Models / Ling-flash-base-2.0

Ling-flash-base-2.0 by inclusionAI

GPU memory needed (smallest version of each): Ling-flash-base-2.0 ~103B about 231.5 GB. The cheapest runs on 8x Nvidia A100 from $4.26/h right now.

1 model (~103B) · ↓ 2.4K downloads a month · from $4.26/h on 8x Nvidia A100 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.

Ling-flash-base-2.0 ~103B

Version	Runtime	Weights	GPU memory	Cheapest machine now
Ling flash 2.0inclusionAI/Ling-flash-2.0	vLLM	206 GB	231.5 GB	$4.26/h 8x Nvidia A100

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…