Instructions to use 0xSero/Qwen3.5-76B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/Qwen3.5-76B with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/Qwen3.5-76B")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("0xSero/Qwen3.5-76B")
model = AutoModelForImageTextToText.from_pretrained("0xSero/Qwen3.5-76B")
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

vLLM

How to use 0xSero/Qwen3.5-76B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/Qwen3.5-76B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xSero/Qwen3.5-76B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/Qwen3.5-76B

SGLang

How to use 0xSero/Qwen3.5-76B 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 "0xSero/Qwen3.5-76B" \
    --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": "0xSero/Qwen3.5-76B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "0xSero/Qwen3.5-76B" \
        --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": "0xSero/Qwen3.5-76B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xSero/Qwen3.5-76B with Docker Model Runner:
```
docker model run hf.co/0xSero/Qwen3.5-76B
```

Support this work → · X · GitHub · REAP paper · Cerebras REAP

Qwen3.5-76B

REAP-pruned Qwen/Qwen3.5-122B-A10B.

At a glance


Base model	Qwen/Qwen3.5-122B-A10B
Format	BF16
Total params	76B
Active / token	10B
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	152 GB

Which variant should I pick?

Variant	Format	Link
`Qwen3.5-264B`	BF16	link
`Qwen3.5-264B-FP8`	FP8	link
`Qwen3.5-264B-W4A16`	W4A16	link
`Qwen3.5-28B`	BF16	link
`Qwen3.5-35B-EXL3-4bpw`	EXL3-4bpw	link
`Qwen3.5-76B` (this)	BF16	link
`Qwen3.5-76B-GGUF`	GGUF	link
`Qwen3.5-88B`	BF16	link
`Qwen3.5-99B`	BF16	link
`Qwen3.5-99B-GGUF`	GGUF	link

40% expert-pruned variant of Qwen3.5-122B-A10B using REAP (Routing-Enhanced Activation Pruning).

Model Details

Property	Value
Base Model	Qwen/Qwen3.5-122B-A10B
Architecture	Qwen3.5 MoE (GDN + Full Attention)
Original Experts	256 per layer
Pruned Experts	154 per layer (40% removed)
Active Parameters	~10B per token
Pruning Method	REAP with targeted refusal preservation
Preserve Threshold	80% (super-expert protection)
Calibration	reap-calibration-data-v1 — 23k benchmark-free samples
Maintainer	0xSero
Organization	Sybil Solutions
Project	REAP PR17

Usage

vllm serve 0xSero/Qwen3.5-76B \
  --tensor-parallel-size 4 \
  --enable-expert-parallel \
  --max-model-len 8192 \
  --trust-remote-code \
  --language-model-only \
  --dtype bfloat16

Important: Use --language-model-only flag — this is a text-only checkpoint pruned from the multimodal base model.

What is REAP?

REAP (Routing-Enhanced Activation Pruning) removes the least-activated experts from MoE models while preserving critical capabilities. It uses router activation patterns from a calibration dataset to identify dispensable experts, with special protection for safety-critical behaviors.

License

Same license as the base model (Qwen).

License & citation

License inherited from the base model.

@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}

Model tree for 0xSero/Qwen3.5-76B

Base model

Qwen/Qwen3.5-122B-A10B

Finetuned

(47)

this model

Space using 0xSero/Qwen3.5-76B 1

Collection including 0xSero/Qwen3.5-76B

Qwen — REAP

Collection

REAP-pruned & quantized Qwen3.5 / 3.6 / Coder variants. • 15 items • Updated 2 days ago

Paper for 0xSero/Qwen3.5-76B

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 20

0xSero
/

Qwen3.5-76B