Models / GLM-4.5-Air-REAP

GLM-4.5-Air-REAP by cerebras

GPU memory needed (smallest version of each): GLM-4.5-Air-REAP 82B about 192.8 GB. The cheapest runs on 8x RTX 4090 from $3.55/h right now.

1 model (82B) · ↓ 292 downloads a month · from $3.55/h on 8x RTX 4090 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").