Model ID
meta-llama/Llama-3.1-405B
Capabilities
Llama 3.1 405B
Llama 3.1 405B is a large-scale multilingual dense transformer language model designed for advanced reasoning, large-context processing, and enterprise AI workloads. The model features a 405B parameter architecture with 126 transformer layers, 128 attention heads, and a 16,384 hidden size, leveraging Grouped Query Attention (GQA) for efficient large-scale inference. It supports up to a 128K token context window with RoPE scaling for extended context understanding. Optimized for multilingual text and code generation, it is designed for research, large-scale AI systems, and high-performance LLM deployments.
About this model
Llama 3.1 405B is a large-scale multilingual dense transformer language model designed for advanced reasoning, large-context processing, and enterprise AI workloads. The model features a 405B parameter architecture with 126 transformer layers, 128 attention heads, and a 16,384 hidden size, leveraging Grouped Query Attention (GQA) for efficient large-scale inference. It supports up to a 128K token context window with RoPE scaling for extended context understanding. Optimized for multilingual text and code generation, it is designed for research, large-scale AI systems, and high-performance LLM deployments.
Model specifications and capabilities are published by the model author and reproduced here from HF Model Card (meta-llama/Llama-3.1-405B). Released under Llama3.1. Further reading: Blog
Deploy Private Inference Endpoint
Choose your hardware and inference engine to get deployment commands and performance benchmarks tailored to your infrastructure
Hardware
MI325X
2,048 GB
B200
1,440 GB
Engine
vLLM
SGLang
Deployment code
Access Restricted
Enter your email to get access to this content
Performance under load
Tokens/s (total)
Benchmarks measured by Vultr on MI325X · vLLM. Throughput and latency vary with concurrency, input length and engine configuration, so treat these as a comparison baseline, not a service guarantee.
AMD Instinct MI325X
Unlock Next-Generation AI Power on Vultr Cloud GPU