Loading…
Loading…
Models / delphi-1e22-9_7Bparams-160Btokens-base-wc386k_lr1e5-sft
GPU memory needed (smallest version of each): delphi-1e22-9_7Bparams-160Btokens-base-wc386k_lr1e5-sft ~0M about 26.4 GB. The cheapest runs on 2x RTX A4000 from $0.22/h right now.
1 model (~0M) · ↓ 173.8K downloads a month · from $0.22/h on 2x 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").