Filters
What Can I Run?
Type of Task
Select the type of task you want to perform with the model.
Model quantization level for inference.
Select your hardware configuration to filter models.
Local LLMs Directory
Top LLM Models by Overall Performance
| Rank | Model | Provider | Parameters | Context | Modality | Released |
|---|---|---|---|---|---|---|
- | NVIDIA Nemotron 3 Nano 30B-A3B Nemotron 3 | NVIDIA | 3.5B | 1M | Dec 15, 2025 |