Model Detail human-review-recommended
CogVideoX 5B
Zhipu AI's CogVideoX 5B. Compact open video model.
COGVIDEOXapache-2.02024-08
Parameters
5B
Dense model
Context window
—
Standard context
Architecture
decoder only transformer
diffusion
Quality score
70
Planner signal
Task Fit
Code AgentNot a fit
Not marked for code agent in the current library.
CodeNot a fit
Not marked for code in the current library.
ChatNot a fit
Not marked for chat in the current library.
RAGNot a fit
Not marked for rag in the current library.
VisionNot a fit
Not marked for vision in the current library.
Image GenerationNot a fit
Not marked for image generation in the current library.
Video GenerationSupported
Native text-to-video or image-to-video model.
VoiceNot a fit
Not marked for voice in the current library.
Source Confidence
Overallmedium · 84/100
ParametersReviewed / seeded
Task fitReviewed / seeded
MemorySeeded artifact
LicenseSource / seed
BenchmarksMissing
Hardware fitCalculated
Review flags
recommended VRAM below minimummissing benchmarks
Variants and Quant Artifacts
Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.
| Quant | Format | Quality | Min RAM | Reco RAM | Runtime | Action |
|---|---|---|---|---|---|---|
| FP16 | checkpoint | high | 16GB | 24GB | ollama | Plan with this |
| Q8 | checkpoint | high | 16GB | 24GB | ollama | Plan with this |
Recommended Hardware
Cheapest That Works
NVIDIA RTX 3060 12GB
Lowest estimated 5-year cost that can run this model.
12GB VRAM$1,570 / 5y
Best Value
NVIDIA RTX 5090 32GB
Plenty of fast-memory headroom for this model.
32GB VRAM$4,788 / 5y
Best Performance
NVIDIA RTX 6000 Blackwell 96GB
Highest local performance signal among compatible hardware.
96GB VRAM$12,376 / 5y
Benchmarks
No benchmark data is available for this model yet.
Source and Review
Hugging FaceTHUDM/CogVideoX-5b
Ollamacogvideox:5b
Verificationhuman-review-recommended
Artifact sourceseeded
Default variantCogVideoX 5B Coder
Tool callingNot marked