Loading…
Loading…
Models / INTELLECT-3
GPU memory needed (smallest version of each): INTELLECT-3 ~107B about 241.4 GB. The cheapest runs on 8x Nvidia A100 from $4.26/h right now.
1 model (~107B) · ↓ 765 downloads a month · from $4.26/h on 8x Nvidia A100 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 |
|---|---|---|---|---|
| OriginalPrimeIntellect/INTELLECT-3 | vLLM | 214 GB | 241.4 GB | $4.26/h 8x Nvidia A100 |
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").