Skip to content
English

Switch theme

// GLM / CogVideoX (Z.ai) · Video generation

CogVideoX-5b: VRAM & local deployment

5.57B parameters. About 4.2 GB at 4-bit and 12.8 GB at BF16.

released 2024-08-17licence: Custom licence – read itmemory figures are estimates

01Specs

PublisherZ.ai (Zhipu) · zai-org
Family / seriesGLM / CogVideoX (Z.ai) · CogVideoX
TypeVideo generation (text-to-video)
Parameters5.57B Source: counted from official safetensors weights
Released weightsBF16 · 21.5 GBdownload
Licenceother · Custom licence – read itThe publisher uses its own licence; we have not classified it. Read the licence text.
Released2024-08-17 (Hugging Face repo created)

02How much VRAM it needs (estimate)

Video models: memory grows with resolution and clip length; official repos usually list a tested GPU in the card. Weights below are the main model only.

PrecisionWeightsWeights + overheadSmallest GPUMac
BF16 / FP16 (original)11.1 GB 12.8 GB 16GB GPUMac 24GB
FP8 / INT8 / Q8_05.9 GB 7.0 GB 8GB GPUMac 16GB
4-bit (Q4_K_M / AWQ / GPTQ-Int4)3.4 GB 4.2 GB 8GB GPUMac 16GB

Bits per weight: BF16 16, FP8 8.5, 4-bit 4.85. “Fits” = total ≤ 90% of memory; Mac GPU can use ~2/3 of unified memory (≤36GB) or ~3/4 (larger). For MoE, all experts must be in memory, so size by total parameters. Method →

03How to run it

Only runtimes the publisher or the runtime’s official library names for this model.

Which inference engine to choose →

04Official repositories & quantised builds

1 official repo(s) from zai-org.

05Other GLM / CogVideoX (Z.ai) models

All 35 →
ModelParams4-bit totalReleased
CogVideoX-2b · same series1.69B1.6 GB2024-08-05
GLM-5.3753.3B504 GB2026-08-25
GLM-5.3-Flash320B / 18B214 GB2026-08-25
GLM-5.2753.3B504 GB2026-06-16
SCAIL-2——2026-06-09
GLM-5.1753.9B504 GB2026-04-03
GLM-5744B / 40B497 GB2026-02-11
GLM-OCR1.32B1.9 GB2026-01-30
GLM-4.7-Flash31.2B / 3B21.8 GB2026-01-19

06Sources

Data checked 2024-11-23. Parameters, context and licence are copied from the official repository; memory figures are our estimates.

Data updated: Self-host open models(UTC+8)