Qwen3-Coder-30B-A3B-Instruct-NVFP4

vllm serve kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 \
  --quantization modelopt \
  --trust-remote-code \
  --max-model-len 32768

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4",
    device_map="auto",
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4"
)

{
  "source_model": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
  "quantization": "NVFP4",
  "tool": "nvidia-modelopt 0.41.0",
  "export_method": "save_pretrained_manual",
  "calib_size": 512,
  "calib_dataset": "synthetic-random",
  "hardware": "NVIDIA GB10 (Blackwell)",
  "elapsed_sec": 472
}