I am a personal developer using NVIDIA NIM for local inference on my RTX 4070 Ti Super (16GB VRAM). I have successfully registered for the free NVIDIA Developer Program and generated an NGC Personal API Key.
`docker login` to `nvcr.io` works, but when I try to pull NIM containers (e.g., `nvcr.io/nvidia/nim/gpt-oss-20b:latest`), I get `Access Denied`.
Based on community discussions, this seems to be due to my personal organization missing the “Public API Endpoints” permission.
I would like to request access to the following models for local deployment on my RTX 4070 Ti Super (16GB VRAM):
- meta/llama-3.1-8b-instruct
- openai/gpt-oss-20b
- microsoft/phi-3-mini-4k-instruct
- mistralai/mistral-7b-instruct
- qwen/qwen2.5-7b-instruct
- qwen/qwen2.5-14b-instruct
- nvidia/nemotron-3-nano-30b-a3b
Could you please enable the “Public API Endpoints” permission for my personal organization so I can authenticate and pull these NIM containers for local inference?
I am a personal developer using NVIDIA NIM for local inference on my RTX 4070 Ti Super (16GB VRAM). I have successfully registered for the free NVIDIA Developer Program and generated an NGC Personal API Key.
`docker login` to `nvcr.io` works, but when I try to pull NIM containers (e.g., `nvcr.io/nvidia/nim/gpt-oss-20b:latest`), I get `Access Denied`.
Based on community discussions, this seems to be due to my personal organization missing the “Public API Endpoints” permission.
I would like to request access to the following models for local deployment on my RTX 4070 Ti Super (16GB VRAM):
- meta/llama-3.1-8b-instruct
- openai/gpt-oss-20b
- microsoft/phi-3-mini-4k-instruct
- mistralai/mistral-7b-instruct
- qwen/qwen2.5-7b-instruct
- qwen/qwen2.5-14b-instruct
- nvidia/nemotron-3-nano-30b-a3b
Could you please enable the “Public API Endpoints” permission for my personal organization so I can authenticate and pull these NIM containers for local inference?