What GPU do I need to run zai-org/GLM-OCR?
1.3B parameters, published in BF16. View on Hugging Face
GLM-OCR is published by zai-org on Hugging Face, with 2,846,242 downloads and 1,996 likes to date. It's a GlmOcrForConditionalGeneration model built for image-text-to-text, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model — check its Hugging Face page before relying on this row.
Cheapest way to run GLM-OCR at its published (BF16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More zai-org models
- GLM-5.2 (753.3B, BF16)
- GLM-4.7-Flash (31.2B, BF16)
- GLM-5.2-FP8 (753.4B, F8_E4M3)
- GLM-5-FP8 (753.9B, F8_E4M3)
- GLM-5.1-FP8 (753.9B, F8_E4M3)
- GLM-4.5-Air (110.5B, BF16)
