Mistral-Nemo-Instruct-2407

Mistral‑Nemo‑Instruct‑2407 was developed jointly by Mistral AI and NVIDIA. With 12 billion parameters and a 118,000-token context, it is designed for multilingual dialogue, code generation and complex instruction following. It supports function calling, structured output and streaming. Its compact size balances response quality with inference speed.

• PROVIDER LOCATION: EU
• PARAMETERS: 12,2B
• MAX CONTEXT: 128K token
• LICENSE: Apache 2.0
• FEATURES: Function calling
• OUTPUT FORMATS: Raw_text, Json_object, Json_schema

• Multilingual chatbot
• Code generation
• Conversational assistant
• Understanding complex instructions

curl --request POST \
--url https://apiaruba.it/aiplatform/v1/chat/completions \
--header 'content-type: application/json' \
--header 'x-aruba-api-key: *****' \
--data '{
"model": "Mistral-Nemo-Instruct-2407",
"messages": [
{
"role": "system",
"content": "Sei un assistente conciso."
},
{
"role": "user",
"content": "Spiega cos'\''è un embedding."
}
],
"temperature": 0.7,
"max_tokens": 1000
}'

{
"id": "chatcmpl-36255b3a-69c2-4884-adcb-49e8211106b1",
"created": 1787560711,
"model": "Mistral-Nemo-Instruct-2407",
"object": "chat.completion",
"system_fingerprint": "vllm-0.22.1-820c92fc",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Un embedding è una rappresentazione densa di una parola o di un concetto in uno spazio vettoriale, dove le parole o i concetti simili sono vicini tra loro. Viene spesso utilizzato in campo dell'elaborazione del linguaggio naturale per rappresentare le parole in modo che i modelli di machine learning possano comprenderne il significato.",
"role": "assistant",
"provider_specific_fields": {
"reasoning": null,
"refusal": null
}
},
"provider_specific_fields": {}
}
],
"usage": {
"completion_tokens": 75,
"prompt_tokens": 17,
"total_tokens": 92
}
}

• Llama‑3.1‑8B‑Instruct

• Hugging Face
• Blog Mistral
• NVIDIA NIM