Instructions to use f3nc3r/BigBang1.1-35B-A3B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use f3nc3r/BigBang1.1-35B-A3B-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="f3nc3r/BigBang1.1-35B-A3B-NPU2")
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("f3nc3r/BigBang1.1-35B-A3B-NPU2")
model = AutoModelForMultimodalLM.from_pretrained("f3nc3r/BigBang1.1-35B-A3B-NPU2", 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 f3nc3r/BigBang1.1-35B-A3B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "f3nc3r/BigBang1.1-35B-A3B-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "f3nc3r/BigBang1.1-35B-A3B-NPU2",
		"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/f3nc3r/BigBang1.1-35B-A3B-NPU2

SGLang

How to use f3nc3r/BigBang1.1-35B-A3B-NPU2 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 "f3nc3r/BigBang1.1-35B-A3B-NPU2" \
    --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": "f3nc3r/BigBang1.1-35B-A3B-NPU2",
		"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 "f3nc3r/BigBang1.1-35B-A3B-NPU2" \
        --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": "f3nc3r/BigBang1.1-35B-A3B-NPU2",
		"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 f3nc3r/BigBang1.1-35B-A3B-NPU2 with Docker Model Runner:
```
docker model run hf.co/f3nc3r/BigBang1.1-35B-A3B-NPU2
```

BigBang1.1-35B-A3B-NPU2 (FastFlowLM / Lemonade NPU2 Quantization)

Quantization & NPU Compatibility Note: This repository contains Q4NX quantized weights converted from mradermacher/BigBang-v1-i1-GGUF to run natively on FastFlowLM (flm) v1.0.3+ and Lemonade on AMD XDNA NPU hardware.

Model Type: Quantized model conversion (NPU Q4NX format)

Parent / Base Model: mradermacher/BigBang-v1-i1-GGUF

Details: Re-quantized with importance matrix (i1) for FastFlowLM v1.0.3+ and Lemonade on AMD XDNA NPU. Configured with verified ChatML EOS stop token handling.

Architecture: BigBang-v1.1 (Qwen3.6 MoE 35B-A3B base with imatrix)

Quantization Format: Q4_K_M (imatrix) / Q4NX

Format: Q4NX (safetensors format with AMD NPU block packing). Note that this is not a standard GGUF file; it is executed natively via flm / Lemonade on AMD Ryzen AI NPUs.

Serving with Lemonade & FastFlowLM

To serve this model via Lemonade or FastFlowLM:

# Pull and run with FLM:
flm pull BigBang1.1-35B-A3B-NPU2
flm serve BigBang1.1-35B-A3B-NPU2 --ctx-len 32768 --port 8001

Or configure via Lemonade:

lemonade run BigBang1.1-35B-A3B-NPU2

Original Model Information (mradermacher/BigBang-v1-i1-GGUF)

Below is the model card from the upstream repository mradermacher/BigBang-v1-i1-GGUF:

About

weighted/imatrix quants of https://huggingface.co/endless-frontier/BigBang-v1

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/BigBang-v1-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link	Type	Size/GB	Notes
GGUF	imatrix	0.3	imatrix file (for creating your own quants)
GGUF	i1-Q2_K	13.3	IQ3_XXS probably better
GGUF	i1-Q3_K_S	15.6	IQ3_XS probably better
GGUF	i1-IQ3_S	15.7	beats Q3_K*
GGUF	i1-IQ3_M	15.9
GGUF	i1-Q3_K_M	17.3	IQ3_S probably better
GGUF	i1-Q3_K_L	18.7	IQ3_M probably better
GGUF	i1-IQ4_XS	19.3
GGUF	i1-Q4_0	20.4	fast, low quality
GGUF	i1-Q4_K_S	20.5	optimal size/speed/quality
GGUF	i1-Q4_K_M	21.8	fast, recommended
GGUF	i1-Q4_1	22.5
GGUF	i1-Q5_K_S	24.7
GGUF	i1-Q5_K_M	25.4
GGUF	i1-Q6_K	29.3	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Downloads last month: 35

Model tree for f3nc3r/BigBang1.1-35B-A3B-NPU2

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

endless-frontier/BigBang-v1

Quantized

mradermacher/BigBang-v1-i1-GGUF

Finetuned

(1)

this model