Models / FLM-2

FLM-2 by CofeAI

GPU memory needed (smallest version of each): FLM-2 52B about 128.3 GB. The cheapest runs on Nvidia H200 from $4.41/h right now.

1 model (52B) · ↓ 1.8K downloads a month · from $4.41/h on Nvidia H200 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").