Qwen3 Coder 30B A3B Instruct

Model Overview¶

Qwen3-Coder-30B-A3B-Instruct model maintains impressive performance and efficiency, featuring the following key enhancements:

Significant Performance among open models on Agentic Coding, Agentic Browser-Use, and other foundational coding tasks.
Long-context Capabilities with native support for 256K tokens, extendable up to 1M tokens using Yarn, optimized for repository-scale understanding.
Agentic Coding supporting for most platform such as Qwen Code, CLINE, featuring a specially designed function call format.

Model Architecture¶

Type: Causal Language Model (CLM)
Number of Parameters: 30.5B in total and 3.3B activated
Number of Layers: 48
Number of Attention Heads (GQA): 32 for Q and 4 for KV
Number of Experts: 128
Number of Activated Experts: 8
Context Length: 262,144 natively.
Model Source: Qwen/Qwen3-Coder-30B-A3B-Instruct
License: apache-2.0

QPC Configurations¶

Precision	SoCs / Tensor slicing	NSP-Cores (per SoC)	Full Batch Size	Chunking Prompt Length	Context Length (CL)	QPC URL	QPC Size	QPC Download	Onnx URL	Onnx Download	Generation Date
MXFP6	4	16	1	128	32768	https://dc00tk1pxen80.cloudfront.net/SDK1.21.4.0/Qwen/Qwen3-Coder-30B-A3B-Instruct/Qwen3_Coder_30B_A3B_Instruct_qpc_16cores_1bs_[2048,4096,8192,12288,16384,24576,32768]ccl_4devices_mxfp6_mxint8.tar.gz	51GB	Download	http://qualcom-qpc-models.s3-website-us-east-1.amazonaws.com/SDK1.21.4.0/Qwen/Qwen3-Coder-30B-A3B-Instruct/Qwen3_Coder_30B_A3B_Instruct_ONNX.tar.gz	Download	5-May-2026

Run This Model¶

Download QPCs¶

mkdir -p Qwen/Qwen3-Coder-30B-A3B-Instruct
cd Qwen/Qwen3-Coder-30B-A3B-Instruct

# Download QPC
wget <QPC_Download_URL>
tar xzvf <qpc_filename.tar.gz>

Run QPC¶

Replace QPC_PATH with actual extracted QPC directories.

python3 -m vllm.entrypoints.openai.api_server \
  --host 0.0.0.0 \
  --port <PORT> \
  --model Qwen/Qwen3-Coder-30B-A3B-Instruct \
  --device-group <DEVICE_IDS> \
  --max-model-len <CTX_LEN> \
  --max-seq-len-to-capture <PREFILL_SEQ_LEN> \
  --max-num-seqs <MAX_NUM_SEQS> \
  --quantization mxfp6 \
  --kv-cache-dtype mxint8 \
  --override-qaic-config "num_cores:[num_cores] qpc_path:[qpc_path] ccl_enabled:True comp_ctx_lengths_prefill=[ccl_prefill_values] comp_ctx_lengths_decode=[ccl_decode_values]"

Run Inference¶

Once the server is running, send a request to the OpenAI-compatible endpoint:

curl http://localhost:<PORT>/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
    "messages": [
      {"role": "user", "content": "<PROMPT>"}
    ],
    "max_tokens": 200
  }'

Useful Links¶

Environment Setup