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.

कुल पैरामीटर109B17B active / token

अनुमानित मेमोरी~78 GBINT4 MoE

कॉन्टेक्स्ट10M advertisedText + Image

LicenseLlama 4 CommunityMultilingual

01 / बेहतर उपयोग

02 / अनुमानित फ़िट

03 / इसके साथ चलाएँ

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

सावधानी

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