GLM-4.6V — local AI model by Zhipu AI (Z.ai)
Written by Jakub Rusinowski · Last updated
Z.ai's vision-language line. The Flash member is the 9B efficiency variant, sharing GLM-4.6V's multimodal capabilities at a fraction of the compute and small enough for an 8 GB card.
Variants
The smallest GLM-4.6V variant needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.
| Model | VRAM at Q4 | VRAM | Context | Run it |
|---|---|---|---|---|
| GLM-4.6V-Flash 9B → 9B | ~6.2 GB | 65,536 | ollama run glm-4-6v |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run GLM-4.6V locally
Install Ollama, then pull the tag.
ollama run glm-4-6vPick a size above for its own VRAM figure, speed estimate and install command.
Licence
Commercial use permitted. No usage restrictions beyond attribution.
Applies to: GLM-4.6V-Flash 9BRecommended GPU
The cheapest catalogued GPU that runs GLM-4.6V locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).
GLM-4.6V — frequently asked questions
How much VRAM does GLM-4.6V need?
GLM-4.6V needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-4.6V-Flash 9B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-4.6V on an RTX 4090 (24 GB)?
Yes — GLM-4.6V runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
What quantization should I use for GLM-4.6V?
Q4_K_M is the best balance of quality and VRAM for GLM-4.6V in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
How do I run GLM-4.6V with Ollama?
GLM-4.6V has no local Ollama tag — the published tag is cloud-hosted, so running it sends your prompts to a hosted GPU rather than your own machine.