LocalOps LogoLocalOps
Back to Calculator

GLM-4.6V

Z.ai's VLM with 106B total / 12B active MoE parameters. SOTA visual understanding at its scale, 128K multimodal context, native Function Call support for visual-to-action workflows.

Specifications

Source
ArchitectureVISION
Parameters106B
Familyglm
VRAM (Q4)53.0G
MoE: 12B active.
50% cheaper API pricing vs GLM-4.5V. Native function calling allows images to trigger APIs directly — key for visual agent pipelines.
zhipuvisionmultimodalmoefunction-callingapache2

Build your Local Rig

Ready to run locally? Shop top-tier GPUs on Amazon for the best performance.

Instant Cloud GPUs

Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.

Deploy Now

Share this Model

Send these specs directly to your community.

Post