InternVL3 models
4 InternVL3 models on Hugging Face, from 938M to 78.4B parameters. At the precision each one is published in, the smallest needs about 2.1 GB of VRAM (InternVL3-1B, cheapest live fit: RTX 5060 Ti) and the largest about 175 GB (InternVL3-78B, cheapest live fit: RTX A5000). The cheapest way to run InternVL3-1B is $0.110/hr.
InternVL3 models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| InternVL3-1B | 938M | BF16 | 2.1 GB | RTX 5060 Ti | $0.110/hr |
| InternVL3-1B-hf | 938M | BF16 | 2.1 GB | RTX 5060 Ti | $0.110/hr |
| InternVL3-8B | 7.9B | BF16 | 17.8 GB | RTX A5000 | $0.176/hr |
| InternVL3-78B | 78.4B | BF16 | 175 GB | RTX A5000 × 8 | $1.41/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from OpenGVLab
- InternVL2 (4 models)
