Can my GPU run GLM-5.2?

Best use

Long-horizon coding, large-repository context, frontend generation, and local sovereignty experiments on very large-memory systems. Weakness: No vision input and impractical for normal consumer GPUs; even 2-bit GGUF needs roughly 238-254 GB before runtime overhead.

GPU fit table

Quantization memory estimate on a 12GB GPU preset

Data sources and confidence

This is a practical planning estimate, not a benchmark. Real memory use changes with backend, context length, KV cache, quantization file, drivers, and offloading settings.

• Z.ai GLM-5.2 docs
• Z.ai GitHub
• Hugging Face base model
• Unsloth GLM-5.2 GGUF

Similar local models