Try NVIDIA NIM APIs

Explore

Models

Blueprints

GPUs

Docs

Your Privacy Choices

Contact

Search Results

Searching for: Scientific knowledge

Sort By

Publisher

Use Case

NIM Type

Blueprint Type

Launchable

Sorting by Most Recent

nvidia llama-3.1-nemotron-ultra-253b-v1

Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.

chat math advanced reasoning instruction following function calling

mistralai mistral-small-24b-instruct

Latency-optimized language model excelling in code, math, general knowledge, and instruction-following.

code chat reasoning agent-centric multilingual

nvidia Build an Enterprise RAG Pipeline Blueprint

Power fast, accurate semantic search across multimodal enterprise data with NVIDIA’s RAG Blueprint—built on NeMo Retriever and Nemotron models—to connect your agents to trusted, authoritative sources of knowledge.

NIM Launchable Nemotron Blueprint Enterprise Retrieval-Augmented Generation NVIDIA AI NeMo Retriever

tiiuae falcon3-7b-instruct

Instruction tuned LLM achieving SoTA performance on reasoning, math and general knowledge capabilities

Coding chat Code Generation Language Generation Improved reasoning Math Scientific knowledge

nvidia usdcode

State-of-the-art LLM that answers OpenUSD knowledge queries and generates USD-Python code.

OpenUSD Synthetic Data Generation Digital Twin chat Code Generation

meta llama-3.3-70b-instruct

Advanced LLM for reasoning, math, general knowledge, and function calling

Reasoning chat Code Generation Text-to-Text Instruction following Math

nvidiallama-3.1-nemotron-ultra-253b-v1

mistralaimistral-small-24b-instruct

nvidiaBuild an Enterprise RAG Pipeline Blueprint

tiiuaefalcon3-7b-instruct

nvidiausdcode