Instructions to use Etherll/Qwen3.6-27B-Layerdose with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Etherll/Qwen3.6-27B-Layerdose with Transformers:

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

pipe = pipeline("image-text-to-text", model="Etherll/Qwen3.6-27B-Layerdose")
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("Etherll/Qwen3.6-27B-Layerdose")
model = AutoModelForMultimodalLM.from_pretrained("Etherll/Qwen3.6-27B-Layerdose")
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 Etherll/Qwen3.6-27B-Layerdose with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Etherll/Qwen3.6-27B-Layerdose"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Etherll/Qwen3.6-27B-Layerdose",
		"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/Etherll/Qwen3.6-27B-Layerdose

SGLang

How to use Etherll/Qwen3.6-27B-Layerdose 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 "Etherll/Qwen3.6-27B-Layerdose" \
    --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": "Etherll/Qwen3.6-27B-Layerdose",
		"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 "Etherll/Qwen3.6-27B-Layerdose" \
        --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": "Etherll/Qwen3.6-27B-Layerdose",
		"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 Etherll/Qwen3.6-27B-Layerdose with Docker Model Runner:
```
docker model run hf.co/Etherll/Qwen3.6-27B-Layerdose
```

Qwen3.6-27B Layerdose

LayerDose replacement candidate derived from Qwen/Qwen3.6-27B.

This is not a plain dense checkpoint. Fourteen low-risk linear_attn operators were replaced with compact rank-64 patch modules. The checkpoint stores the reduced model shards plus layerdose_patches.safetensors and layerdose_replacement_manifest.json.

Important Loading Note

A plain AutoModelForCausalLM.from_pretrained() load is not enough to activate the replacements. Load the model, then install the LayerDose patch stack from this model directory:

from layerdose.materialized import install_sublayer_patch_stack

model = ...  # load the Qwen/Qwen3.6-compatible model
install_sublayer_patch_stack(model, "/path/to/Qwen3.6-27B-LayerDose-14LinearAttnRank64")

The GGUF build requires the patched llama.cpp source published with the GGUF repository.

Size

Safetensors directory: about 49 GB on disk
Removed/replaced checkpoint tensor storage: about 3.28 GB before patch tensors
Patch tensor file: about 27 MB

Smoke Results

Post-GGUF smoke checks comparing LayerDose BF16 GGUF to LayerDose Q4_K_M GGUF:

ARC64-95: BF16 0.9375, Q4 0.9375, delta 0.0000
HellaSwag64-95: BF16 0.5625, Q4 0.5625, delta 0.0000
Combined option KL BF16->Q4: 0.008657
LM KL Q4-vs-BF16 on 16 held-out prompts: 0.017597 +/- 0.001729
Same-top-token rate: 96.429%
Greedy generation smoke passed for both BF16 and Q4

This is a smoke-level validation, not a full benchmark suite.

Provenance

The candidate was built by LayerDose using measured coarse-to-fine importance ranking and operator-specific replacement. The selected target was the 14-layer linear-attn replacement candidate.

Downloads last month: 29

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for Etherll/Qwen3.6-27B-Layerdose

Base model

Qwen/Qwen3.6-27B

Finetuned

(260)

this model