Instructions to use kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4

SGLang

How to use kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4 with Docker Model Runner:
```
docker model run hf.co/kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4
```

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

NVFP4 (4-bit floating point) quantization of Qwen/Qwen3-Coder-30B-A3B-Instruct, optimized for NVIDIA Blackwell GPUs.

Model Details

Property	Value
Base Model	Qwen/Qwen3-Coder-30B-A3B-Instruct
Architecture	Qwen3MoeForCausalLM (Mixture-of-Experts)
Total Parameters	30B (3B active per token)
Experts	128 per layer
Quantization	NVFP4 (4-bit NV floating point)
KV Cache	FP8 (8-bit float)
Original Precision	BF16
Quantized Size	~57 GB
Quantization Tool	NVIDIA ModelOpt 0.41.0
Calibration	512 samples (synthetic)
Hardware	NVIDIA DGX Spark GB10 (Blackwell)

Quantization Details

Method: Post-training quantization via nvidia-modelopt with NVFP4_DEFAULT_CFG
Weights: 4-bit NV floating point, group size 16
Activations: 4-bit NV floating point, group size 16
KV Cache: FP8 quantized for reduced memory during inference
Excluded layers: lm_head and all MoE router/gate layers (48 total) — these remain in original precision to preserve routing quality
Export method: HuggingFace save_pretrained with manual quantization_config injection (ModelOpt 0.41.0 native export does not yet support Qwen3MoeExperts)

Usage

With vLLM (Recommended)

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

With Transformers

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"
)

Hardware Requirements

Minimum VRAM: ~57 GB (unified memory or dedicated)
Tested on: NVIDIA DGX Spark (GB10, 128 GB unified memory)
Recommended: NVIDIA Blackwell GPUs (GB10, GB200, B200)

Provenance

{
  "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
}

Limitations

This quantization uses synthetic calibration data (random tokens) because the container runs in offline mode. Production-grade quantization with real calibration data (e.g., C4, RedPajama) may yield slightly better quality.
The export uses save_pretrained fallback rather than ModelOpt's native HF checkpoint exporter, since Qwen3MoeExperts is not yet in ModelOpt 0.41.0's export allowlist. The quantization math is identical — only the serialization path differs.
MoE gate/router layers are preserved in original precision by design.

License

This model inherits the Apache 2.0 license from the base Qwen3-Coder-30B-A3B-Instruct model.

Acknowledgments

Qwen Team for the base model
NVIDIA for ModelOpt quantization toolkit

Downloads last month: 26

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Quantized

(146)

this model

Collection including kleinpanic93/Qwen3-Coder-30B-A3B-Instruct-NVFP4

NVIDIA-DGX-Spark

Collection

A collection of models I re-quantized, or distilled, or in some other way altered from the base to achieve a runnable status on one NVIDIA-DGX-Spark. • 2 items • Updated Mar 4