Latest Content
Phi 4 Mini Instruct icon

Phi 4 Mini Instruct

NVIDIA
Phi-4-mini-instruct is a lightweight dense transformer model designed for efficient multilingual reasoning, instruction-following, and agentic tool-calling in constrained environments. It features 3.8B parameters with 32 layers, 3,072 hidden size, and 24 attention heads with grouped-query attention using 8 key-value heads. The model supports a 128K token context window and uses long RoPE scaling for extended context handling. Trained on 5T tokens with supervised fine-tuning and direct preference optimization, it is optimized for low-latency inference and strong reasoning performance.
TypeDense LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+5 more
Group Release DateDecember 11, 2024
Links
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:v0.5.9 
 python3 -m sglang.launch_server 
 --model-path microsoft/Phi-4-mini-instruct 
 --host 0.0.0.0 
 --port 8000 
 --max-running-requests 1024 
 --max-prefill-tokens 65536 
 --tp 8 
 --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