> This page is for version 1.0.0 (Latest) (default). > For other versions, use one of these documentation indexes: > - 1.0.0 (Latest) (default): https://docs.nvidia.com/nim/metadata-api/1.0.0/llms.txt > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nim/metadata-api/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/metadata-api/_mcp/server. # Glossary for NIM Metadata API > Definitions of the profile, hardware, and identifier terms used throughout the NIM Metadata API documentation. Use this glossary to understand key terms used throughout the NIM Metadata API documentation. ## G Browse terms starting with **G**. GPU-agnostic profile A profile that is not tied to a particular GPU and runs anywhere with sufficient vRAM. These profiles omit `gpu` and `gpu_device` entirely and can carry an empty `tested_gpu_devices` array. **Related**: [Core Concepts Overview](/nim/metadata-api/about/core-concepts) gpu_device The PCI identifier of the GPU a profile targets, in the form `pciDeviceId:pciVendorId`. This value is precise and machine-comparable, so it is the field to match on when you evaluate hardware fit. ```text 2330:10de ``` **Related**: [Response Fields](/nim/metadata-api/reference/response-fields) ## I Browse terms starting with **I**. Inference backend The serving backend a profile uses, such as `tensorrt_llm`, `vllm`, or `sglang`. Treat this value as an open string rather than an enumeration, because new values appear without notice. **Related**: [Notes for Automated Agents](/nim/metadata-api/guides/automated-agents) ## M Browse terms starting with **M**. Metadata coverage The extent to which published NIM microservices have API-backed metadata. Metadata is attached at publish time, so coverage grows as NIM microservices are released and re-released. **Related**: [Current Limitations](/nim/metadata-api/reference/limitations) ## N Browse terms starting with **N**. NIM microservice An NVIDIA NIM microservice, which is a GPU-accelerated container that packages a model, the inference stack, and a unified API. Each NIM microservice ships one or more profiles. **Related**: [NIM Metadata API Documentation](/nim/metadata-api/about/overview) ## P Browse terms starting with **P**. Pipeline parallel size The number of pipeline stages a profile splits the model across, recorded as `pipeline_parallel_size`. It combines with tensor parallel size to determine the total number of GPUs a profile requires. **Related**: [Choose a Profile for Your Hardware](/nim/metadata-api/guides/choose-a-profile) Precision The numeric precision a profile uses, such as `fp8`, `bf16`, or `fp16`. Lower precision generally favors throughput, and higher precision generally favors accuracy. **Related**: [Response Fields](/nim/metadata-api/reference/response-fields) Profile A deployable configuration of a NIM microservice that pairs the model with a GPU target, a numeric precision, an inference backend, and a parallelism layout. A single NIM microservice can publish a handful of profiles or several hundred. **Related**: [Core Concepts Overview](/nim/metadata-api/about/core-concepts) Profile identifier The unique identifier for a profile, recorded as `profile_id`, and the value you supply at deployment time. Treat it as opaque: compare it for equality, and never parse it or derive meaning from its structure. **Related**: [Current Limitations](/nim/metadata-api/reference/limitations) ## R Browse terms starting with **R**. Resource identifier The slash-separated repository path that identifies a NIM microservice container, recorded as `resourceId`. It takes the form `{org}/{repo-name}` or `{org}/{team-name}/{repo-name}`, and it must not contain a colon. ```text nim/meta/llama-3.1-8b-instruct ``` **Related**: [Prerequisites](/nim/metadata-api/get-started/prerequisites) ## T Browse terms starting with **T**. Tag The container tag, exactly as it appears in the catalog, such as `1.2.0` or `latest`. Metadata is stored per tag, so the presence of metadata for one tag says nothing about another. **Related**: [Endpoints](/nim/metadata-api/reference/endpoints) Tensor parallel size The number of GPUs a profile shards the model across tensor-wise, recorded as `tensor_parallel_size`. **Related**: [Choose a Profile for Your Hardware](/nim/metadata-api/guides/choose-a-profile) Tested GPU devices The PCI identifiers a profile has been validated on, recorded as `tested_gpu_devices`. An empty array means the profile was explicitly tested on nothing, and an absent field means no testing information was recorded. **Related**: [Core Concepts Overview](/nim/metadata-api/about/core-concepts) Throughput A recorded throughput figure for a profile. Units and measurement conditions are not standardized, so figures are not comparable across NIM microservices. **Related**: [Current Limitations](/nim/metadata-api/reference/limitations) ## V Browse terms starting with **V**. vRAM floor The minimum vRAM a profile requires per GPU, recorded as `min_vram_per_device_gb`. The value is per device rather than a total across devices, and it is the primary hardware-fit field. **Related**: [Response Fields](/nim/metadata-api/reference/response-fields) ## W Browse terms starting with **W**. Workspace hash A digest over the workspace contents of a profile, recorded as `workspace_hash`. Use it to verify supply-chain integrity after download. This field is optional today, so do not assume its presence. **Related**: [Current Limitations](/nim/metadata-api/reference/limitations) ## Related Documentation * [Core Concepts Overview](/nim/metadata-api/about/core-concepts) * [Response Fields](/nim/metadata-api/reference/response-fields) * [Resources Overview](/nim/metadata-api/resources/resources-overview)