Loading…
Loading…
Models / gemma-4
1 model (26B) · ↓ 21.2K downloads a month · from $0.13/h on RTX A4000 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 |
|---|---|---|---|---|
| NVFP4 (AEON-7)AEON-7/Gemma-4-26B-A4B-it-Uncensored-NVFP4 | vLLM | 16 GB | 22.7 GB | $0.21/h RTX 3090 |
| Gemma 4 E4B it Uncensored NVFP4 (AEON-7)AEON-7/Gemma-4-E4B-it-Uncensored-NVFP4 | vLLM | 10 GB | 14.3 GB | $0.13/h RTX A4000 |
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").