2024 NVIDIA embedding snapshot. Rechecked: HF card still listed. Not a 2026 MTEB #1 census.

Previous NVIDIA Llama 3.1 Nemotron 70B Instruct snapshot. Rechecked: live open path on this site is Nemotron 3.5 Lightning. Not a 2026 default.

NVIDIA's efficient open-weight 30B MoE hybrid model with 3B active parameters, 1M-token context, and single-GPU deployment for local reasoning and coding.

Previous Mistral Nemo 12B snapshot. Rechecked: leftover NVIDIA 128k path. Live catalog is Medium 3.5 / Small 4 / Large 3.

Previous NVIDIA nv-rerankqa-mistral-4b-v3 snapshot. Rechecked: leftover HF card, not a 2026 rerank default. Drop leftover 32768 / TensorRT crown.

NVIDIA's open-source LLM vulnerability scanner with dozens of plugins and thousands of prompts for probing jailbreaks, prompt injection, and data leakage.

NVIDIA's open-source toolkit for adding programmable guardrails to LLM conversational applications, with Colang flows for input, dialog, retrieval, and output rails.

NVIDIA CUDA MCP server and Nsight Copilot for coding agents. Hosted docs MCP plus an Apache 2.0 self-hosted blueprint.