Loading…
Loading…
Models / KaLM-Embedding-Gemma3
GPU memory needed (smallest version of each): KaLM-Embedding-Gemma3 12B about 29.7 GB. The cheapest runs on Nvidia A100 from $0.50/h right now.
1 model (12B) · ↓ 20.1K downloads a month · from $0.50/h on Nvidia A100 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 |
|---|---|---|---|---|
| Originaltencent/KaLM-Embedding-Gemma3-12B-2511 | vLLM | 24 GB | 29.7 GB | $0.50/h Nvidia A100 |
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").