How much RAM does GLM-4.6V need?

GLM-4.6V needs about 69 GB of memory at Q4_K_M quantization with 4K context. The download itself is 65 GB; the extra covers the context cache and runtime overhead.

Can I run GLM-4.6V on a laptop?

Yes — it runs comfortably on a machine with 128GB RAM, for example Mac Studio M3 Ultra.

GLM-4.6V: hardware requirements

GLM-4.6V needs about 69 GB of memory at Q4 quantization — a 65 GB download plus room for context and overhead. That fits a machine with 128GB RAM.

Parameters

108B

Tier

Needs a workstation

Licence

See model card

Released

2025-09-30

Will it run on your machine?

8GB RAMNot enough memory 16GB RAMNot enough memory 24GB RAMNot enough memory 32GB RAMNot enough memory 64GB RAMNot enough memory 128GB RAMRuns well 8GB VRAMNot enough memory 12GB VRAMNot enough memory 16GB VRAMNot enough memory 24GB VRAMNot enough memory 32GB VRAMNot enough memory

Download sizes by quantization

Lower quantization means a smaller file and less memory, at some cost to quality. Q4_K_M is the usual starting point. What is this?

Quant	Download	RAM @ 4K	RAM @ 32K	Source
Q4_K_Mrecommended	65 GB	69 GB	74 GB	estimated
Q5_K_M	76 GB	80 GB	86 GB	estimated
Q6_K	88 GB	92 GB	98 GB	estimated
Q8_0	114 GB	118 GB	124 GB	estimated
BF16	215 GB	219 GB	225 GB	estimated

“Measured” sizes are read from published GGUF files. “Estimated” sizes are derived from the parameter count and are typically within a few percent. The RAM columns add the context cache and runtime overhead to the download size.

Other sizes of GLM-4.6

GLM-4.6V-Flash10B · 7.0 GB

Model card on HuggingFace →API specs & pricing →Verified 2026-09-13Tracked for 12 months after release