Loading…
Loading…
Models / Llama-4-Maverick
2 models (17B to 17B) · ↓ 51.8K downloads a month · from $11.77/h on 8x RTX PRO 6000 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 |
|---|---|---|---|---|
| Originalmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Licence to accept | vLLM | 417 GB | ~502.3 GB | $11.77/h 8x RTX PRO 6000 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| Instructmeta-llama/Llama-4-Maverick-17B-128E-InstructLicence to accept | vLLM | 803 GB | ~966 GB | $50.44/h 8x Nvidia H200 |
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").