Loading…
Loading…
Models / JoyAI-LLM-Flash
GPU memory needed (smallest version of each): JoyAI-LLM-Flash ~49.3B about 114.7 GB. The cheapest runs on 4x RTX 5090 from $2.18/h right now.
1 model (~49.3B) · ↓ 724 downloads a month · from $2.18/h on 4x RTX 5090 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 |
|---|---|---|---|---|
| Originaljdopensource/JoyAI-LLM-Flash | vLLM | 99 GB | 114.7 GB | $2.18/h 4x RTX 5090 |
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").