LLM EXPLORER 67,808 MODELS INDEXED

Llama 3.2 1B Qwen3.8 27B Draft by nvidia

By nvidia · 232 downloads

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.

  Arxiv:2407.21783 Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.8-27b   Conversational   Draft   Llama   Llama3.2   Model optimizer   Modelopt   Nvidia   Qwen3.8   Region:us   Safetensors

Llama 3.2 1B Qwen3.8 27B Draft Parameters and Internals

LLM NameLlama 3.2 1B Qwen3.8 27B Draft
Repository πŸ€—https://huggingface.co/nvidia/Llama-3.2-1B-Qwen3.8-27B-Draft 
Base Model(s)  meta-llama/Llama-3.2-1B   Qwen/Qwen3.8-27B   meta-llama/Llama-3.2-1B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM3 GB
Updated2026-11-19
Maintainernvidia
Model Typellama
Model Files  3.0 GB
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace