GLM-5.3 — local AI model by Zhipu AI (Z.ai)
Written by Jakub Rusinowski · Last updated
Z.ai's 753B-parameter flagship, released in August 2026. It shares GLM-5.2's base model, so every gain is post-training: Z.ai's card leads with agentic coding and cyber-security benchmarks. Text only, 1M-token context, and a bespoke licence: MIT-style, except that a Model-as-a-Service operator with more than $10 billion in annual revenue must pass Z.ai's security review before commercial use. For the natively multimodal 320B sibling, see GLM-5.3-Flash.
Variants
The smallest GLM-5.3 variant needs about 456 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-5.3 → 753B (40B active) | ~455.6 GB | 1,048,576 | cloud-hosted tag |
Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.
How to run GLM-5.3 locally
Install Ollama, then pull the tag.
No local Ollama tag. Ollama lists glm-5.3 only as a cloud-hosted ':cloud' tag, which runs on Ollama's servers, not your machine.
Pick a size above for its own VRAM figure, speed estimate and install command.
Licence
Weights are downloadable and commercial use is permitted, subject to the licence’s acceptable-use terms.
Applies to: GLM-5.3GLM-5.3 — frequently asked questions
How much VRAM does GLM-5.3 need?
GLM-5.3 needs about 456 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: GLM-5.3 (456 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run GLM-5.3 on an RTX 4090 (24 GB)?
GLM-5.3's smallest variant needs about 456 GB, which exceeds a single RTX 4090 (24 GB). Use multiple GPUs, a higher-VRAM card, or Apple Silicon with large unified memory.
What quantization should I use for GLM-5.3?
Q4_K_M is the best balance of quality and VRAM for GLM-5.3 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-5.3 with Ollama?
GLM-5.3 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.