12B open-weight LLM by cyankiwi
NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit is an open-weight text-generation model with roughly 12B parameters published by cyankiwi on the Hugging Face Hub. It has 563 downloads. Runs with transformers.
cyankiwi
api
free
Others in the same category, ranked by how often they are opened.