Models / Gemma-SEA-LION-v4.5-E2B

Gemma-SEA-LION-v4.5-E2B by aisingapore

GPU memory needed (smallest version of each): Gemma-SEA-LION-v4.5-E2B ~5.12B about 13.9 GB. The cheapest runs on RTX A4000 from $0.11/h right now.

1 model (~5.12B) · ↓ 1.8K downloads a month · from $0.11/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.

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").