Instructions to use rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included with Transformers:

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

pipe = pipeline("image-text-to-text", model="rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included")
model = AutoModelForImageTextToText.from_pretrained("rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included")
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

vLLM

How to use rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included

SGLang

How to use rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included 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 "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included" \
    --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": "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included" \
        --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": "rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included with Docker Model Runner:
```
docker model run hf.co/rdtand/Qwen3.5-27B-NVFP4-DeltaNet-Included
```

rdtand commited on Apr 6

Commit

d6829ee

verified ·

1 Parent(s): b245dda

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -40,6 +40,17 @@ Measured with vLLM 0.19.1 + FlashInfer 0.6.7, CUTLASS W4A4 backend, no MTP:
 The speedup comes from eliminating ~5 GB of BF16 weight loads per token for the DeltaNet layers, replacing them with ~1.4 GB of FP4 loads.
 ## Quantization details
 - **Method**: llm-compressor `oneshot` with calibrated NVFP4 (W4A4)

 The speedup comes from eliminating ~5 GB of BF16 weight loads per token for the DeltaNet layers, replacing them with ~1.4 GB of FP4 loads.
+## Quality benchmarks (0-shot, 200-sample subsets)
+| Benchmark | Metric | This checkpoint | BF16 typical | Recovery |
+|---|---|---|---|---|
+| **ARC-Challenge** | acc_norm | **63.5%** | ~66% | ~96% |
+| **HellaSwag** | acc_norm | **74.0%** | ~78% | ~95% |
+| **TruthfulQA MC2** | acc | **54.2%** | ~55% | ~99% |
+| **Winogrande** | acc | **51.5%** | ~52% | ~99% |
+95-99% quality recovery across knowledge and reasoning benchmarks. Quantizing the DeltaNet linear attention layers to FP4 is near-lossless.
 ## Quantization details
 - **Method**: llm-compressor `oneshot` with calibrated NVFP4 (W4A4)