Skip to content

Cost to run

Qwen 1.5 MoE A2.7B

alibaba/qwen-1.5-moe-a2.7b

Family
Qwen 1.5
Context
32,768 tokens

Qwen 1.5 MoE A2.7B can be run self-hosted (rent a GPU + run vLLM/TGI) or through a serverless API (pay per token). Live pricing comparisons:

Need to benchmark this model against another? Try the calculator or see where it ranks on the InferenceScore leaderboard.