Latest Content
Gemma 4 E4B IT icon

Gemma 4 E4B IT

NVIDIA
Gemma 4 E4B IT is a multimodal dense transformer model designed for efficient on-device reasoning, coding, and agentic workflows. It features 4.5B effective parameters, around 8B including embeddings, with 42 layers, 2,560 hidden size, and 8 attention heads. The model uses hybrid attention with 512 token sliding window and global layers, supporting up to 128K context with proportional RoPE scaling. It supports text, image, video, and audio with dedicated encoders and is optimized for strong multilingual and multimodal performance.
TypeOmni Model
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+7 more
Release Date02 April, 2026
Links
Blog|HF Model Card
LicenseApache 2.0

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 -it --rm 
 --runtime=nvidia 
 --gpus all 
 --ipc=host 
 --shm-size=128g 
 -p 8000:8000 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 vllm/vllm-openai:gemma4-cu130 
 google/gemma-4-E4B-it 
  --tensor-parallel-size 8 
 --max-model-len auto 
 --max-num-batched-tokens 65536 
  --gpu-memory-utilization 0.95 
  --max-num-seqs 1024 
 --enable-auto-tool-choice 
 --reasoning-parser gemma4 
 --tool-call-parser gemma4 
 --trust-remote-code
Note

Use the vllm/vllm-openai:gemma4 image (or later) for CUDA 12.9 compatibility and ensure vllm[audio] is installed for audio support.

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