🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN ON CONSUMER GPU
Run Cosmos-Predict1-7b-Video2World on Consumer GPU hardware
10 options with enough VRAM (FP16), ranked by headroom.
| Hardware | VRAM | Fits FP16? | Headroom | ~Price |
|---|---|---|---|---|
| NVIDIA DGX Spark → | 128 GB | yes | ~99.7 GB | ~$3,999 |
| AMD Ryzen AI Max+ 395 → | 128 GB | yes | ~99.7 GB | ~$1,999 |
| NVIDIA GeForce RTX 5090 → | 32 GB | yes | ~13.9 GB | ~$1,999 |
| Intel Arc Pro B70 → | 32 GB | yes | ~13.9 GB | — |
| NVIDIA GeForce RTX 4090 → | 24 GB | yes | ~6.6 GB | ~$1,599 |
| NVIDIA GeForce RTX 3090 Ti → | 24 GB | yes | ~6.6 GB | ~$1,999 |
| AMD Radeon RX 7900 XTX → | 24 GB | yes | ~6.6 GB | ~$999 |
| NVIDIA GeForce RTX 3090 → | 24 GB | yes | ~6.6 GB | ~$1,499 |
| Intel Arc Pro B60 → | 24 GB | yes | ~6.6 GB | — |
| AMD Radeon RX 7900 XT → | 20 GB | yes | ~2.9 GB | ~$899 |
VRAM fit at FP16 (lower precision needs less). We don't estimate generation speed for image/video/audio — it depends on tool, resolution and steps.
FAQ
What Consumer GPU hardware can run Cosmos-Predict1-7b-Video2World?▶
On GenAIList, 10 Consumer GPU GPUs have enough VRAM to hold Cosmos-Predict1-7b-Video2World at FP16 — the most headroom is on the NVIDIA DGX Spark (128 GB).
How fast is Cosmos-Predict1-7b-Video2World on Consumer GPU hardware?▶
We don't estimate generation speed for image/video/audio models — it depends on the tool, resolution and step count. This page ranks by which hardware fits the model in memory.