GB11.5 GB5.8 GBRTX A5000$0.176/hr1.3 GB
GLM-Z1-32B-041432.6B72.8 GB36.4 GB18.2 GBA100$1.18/hr1.9 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (6)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
glm-4-9b-hf9.4BBF1621.0 GBRTX A5000$0.176/hr
codegeex4-all-9b9.4BBF1621.0 GBRTX A5000$0.176/hr
glm-4-9b9.4BBF1621.0 GBRTX A5000$0.176/hr
GLM-4-9B-04149.4BBF1621.0 GBRTX A5000$0.176/hr
GLM-4.1V-9B-Thinking10.3BBF1623.0 GBRTX A5000$0.176/hr
GLM-Z1-32B-041432.6BBF1672.8 GBA100$1.18/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Z.ai

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.