Instructions to use RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged with Transformers:

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

pipe = pipeline("image-text-to-text", model="RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged")
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("RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged")
model = AutoModelForMultimodalLM.from_pretrained("RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged", 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 RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged",
		"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/RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged

SGLang

How to use RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged 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 "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged" \
    --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": "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged",
		"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 "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged" \
        --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": "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged",
		"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 RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged with Docker Model Runner:
```
docker model run hf.co/RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged
```

Qwen3.5-35B-A3B-Base-8be64d30-Merged

This repository contains the Final Merged checkpoint from Together AI fine-tuning job ft-b042b356-9d1d, based on Qwen/Qwen3.5-35B-A3B-Base.

The weights are published in the standard Hugging Face Transformers format as 14 Safetensors shards with the accompanying config.json, tokenizer files, processor configuration, and shard index. The model configuration retains the Qwen-compatible chat template supplied in tokenizer_config.json.

Model overview

Property	Value
Base model	`Qwen/Qwen3.5-35B-A3B-Base`
Checkpoint	Together AI Final Merged, step 40
Architecture	`Qwen3_5MoeForConditionalGeneration`
Format	Hugging Face Transformers / Safetensors
Pipeline	Image-text-to-text

Loading with Transformers

from transformers import AutoProcessor, Qwen3_5MoeForConditionalGeneration

model_id = "RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged"
processor = AutoProcessor.from_pretrained(model_id)
model = Qwen3_5MoeForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

License

This checkpoint follows the Apache-2.0 license of its base model. See the base model repository for its model documentation and license information.

Downloads last month: -

Safetensors

Model size

36B params

Tensor type

BF16

F32

Model tree for RoseG/Qwen3.5-35B-A3B-Base-8be64d30-Merged

Base model

Qwen/Qwen3.5-35B-A3B-Base

Finetuned

(71)

this model