NVIDIA Nemotron 3 Nano 4B FP8 is an open-source language model by unsloth. Features: 4b LLM, VRAM: 10.6GB, Context: 256K, License: other.
| LLM Name | NVIDIA Nemotron 3 Nano 4B FP8 |
| Repository ๐ค | https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B-FP8 |
| Base Model(s) | |
| Model Size | 4b |
| Required VRAM | 10.6 GB |
| Updated | 2026-03-27 |
| Maintainer | unsloth |
| Model Type | nemotron_h |
| Model Files | |
| Supported Languages | en |
| Model Architecture | NemotronHForCausalLM |
| License | other |
| Context Length | 262144 |
| Model Max Length | 262144 |
| Transformers Version | 4.53.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 131072 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| NVIDIA Nemotron 3 Nano 4B FP8 | 256K / 5.3 GB | 7804 | 13 |
| Nemotron H 4B Instruct 128K | 128K / 9 GB | 79823 | 9 |
๐ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐