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.

総パラメータ109B17B active / token

推定メモリ~78 GBINT4 MoE

コンテキスト10M advertisedText + Image

LicenseLlama 4 CommunityMultilingual

01 / 用途

02 / 推定適合

03 / 実行環境

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

注意

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