What GPU do I need to run zai-org/GLM-5-FP8?
753.9B parameters, published in F8_E4M3. View on Hugging Face
Set up GLM-5-FP8GLM-5-FP8 is published by zai-org on Hugging Face, with 825,128 downloads and 182 likes to date. It's a GlmMoeDsaForCausalLM model built for text-generation, published natively in F8_E4M3.
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
GLM-5-FP8: common questions
Can GLM-5-FP8 run on a single GPU?
Not on a desktop card. At FP8 (native) it needs 842.6 GB of VRAM, more than a single 32 GB desktop card holds. No card currently listed on the marketplace both supports FP8 (native) and has enough VRAM for it, so how many it would take is not something this page can answer today.
Is GLM-5-FP8 already quantized?
Yes. It is published in FP8, one byte per parameter, so the 842.6 GB figure is already a quantized footprint rather than a full-precision one. Only INT4 goes below it, at 421.3 GB. A GPU without FP8 tensor cores cannot run it as published, which is why cards here are matched on precision support and not on VRAM alone.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More zai-org models
- GLM-OCR (1.3B, BF16)
- GLM-4.7-Flash (31.2B, BF16)
- GLM-5.2-FP8 (753.3B, F8_E4M3)
- GLM-5.2 (753.3B, BF16)
- GLM-5.3-Flash (321.3B, F8_E4M3)
- GLM-5.1-FP8 (753.9B, F8_E4M3)
