Instructions to use davidyu-nv/Qwen3.5-9B-NVFP4-MSE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidyu-nv/Qwen3.5-9B-NVFP4-MSE with Transformers:

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

pipe = pipeline("text-generation", model="davidyu-nv/Qwen3.5-9B-NVFP4-MSE")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("davidyu-nv/Qwen3.5-9B-NVFP4-MSE")
model = AutoModelForMultimodalLM.from_pretrained("davidyu-nv/Qwen3.5-9B-NVFP4-MSE")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use davidyu-nv/Qwen3.5-9B-NVFP4-MSE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidyu-nv/Qwen3.5-9B-NVFP4-MSE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidyu-nv/Qwen3.5-9B-NVFP4-MSE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davidyu-nv/Qwen3.5-9B-NVFP4-MSE

SGLang

How to use davidyu-nv/Qwen3.5-9B-NVFP4-MSE 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 "davidyu-nv/Qwen3.5-9B-NVFP4-MSE" \
    --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": "davidyu-nv/Qwen3.5-9B-NVFP4-MSE",
		"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 "davidyu-nv/Qwen3.5-9B-NVFP4-MSE" \
        --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": "davidyu-nv/Qwen3.5-9B-NVFP4-MSE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use davidyu-nv/Qwen3.5-9B-NVFP4-MSE with Docker Model Runner:
```
docker model run hf.co/davidyu-nv/Qwen3.5-9B-NVFP4-MSE
```

Qwen3.5-9B NVFP4 (MLP-only, MSE calibration)

NVFP4-quantized variant of Qwen/Qwen3.5-9B, produced with NVIDIA Model Optimizer using the nvfp4_mlp_only_mse-fp8_cast_kv recipe from PR #1391.

Quantization details

Component	Precision	Notes
MLP weights (32 layers)	NVFP4 (W4A4, block-16, e2m1 / e4m3 scale)	quantized
`self_attn` QKVO (8 layers)	BF16	preserved
`linear_attn` blocks (24 layers)	BF16	preserved (Mamba-style hybrid layers)
`embed`, `lm_head`, `norm`, `mtp`, `visual`	BF16	preserved
KV cache	FP8	`use_constant_amax: true`
Calibration	MSE + `fp8_scale_sweep: true`	static MLP weight scales

Checkpoint size: 12.38 GB (vs 19.3 GB BF16, −36%).

Evaluation

Δ columns are absolute percentage-point differences vs Qwen/Qwen3.5-9B BF16.

Metric	BF16	This model
MMLU-Pro pass@1	82.89	82.40 (−0.49)
AIME 2025 avg-of-64	67.34	65.36 (−1.98)
AIME 2025 majority@64	90.00	87.78 (−2.22)
LCB pass@3	66.08	68.72 (+2.64)
GPQA avg-of-8	81.06	80.68 (−0.38)
GPQA majority@8	83.84	83.59 (−0.25)
AA-LCR pass@1 [avg-of-3]	56.33	50.67 (−5.66)
AA-LCR pass@3	71.00	66.00 (−5.00)
τ²-bench-telecom pass@1	15.79	12.28 (−3.51)

Eval was run via nemo-evaluator-launcher using the nemo-skills:26.03 container. AA-LCR judge: Qwen3-235B-A22B-Instruct-2507 (Non-Reasoning).

Usage

vLLM

vllm serve davidyu-nv/Qwen3.5-9B-NVFP4-MSE \
  --tensor-parallel-size 2 \
  --data-parallel-size 4 \
  --reasoning-parser qwen3 \
  --max-model-len 131072 \
  --trust-remote-code \
  --disable-custom-all-reduce \
  --no-enable-prefix-caching

For tool-calling workloads (e.g. τ²-bench), also pass:

--enable-auto-tool-choice --tool-call-parser hermes

Container

Tested with nvcr.io/nvstaging/nim/vllm-modelopt:v0.19.1.

License

Apache 2.0, inherited from Qwen/Qwen3.5-9B.

Acknowledgments

Base model: Qwen team
Quantization recipe: NVIDIA Model Optimizer PR #1391

Downloads last month: 23

Safetensors

Model size

7B params

Tensor type

BF16

F8_E4M3

Model tree for davidyu-nv/Qwen3.5-9B-NVFP4-MSE

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(286)

this model