Instructions to use RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3 with Transformers:

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

pipe = pipeline("text-generation", model="RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3")
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("RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3")
model = AutoModelForMultimodalLM.from_pretrained("RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3")
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 RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3

SGLang

How to use RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3 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 "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3" \
    --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": "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3",
		"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 "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3" \
        --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": "RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3 with Docker Model Runner:
```
docker model run hf.co/RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3
```

Qwen3.6-35B-A3B Packed-Qwen BNB4 Pre-REAP Pruned Ratio 0.3

This checkpoint is derived from Qwen/Qwen3.6-35B-A3B using REAP routed-expert pruning with pruning ratio 0.30. It differs from earlier pre-REAP bnb4 experiments by quantizing the packed Qwen routed experts and router during REAP score collection, not only standard nn.Linear modules.

The final checkpoint is saved from the full-precision/BF16 model after pruning. It is not a bitsandbytes-quantized checkpoint.

Pruning setup

Base model: Qwen/Qwen3.6-35B-A3B
Method: REAP routed-expert pruning
Pre-REAP scoring quantization: bitsandbytes 4-bit NF4, BF16 compute, double quantization enabled
Packed-Qwen scoring coverage: standard linear layers plus packed routed experts and router
Pruning ratio: 0.30
Routed experts before pruning: 256 per MoE layer
Routed experts pruned: 76 per MoE layer
Routed experts retained: 180 per MoE layer
num_experts_per_tok: 8
Shared experts: preserved
Calibration samples: 1024
Sequence length: 2048
Seed: 42
Router renormalization: enabled

Notes

REAP saliency was collected with a quantization-aware scoring model, then the quantized scoring model was discarded and the original BF16 checkpoint was reloaded for structural pruning and saving.

Use with Transformers and trust_remote_code=True.

Downloads last month: 5

Safetensors

Model size

26B params

Tensor type

BF16

Model tree for RangerX/Qwen3.6-35B-PreREAP-BNB4-PackedQwen-Pruned-ratio-0.3

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

(154)

this model