Llama 3.2 1B Qwen3.8 27B Draft is an open-source language model by nvidia. Features: 27b LLM, VRAM: 3GB, Context: 128K, License: other.
| LLM Name | Llama 3.2 1B Qwen3.8 27B Draft |
| Repository π€ | https://huggingface.co/nvidia/Llama-3.2-1B-Qwen3.8-27B-Draft |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 3 GB |
| Updated | 2026-11-19 |
| Maintainer | nvidia |
| Model Type | llama |
| Model Files | |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 5.14.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 248320 |
| Errors | replace |