1.4B open-weight LLM by inference-optimization
Nemotron-3.5-Lightning-1.4B-A0.1B-MTP is an open-weight text-generation model with roughly 1.4B parameters published by inference-optimization on the Hugging Face Hub. It has 464 downloads. Runs with transformers.
inference-optimization
api
free
Others in the same category, ranked by how often they are opened.
