Latest Content
DeepSeek R1 Distill Llama 70B icon

DeepSeek R1 Distill Llama 70B

NVIDIA
DeepSeek-R1-Distill-Llama-70B is a dense reasoning-optimized language model developed by DeepSeek AI through distillation from the larger DeepSeek-R1 model. It features a 70B parameter transformer architecture with 80 layers, 64 attention heads, and an 8,192 hidden size, built on the Llama architecture and fine-tuned using reasoning traces generated by DeepSeek-R1. The model is designed to transfer advanced reasoning behaviors into a smaller dense model, improving performance on mathematics, coding, and logical tasks. It supports a 128K token context window using Llama-3 style RoPE scaling for long-context reasoning and analysis.
TypeDense LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+4 more
Paper/Blog
Paper|Blog|HF Model Card
LicenseMIT

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 deepseek-ai/DeepSeek-R1-Distill-Llama-70B 
 --host 0.0.0.0 
 --port 8000 
 --max-running-requests 1024 \ --tp 8 
 --max-prefill-tokens 65536 
 --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