Instructions to use timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16")
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("timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16")
model = AutoModelForMultimodalLM.from_pretrained("timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16", 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 timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16",
		"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/timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16

SGLang

How to use timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16 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 "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16" \
    --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": "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16",
		"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 "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16" \
        --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": "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16",
		"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 timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16 with Docker Model Runner:
```
docker model run hf.co/timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16
```

Qwen3.8-27B-Opus-Reasoning-Control-BF16 / manifests /artifact-manifest.json

timteh673

Publish release card, license, benchmarks, and integrity manifests

cc8fe65 verified about 1 month ago

Raw History Blame Contribute Delete

4.15 kB

	{
	"base_model": "Qwen/Qwen3.8-27B",
	"excluded_source_entries": [
	{
	"path": "merge-report.json",
	"reason": "Internal merge receipt contains local paths; public integrity metadata is supplied separately."
	}
	],
	"file_count": 20,
	"files": [
	{
	"path": "chat_template.jinja",
	"sha256": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041",
	"size": 8952
	},
	{
	"path": "config.json",
	"sha256": "4c95af1d45132ead5b63e540f08f32a351e20512e62438a3a78faf9881d1e7dc",
	"size": 3688
	},
	{
	"path": "generation_config.json",
	"sha256": "b8eb74d15e0a56623d00ccd14950a4bb87fabbf84b5cc030dcc904b899fb1eb5",
	"size": 214
	},
	{
	"path": "model-00001-of-00012.safetensors",
	"sha256": "54d83c1d36631de231876217a8e0c2483eccee8746369a482b79442bdfc5d958",
	"size": 2542796928
	},
	{
	"path": "model-00002-of-00012.safetensors",
	"sha256": "fdf7403e5feaade290459946c97b62a878f53a40f6aca80be85a0e996c1f2a09",
	"size": 4842451920
	},
	{
	"path": "model-00003-of-00012.safetensors",
	"sha256": "f6927154cebe9916b67517f1682df7078900dbd0f9042c80357d12d4afd11a53",
	"size": 4965227944
	},
	{
	"path": "model-00004-of-00012.safetensors",
	"sha256": "14ec76c14df273ceb7a260b597f241cb7033898b31befc8c6cffd1eba8375200",
	"size": 4912819264
	},
	{
	"path": "model-00005-of-00012.safetensors",
	"sha256": "9395772c41b20ac2a8dc83b29c61a60bc2744fb5fb8b92934893b2b6820031a3",
	"size": 4986198544
	},
	{
	"path": "model-00006-of-00012.safetensors",
	"sha256": "1f7bc1d5325e5e00feda62d9582064d573fb92d6ec2a54a265f33a4c6e628935",
	"size": 4912819320
	},
	{
	"path": "model-00007-of-00012.safetensors",
	"sha256": "626e69d375a133bc40deb70d28457bde723728884e3e881afa378495436997aa",
	"size": 4932703272
	},
	{
	"path": "model-00008-of-00012.safetensors",
	"sha256": "effe0fde122088f3caf54e42b7dde07f9e56cd52308b5978bbbfcbe1693a6ec2",
	"size": 4966314576
	},
	{
	"path": "model-00009-of-00012.safetensors",
	"sha256": "96cb57f12737f225f80fd2cd37da3ca651861c3be5e8885f9f3db65eef6126ac",
	"size": 4964162248
	},
	{
	"path": "model-00010-of-00012.safetensors",
	"sha256": "f1a8169114ea874728eabeb0b59c65c856fd048ba3ad9f57027d0bdc9c9e2048",
	"size": 4933789824
	},
	{
	"path": "model-00011-of-00012.safetensors",
	"sha256": "bd87144735636d2116ab0869f9da30745f25eb1b55ae10b229cea20d588b5f46",
	"size": 4965228032
	},
	{
	"path": "model-00012-of-00012.safetensors",
	"sha256": "8788ae7f5b7fd70ac5895ef35d70024ef09df2164871bbe1414b6ae544ed4735",
	"size": 2789094896
	},
	{
	"path": "model.safetensors.index.json",
	"sha256": "421d50987269feb928c5d6b8af7f76665be6dbb2501e3a89913b5cef653e8bd6",
	"size": 111996
	},
	{
	"path": "mtp.safetensors",
	"sha256": "90fa0e3eed5a647c035c6df9ecabc416c0f8d573ff84ac12485b085f00a7cdf2",
	"size": 849400424
	},
	{
	"path": "processor_config.json",
	"sha256": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
	"size": 1191
	},
	{
	"path": "tokenizer.json",
	"sha256": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
	"size": 19989325
	},
	{
	"path": "tokenizer_config.json",
	"sha256": "bee8eba30f0eb4af73c0fe2cd06d0f89b657d7819941c438157ec42f7c80ea87",
	"size": 1123
	}
	],
	"format": "BF16 Transformers",
	"hash_algorithm": "sha256",
	"repo_id": "timteh673/Qwen3.8-27B-Opus-Reasoning-Control-BF16",
	"schema_version": 1,
	"scope": "Deliberately published model/runtime payload; generated documentation is outside this checksum scope.",
	"sealed_source_components": [
	{
	"aggregate_sha256": "51979419f5f2fa5860f3cf9b9cd1c54d8e4e8f1585e5a182dea395e3ef3e11e9",
	"bytes": 55583127863,
	"files": 21,
	"name": "BF16 trained control"
	}
	],
	"total_bytes": 55583123681,
	"variant_role": "Full-precision baseline comparator"
	}