Loading…
Loading…
Models / AFM
1 model (4.5B) · ↓ 7.9K downloads a month · from $0.15/h on RTX 5060 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 |
|---|---|---|---|---|
| Instructarcee-ai/AFM-4.5B | vLLM | 9.2 GB | 13.2 GB | $0.15/h RTX 5060 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").