LocalForge
Wróć
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.

Źródło pierwotne
Wszystkie parametry109B17B active / token
Szacowana pamięć~78 GBINT4 MoE
Kontekst10M advertisedText + Image
LicenseLlama 4 CommunityMultilingual
01 / NAJLEPSZY DO
  • long context
  • vision
  • datacenter serving
02 / SZACOWANE DOPASOWANIE
03 / URUCHOM PRZEZ
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
Uwaga

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