Latest Content
DeepSeek R1 Distill Qwen 1.5B icon

DeepSeek R1 Distill Qwen 1.5B

NVIDIA
DeepSeek R1 Distill Qwen 1.5B is a lightweight dense reasoning-focused language model developed by DeepSeek AI through distillation from the larger DeepSeek-R1 model. It features a 1.5B parameter transformer architecture with 28 layers, 12 attention heads, and a 1,536 hidden size, built on the Qwen2 architecture and fine-tuned using reasoning traces generated by DeepSeek-R1. The model transfers core reasoning behaviors into a compact efficient model optimized for mathematics, coding, and logical analysis, supporting a 128K token context window for extended reasoning tasks.
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-Qwen-1.5B 
 --host 0.0.0.0 
 --port 8000 
 --max-running-requests 1024 \ --tp 4 
 --max-prefill-tokens 65536 
 --enable-piecewise-cuda-graph 
 --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
How to Deploy DeepSeek R1 Distill Qwen 1.5B on NVIDIA GPUs | Vultr Docs