Models / SAGE-MM-Molmo2

SAGE-MM-Molmo2 by allenai

GPU memory needed (smallest version of each): SAGE-MM-Molmo2 8B about 24.2 GB. The cheapest runs on RTX 5000 Ada from $0.44/h right now.

1 model (8B) · ↓ 243 downloads a month · from $0.44/h on RTX 5000 Ada 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.

SAGE-MM-Molmo2 8B

Version	Runtime	Weights	GPU memory	Cheapest machine now
Originalallenai/SAGE-MM-Molmo2-8B-SFT	vLLM	17 GB	24.2 GB	$0.44/h RTX 5000 Ada
RLallenai/SAGE-MM-Molmo2-8B-SFT_RL	vLLM	17 GB	24.2 GB	$0.44/h RTX 5000 Ada

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").

Loading…