MODEL / META

Llama 4 Scout

Meta's single-H100 fit requires INT4. All 109B parameters must be stored; 17B active is not the memory number.

총 파라미터109B17B active / token

추정 메모리~78 GBINT4 MoE

컨텍스트10M advertisedText + Image

LicenseLlama 4 CommunityMultilingual

01 / 추천 용도

02 / 추정 적합도

03 / 배포 환경

vLLMAdvancedvllm serve meta-llama/Llama-4-Scout-17B-16E-Instruct --dtype auto

TensorRT-LLMAdvancedtrtllm-serve meta-llama/Llama-4-Scout-17B-16E-Instruct

llama.cppMediumllama-server -m /path/to/verified-model.gguf --port 8080

주의

Meta's single-H100 fit requires INT4. All 109B parameters must be stored; 17B active is not the memory number.