Models / LLaVA-NeXT-Video

LLaVA-NeXT-Video by llava-hf

GPU memory needed (smallest version of each): LLaVA-NeXT-Video 34B about 80.6 GB. The cheapest runs on 4x RTX 3090 from $0.99/h right now.

1 model (34B) · ↓ 185 downloads a month · from $0.99/h on 4x RTX 3090 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.

Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").