LLM Name | Llama 3 3 Nemotron Super 49B V1 |
Repository ๐ค | https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1 |
Model Size | 49b |
Required VRAM | 100.2 GB |
Updated | 2025-06-10 |
Maintainer | nvidia |
Model Type | nemotron-nas |
Model Files | |
Supported Languages | en |
Model Architecture | DeciLMForCausalLM |
License | other |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.48.3 |
Tokenizer Class | PreTrainedTokenizerFast |
Vocabulary Size | 128256 |
Torch Data Type | bfloat16 |
Model |
Likes |
Downloads |
VRAM |
---|---|---|---|
...3 3 Nemotron Super 49B V1 GGUF | 5 | 22703 | 11 GB |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
... 3 3 Nemotron Super 49B V1 FP8 | 128K / 52 GB | 2411 | 7 |
...3 3 Nemotron Super 49B V1 GGUF | 128K / 11.4 GB | 22703 | 5 |
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