Loading…
Loading…
Models / starchat2
GPU memory needed (smallest version of each): starchat2 15B about 38.4 GB. The cheapest runs on 2x RTX 3090 from $0.42/h right now.
1 model (15B) · ↓ 168 downloads a month · from $0.42/h on 2x RTX 3090 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 |
|---|---|---|---|---|
| starchat2 15b v0.1HuggingFaceH4/starchat2-15b-v0.1 | vLLM | 32 GB | 38.4 GB | $0.42/h 2x RTX 3090 |
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").