Loading…
Loading…
Models / LensVLM
GPU memory needed (smallest version of each): LensVLM 9B about 24.3 GB. The cheapest runs on 2x RTX 4060 Ti from $0.27/h right now.
1 model (9B) · ↓ 2.8K downloads a month · from $0.27/h on 2x RTX 4060 Ti 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.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalapple/LensVLM-9B | vLLM | 19 GB | 24.3 GB | $0.27/h 2x RTX 4060 Ti |
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").