Instructions to use ATinyGreenCell/scadcoder-qwen3.5-9b-v9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ATinyGreenCell/scadcoder-qwen3.5-9b-v9 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ATinyGreenCell/scadcoder-qwen3.5-9b-v9")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ATinyGreenCell/scadcoder-qwen3.5-9b-v9")
model = AutoModelForMultimodalLM.from_pretrained("ATinyGreenCell/scadcoder-qwen3.5-9b-v9", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ATinyGreenCell/scadcoder-qwen3.5-9b-v9 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ATinyGreenCell/scadcoder-qwen3.5-9b-v9"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ATinyGreenCell/scadcoder-qwen3.5-9b-v9",
		"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/ATinyGreenCell/scadcoder-qwen3.5-9b-v9

SGLang

How to use ATinyGreenCell/scadcoder-qwen3.5-9b-v9 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 "ATinyGreenCell/scadcoder-qwen3.5-9b-v9" \
    --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": "ATinyGreenCell/scadcoder-qwen3.5-9b-v9",
		"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 "ATinyGreenCell/scadcoder-qwen3.5-9b-v9" \
        --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": "ATinyGreenCell/scadcoder-qwen3.5-9b-v9",
		"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 ATinyGreenCell/scadcoder-qwen3.5-9b-v9 with Docker Model Runner:
```
docker model run hf.co/ATinyGreenCell/scadcoder-qwen3.5-9b-v9
```

scadcoder-qwen3.5-9b-v9

A LoRA fine-tune of Qwen3.5-9B for parametric bio-lab OpenSCAD, for the Tiiny Pocket Lab (v9).

Base: Qwen/Qwen3.5-9B (arch Qwen3_5ForConditionalGeneration); vision encoder preserved, language layers LoRA-merged to bf16 safetensors.
Run with reasoning/thinking off.

Training data

v9 is v5 plus 869 on-policy repair conversations, each included twice (1,738 rows): v5's own failed first attempts at training prompts that are not Prompt-to-Bench tasks (6,000 attempts at 3,000 prompts; 85.5% passed), each followed by the benchmark's feedback for that attempt and then the reference file, with the failed turn masked from the loss. 724 of the 869 come from Claude Opus distilled descriptions in 14 part families v5 never saw. 12,374 rows, 3 epochs, LoRA rank 32. Details: https://github.com/ATinyGreenCell/prompt-to-bench (§6.4).

Downloads last month: 31

Safetensors

Model size

10B params

Tensor type

BF16

F32

Model tree for ATinyGreenCell/scadcoder-qwen3.5-9b-v9

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(1199)

this model