Instructions to use kshitijthakkar/qwen3.5-moe-4.7B-d4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kshitijthakkar/qwen3.5-moe-4.7B-d4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="kshitijthakkar/qwen3.5-moe-4.7B-d4B")
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("kshitijthakkar/qwen3.5-moe-4.7B-d4B")
model = AutoModelForMultimodalLM.from_pretrained("kshitijthakkar/qwen3.5-moe-4.7B-d4B", device_map="auto")
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 kshitijthakkar/qwen3.5-moe-4.7B-d4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kshitijthakkar/qwen3.5-moe-4.7B-d4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kshitijthakkar/qwen3.5-moe-4.7B-d4B",
		"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/kshitijthakkar/qwen3.5-moe-4.7B-d4B

SGLang

How to use kshitijthakkar/qwen3.5-moe-4.7B-d4B 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 "kshitijthakkar/qwen3.5-moe-4.7B-d4B" \
    --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": "kshitijthakkar/qwen3.5-moe-4.7B-d4B",
		"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 "kshitijthakkar/qwen3.5-moe-4.7B-d4B" \
        --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": "kshitijthakkar/qwen3.5-moe-4.7B-d4B",
		"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 kshitijthakkar/qwen3.5-moe-4.7B-d4B with Docker Model Runner:
```
docker model run hf.co/kshitijthakkar/qwen3.5-moe-4.7B-d4B
```

Qwen3.5 MoE 4.54B (from Qwen3.5-4B)

A Qwen3.5 Mixture-of-Experts model created via dual-source weight transfer:

Backbone (attention, embeddings, vision, norms): from Qwen/Qwen3.5-4B
MoE experts (routed + shared): from Qwen/Qwen3.5-35B-A3B (sliced 256->8 experts, bilinear resized)

Model Details

Property	Value
Total Parameters	4,540,002,816 (4.54B)
Active Parameters	3,030,053,376 (3.03B)
Architecture	Qwen3.5 Hybrid MoE
Experts	8 routed + 1 shared, top-2
Hidden Size	2560
Layers	32 (hybrid: DeltaNet + full attention)
Attention	GQA 16Q / 4KV, head_dim=256
Context	262,144 tokens
Vocab	248,320
Dtype	bfloat16

Design

Total MoE FFN parameters are approximately equal to the dense model's FFN parameters. The speed benefit comes from sparsity: only top-2 experts

shared expert are active per token (~1/3 of total FFN).

Most weights are pre-trained (backbone from dense model, experts from 35B-A3B). Only the MoE dimension resize introduces noise, making this model suitable for fine-tuning at nominal cost.

Weight Transfer Sources

Component	Source	Strategy
Embeddings, LM Head	Qwen/Qwen3.5-4B	Exact copy
Attention (Q/K/V/O, norms)	Qwen/Qwen3.5-4B	Exact copy
DeltaNet (linear attention)	Qwen/Qwen3.5-4B	Exact copy
Vision encoder	Qwen/Qwen3.5-4B	Exact copy
Layer norms	Qwen/Qwen3.5-4B	Exact copy
Routed experts	Qwen3.5-35B-A3B	Slice 256->8, bilinear resize
Shared expert	Qwen3.5-35B-A3B	Bilinear resize
Router	Qwen3.5-35B-A3B	Slice + resize

License

Apache 2.0 (following source models)

Downloads last month: 302

Safetensors

Model size

5B params

Tensor type

BF16

Collection including kshitijthakkar/qwen3.5-moe-4.7B-d4B

Qwen3.5 Dense-to-MoE Weight Transfer

Collection

Qwen3.5 MoE models from dual-source weight transfer (dense backbone + 35B-A3B experts). Hybrid DeltaNet + GQA attention. • 6 items • Updated Mar 4 • 1