Loading…
Loading…
Models / meditron
GPU memory needed (smallest version of each): meditron 7B about 18.4 GB, meditron 70B about 167.8 GB. The cheapest runs on 2x RTX 3060 from $0.16/h right now.
2 models (7B to 70B) · ↓ 2K downloads a month · from $0.16/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 |
|---|---|---|---|---|
| Originalepfl-llm/meditron-7bLicence to accept | vLLM | 13 GB | ~18.4 GB | $0.16/h 2x RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Originalepfl-llm/meditron-70bLicence to accept | vLLM | 138 GB | ~167.8 GB | $2.25/h 8x RTX 3090 |
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").