Z.ai

GLM-5.3 Flash Flash

321,3B

Parameters

186,0 Go

Q4_K_XL file

≥ 187,5 Go

Recommended VRAM

1 048 576

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 187,5 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2026-08-25
Architecture
45 layers · 64 KV heads · dimension ?
Attention
Latent (MLA): the context cache is compressed — much lighter than the standard formula.
GGUF file
unsloth/GLM-5.3-Flash-GGUF · 6 files Download (186,0 Go)

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.