Latest Content
Llama 3.1 8B icon

Llama 3.1 8B

NVIDIA
Llama-3.1-8B is a multilingual dense transformer large language model designed for scalable text generation, reasoning, and dialogue applications. The model features an 8B parameter architecture with 32 transformer layers, 32 attention heads, and a 4,096 hidden size, utilizing Grouped Query Attention (GQA) for efficient inference. It supports up to a 128K token context window with advanced RoPE scaling for long-context processing. Optimized for multilingual text and code generation, it is widely used for conversational AI, developer tools, and production-grade LLM deployments.
TypeDense LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+5 more
Group Release DateJuly 22, 2024
Links
Blog|HF Model Card
LicenseLlama3.1

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE
docker run --gpus all 
 --shm-size 128g 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 --ipc=host 
 lmsysorg/sglang:v0.5.8-cu130 
 python3 -m sglang.launch_server 
 --model-path meta-llama/Llama-3.1-8B 
 --host 0.0.0.0 
 --port 8000 
 --max-prefill-tokens 65536 
 --max-running-requests 1024 
 --tp 8 
 --mem-fraction-static 0.95 
 --trust-remote-code

Model Benchmarks

Each model was tested with a fixed input size and total token volume while increasing concurrency to measure serving performance under load.

ITL vs Concurrency

Time to First Token

Throughput Scaling

Total Tokens/sec vs Avg TTFT

Vultr Cloud GPU

NVIDIA HGX B200

Deploy NVIDIA B200 on Vultr Cloud GPU

Deploy NVIDIA B200 instancesContact Sales