Loading…
Loading…
Models / NeuralHermes-2.5-Mistral
GPU memory needed (smallest version of each): NeuralHermes-2.5-Mistral 7B about 19.5 GB. The cheapest runs on 2x RTX 3060 from $0.23/h right now.
1 model (7B) · ↓ 86 downloads a month · from $0.23/h on 2x RTX 3060 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 |
|---|---|---|---|---|
| Originalmlabonne/NeuralHermes-2.5-Mistral-7B | vLLM | 14 GB | 19.5 GB | $0.23/h 2x RTX 3060 |
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").