Loading…
Loading…
Models / gemma-4
GPU memory needed (smallest version of each): gemma-4 12B about 32.4 GB. The cheapest runs on RTX A6000 from $0.46/h right now.
1 model (12B) · ↓ 827 downloads a month · from $0.46/h on RTX A6000 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 |
|---|---|---|---|---|
| Originalyuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2 | vLLM | 24 GB | 32.4 GB | $0.46/h RTX A6000 |
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").