🚀 NVIDIA AI Multi-Model v3.1

38 modelli VERIFICATI + auto-adattamento system role • Memoria • SSE • MCP

🏠 UI | 📖 Docs | 🔧 Swagger | 🔌 MCP

Default: meta/llama-3.2-3b-instruct (⚡ 153ms)

Chatbot

🤖 Modello

🔑 Session ID

📝 System Prompt

🌡️ Temp

0 2

📏 Tokens

256 16384

🧠 Memoria

📊 Memoria

📋 Catalogo — 38 modelli verificati

Cat	Nome	ID	Context	Descrizione	System Role
Translation	🐢 Nemotron 3 Nano Omni (Reasoning)	nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	131072	Diffusion-based Gemma — 843ms (no system role)	✅

Cat	Nome	ID	Context	Descrizione	System Role
LLM	⚡ LLaMA 3.2 3B Instruct	meta/llama-3.2-3b-instruct	131072	🥇 FASTEST — 153ms — DEFAULT	✅
LLM	⚡ Nemotron Mini 4B	nvidia/nemotron-mini-4b-instruct	8192	Ultra-fast 4B — 186ms	✅
Vision	⚡ LLaMA 3.2 11B Vision	meta/llama-3.2-11b-vision-instruct	131072	Fast vision-language — 196ms	✅
LLM	⚡ Phi 4 Mini Instruct	microsoft/phi-4-mini-instruct	131072	🆕 Latest Phi 4 Mini — 206ms	✅
LLM	⚡ Gemma 2 2B	google/gemma-2-2b-it	8192	Compact Gemma — 212ms (no system role)	❌
LLM	⚡ Nemotron Nano 8B v1	nvidia/llama-3.1-nemotron-nano-8b-v1	131072	Efficient Nemotron — 239ms	✅
LLM	⚡ Stockmark 2 100B	stockmark/stockmark-2-100b-instruct	32768	Japanese specialist 100B — 261ms	✅
LLM	⚡ Solar 10.7B	upstage/solar-10.7b-instruct	4096	Upstage Solar — 261ms	✅
LLM	⚡ LLaMA 3.1 70B Instruct	meta/llama-3.1-70b-instruct	131072	High-quality 70B — 263ms	✅
LLM	⚡ Sarvam M	sarvamai/sarvam-m	32768	Indian multilingual — 285ms	✅
LLM	🚀 Ising Calibration 35B	nvidia/ising-calibration-1-35b-a3b	131072	Calibration model — 331ms	✅
Vision	🚀 Nemotron Nano 12B v2 VL	nvidia/nemotron-nano-12b-v2-vl	131072	Vision Nemotron 12B — 334ms	✅
LLM	🚀 Mistral Small 4 119B	mistralai/mistral-small-4-119b-2603	131072	Mistral Small 4 — 357ms	✅
LLM	🚀 Qwen3 Next 80B	qwen/qwen3-next-80b-a3b-instruct	131072	🆕 Latest Qwen 3 — 371ms	✅
LLM	🚀 Gemma 3n E2B	google/gemma-3n-e2b-it	8192	Gemma 3 Nano — 380ms (no system role)	❌
LLM	🚀 Mistral Nemotron	mistralai/mistral-nemotron	131072	NVIDIA-Mistral collab — 383ms	✅
LLM	🚀 LLaMA 3.1 8B Instruct	meta/llama-3.1-8b-instruct	131072	Popular 8B — 404ms	✅
LLM	🚀 MiniMax M2.7	minimaxai/minimax-m2.7	131072	MiniMax model — 409ms	✅
LLM	🚀 Nemotron 3 Nano 30B	nvidia/nemotron-3-nano-30b-a3b	131072	🆕 Nemotron 3 MoE — 410ms	✅
Vision	🚀 LLaMA 3.2 90B Vision	meta/llama-3.2-90b-vision-instruct	131072	Large vision-language — 419ms	✅
LLM	🚀 Mistral Medium 3.5 128B	mistralai/mistral-medium-3.5-128b	131072	Mistral Medium 3.5 — 419ms	✅
LLM	💪 Qwen 3.5 122B	qwen/qwen3.5-122b-a10b	131072	🔥 Qwen 3.5 MoE — 505ms	✅
LLM	💪 Nemotron 3 Super 120B	nvidia/nemotron-3-super-120b-a12b	131072	🔥 Nemotron 3 Super MoE — 556ms	✅
LLM	💪 Mixtral 8x7B	mistralai/mixtral-8x7b-instruct-v0.1	32768	Classic MoE — 685ms	✅
LLM	💪 Nemotron 3 Ultra 550B	nvidia/nemotron-3-ultra-550b-a55b	131072	🚀 MASSIVE 550B MoE — 707ms	✅
LLM	💪 DeepSeek V4 Flash	deepseek-ai/deepseek-v4-flash	131072	🆕 Fast DeepSeek V4 — 712ms	✅
LLM	💪 Dracarys LLaMA 3.1 70B	abacusai/dracarys-llama-3.1-70b-instruct	131072	AbacusAI fine-tuned 70B — 774ms	✅
LLM	💪 DiffusionGemma 26B	google/diffusiongemma-26b-a4b-it	131072	Diffusion-based Gemma — 843ms (no system role)	❌
LLM	🐢 Kimi K2.6	moonshotai/kimi-k2.6	131072	🆕 Moonshot Kimi — 1.12s	✅
LLM	🐢 GLM 5.2	z-ai/glm-5.2	131072	🆕 Zhipu GLM 5.2 — 1.5s	✅
Reasoning	🐢 DeepSeek V4 Pro	deepseek-ai/deepseek-v4-pro	131072	🔥 Advanced reasoning — 1.7s	✅
LLM	🐢 LLaMA 3.2 1B	meta/llama-3.2-1b-instruct	131072	Ultra-lightweight — 1.9s	✅
Reasoning	🐢 Nemotron 3 Nano Omni (Reasoning)	nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	131072	🧠 Reasoning model — 2.6s	✅
LLM	🐢 MiniMax M3	minimaxai/minimax-m3	131072	🆕 Latest MiniMax — 3.6s	✅
LLM	🐢 Ministral 14B	mistralai/ministral-14b-instruct-2512	131072	Mistral Ministral — 4.6s	✅
Vision	🐢 Nemotron Nano VL 8B	nvidia/llama-3.1-nemotron-nano-vl-8b-v1	131072	Vision Nemotron — 5.9s	✅
LLM	🐢 Mistral Large 3 675B	mistralai/mistral-large-3-675b-instruct-2512	131072	🚀 MASSIVE 675B — 8.2s	✅
Translation	🌍 Riva Translate 4B v1.1	nvidia/riva-translate-4b-instruct-v1.1	8192	NVIDIA translation — 178ms	✅

🚀 NVIDIA AI Multi-Model v3.1

📋 Catalogo — 38 modelli verificati

⚡ Verifica live tutti i modelli in parallelo (con system prompt)

🎯 Auto-adattamento System Role

📋 Modelli attualmente in auto-adattamento:

📖 Documentazione

Endpoints principali: