Non sono ancora disponibili benchmark associati a questa scheda.
Esecuzione locale
Inferenza · stima della memoria
replicate/ibm-granite/granite-3.3-8b-instruct
Informazioni verificate sull’architettura insufficienti per una stima affidabile della VRAM.
Capacità
Uso di strumenti
Sì*
Modalità API
Chat*
Messaggi di sistema
Sì*
Configurazione di sistema
Specifiche dettagliate
Specifiche · 6 campi
input cost per token
3,0e-8*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
replicate*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
2,5e-7*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Sì*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports system messages
Sì*Ambito e condizioni
native_context
provider
replicate*
mode
chat*
full_native_model_id
replicate/ibm-granite/granite-3.3-8b-instruct*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*