Instructions to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with Transformers:

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

pipe = pipeline("image-text-to-text", model="bottlecapai/ThinkingCap-Qwen3.8-Flash-Next")
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("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next")
model = AutoModelForMultimodalLM.from_pretrained("bottlecapai/ThinkingCap-Qwen3.8-Flash-Next", 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 bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with vLLM:

Install from pip and serve model

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

SGLang

How to use bottlecapai/ThinkingCap-Qwen3.8-Flash-Next 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 "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next" \
    --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": "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
		"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 "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next" \
        --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": "bottlecapai/ThinkingCap-Qwen3.8-Flash-Next",
		"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 bottlecapai/ThinkingCap-Qwen3.8-Flash-Next with Docker Model Runner:
```
docker model run hf.co/bottlecapai/ThinkingCap-Qwen3.8-Flash-Next
```

Running ThinkingCap on the strata-nvfp4 fork (12 GB GPU) by swapping 372 tensors

by LIOSAM007 - opened 3 days ago

Discussion

LIOSAM007

3 days ago

Thanks for ThinkingCap. We run Qwen3.8-Flash-Next on an RTX 4070 SUPER 12 GB with 96 GB RAM through the strata-nvfp4 fork, and wanted ThinkingCap without a 131 GB download in a format the fork doesn't load. Comparing your BF16 checkpoint with the base showed that only 372 tensors differ (5.84 GB: linear attention in 36 layers, full attention in 12, shared experts in 48), while experts, PLE, router, vision, MTP and embeddings are byte-identical. So we replaced those tensors in the fork's dense files and kept the expert files of the base NVFP4-GPTQ pack.

Against the base on the same day: thinking time -23% on 12 reasoning tasks (12/12 for both), -25% on 8 open questions, -59% on 6 trick questions (12/12 for both); ruIFEval 80.5% vs 78.5% and BigCodeBench-Hard 30 vs 27 (base answers from an earlier day); generation speed unchanged, about 51 tok/s on long answers. One miss: on a small 7-video frame-check task it flagged 2 of 4 clean videos as unsure where the base flagged none. The experts were quantized on the base model's activations, so this is not a clean NVFP4 build of ThinkingCap.

Details and the transplant steps: https://github.com/semenovsas-bit/claude-code-local-brain/tree/main/local-brain

Adamiros

BottleCapAI org 3 days ago

That's a very cool use case. Thank you for sharing!

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