Latest Content
Qwen3 Coder 30B A3B Instruct icon

Qwen3 Coder 30B A3B Instruct

NVIDIA
Qwen3 Coder 30B A3B Instruct is a Mixture-of-Experts coding-focused language model optimized for agentic development workflows and repository-scale reasoning. It features 30.5B total parameters with ~3.3B active, using 128 experts with 8 selected per token across a 48-layer architecture with 2,048 hidden size and 32 attention heads (GQA with 4 KV heads). Supporting a native 256K context window, extendable to 1M, it delivers strong agentic tool calling, structured function execution, and high performance across coding and browser-based tasks.
TypeMoE LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+5 more
Release Date01 January, 2025
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 VLLM_USE_FLASHINFER_MOE_FP16=1 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 vllm/vllm-openai:v0.19.1 
 Qwen/Qwen3-Coder-30B-A3B-Instruct 
  --tensor-parallel-size 8 
 --enable-expert-parallel 
 --max-model-len auto 
  --max-num-batched-tokens 65536 
 --gpu-memory-utilization 0.95 
 --tool-call-parser qwen3_coder 
 --enable-auto-tool-choice 
 --max-num-seqs 1024 
 --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