Instructions to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1")
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("DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1")
model = AutoModelForMultimodalLM.from_pretrained("DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

SGLang

How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 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 "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1" \
    --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": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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 "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1" \
        --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": "DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1",
		"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"
						}
					}
				]
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1 with Docker Model Runner:
```
docker model run hf.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
```

Qwen3.8-27B-Cold-Fusion-FF711-Darker-Hero-GAIN-B

#12

by nightmedia - opened Aug 17

Discussion

nightmedia

Aug 17

•

edited Aug 17

This is a merge using this model as a base, and the Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0: a 3.6-based Fable-Fusion-711 that was post-trained by David with the GAIN method.

Here are first the early numbers for this model

Qwen3.8-27B-Cold-Fusion-GAIN-V1.1

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.655,0.838,0.898
q6-hi     0.655,0.832,0.896
mxfp4     0.645,0.833,0.887

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     3.878 ± 0.024    34.74 GB     170

In the merged model, the B is the variant used in the mixing on my end, representing the mix ratio. For this model it is 1.6/0.4 NuSLERP.

Cognitive numbers are solid, and interpolate somewhere between the host and the 3.6 model, gaining significantly on arc and logic over the stock 3.8. I set the reasoning in the template to medium: that can be changed easily in the second line of the template.

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.681,0.855,0.902
mxfp4     0.672,0.848,0.905

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     3.745 ± 0.023   34.74 GB      168

Speed is a bit faster than the caveman 3.8, and here are the definitive metrics for the Qwen3.8-27B in instruct mode, default reasoning:

          arc   arc/e boolq hswag obkqa piqa  wino
mxfp8     0.591,0.782,0.896
q8-hi     0.602,0.779,0.896,0.747,0.446,0.793,0.703
q6-hi     0.602,0.775,0.895,0.748,0.448,0.795,0.710
mxfp4     0.581,0.771,0.889,0.738,0.442,0.798,0.713

Quant     Perplexity      Peak Memory   Tokens/sec
mxfp8     6.090 ± 0.054   34.74 GB      138
mxfp4     5.952 ± 0.051   21.30 GB      148

https://huggingface.co/nightmedia/Qwen3.8-27B-Cold-Fusion-FF711-Darker-Hero-GAIN-B-mxfp8-mlx

nlpguy

Aug 23

What was the merge config?

nightmedia

Aug 23

I usually put it at the bottom of the model card, here is the recipe for this one

models:
  - model: DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1
    parameters:
      weight: 1.6
  - model: DavidAU/Qwen3.6-27B-V1.1-FF711-Darker-Hero-GAIN-H2.0
    parameters:
      weight: 0.4
merge_method: nuslerp
dtype: bfloat16
name: Qwen3.8-27B-Cold-Fusion-FF711-Darker-Hero-GAIN-B

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment