Instructions to use 0xSero/Qwen3.5-28B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xSero/Qwen3.5-28B with Transformers:

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

pipe = pipeline("text-generation", model="0xSero/Qwen3.5-28B")
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("0xSero/Qwen3.5-28B")
model = AutoModelForMultimodalLM.from_pretrained("0xSero/Qwen3.5-28B", 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 0xSero/Qwen3.5-28B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xSero/Qwen3.5-28B"
# 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/Qwen3.5-28B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xSero/Qwen3.5-28B

SGLang

How to use 0xSero/Qwen3.5-28B 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/Qwen3.5-28B" \
    --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/Qwen3.5-28B",
		"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/Qwen3.5-28B" \
        --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/Qwen3.5-28B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xSero/Qwen3.5-28B with Docker Model Runner:
```
docker model run hf.co/0xSero/Qwen3.5-28B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

Qwen3.5-28B

REAP-pruned Qwen/Qwen3.5-35B-A3B.

At a glance


Base model	Qwen/Qwen3.5-35B-A3B
Format	BF16
Total params	28B
Active / token	3B
Experts / layer	—
Layers	—
Hidden size	—
Context	—
On-disk size	57 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` (this)	BF16	link
`Qwen3.5-35B-EXL3-4bpw`	EXL3-4bpw	link
`Qwen3.5-76B`	BF16	link
`Qwen3.5-76B-GGUF`	GGUF	link
`Qwen3.5-88B`	BF16	link
`Qwen3.5-99B`	BF16	link
`Qwen3.5-99B-GGUF`	GGUF	link

This is a 20% expert-pruned version of Qwen/Qwen3.5-35B-A3B, produced using the REAP (Router-weighted Expert Activation Pruning) method from the paper "REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression" (ICLR 2026).

The model retains 205 of 256 experts (~80% of original experts) while remaining competitive on standard benchmarks.

What We Did

Method: REAP Layerwise Pruning

REAP prunes MoE experts by scoring each expert's importance using a combination of:

Router gate-values — how often and how strongly the router selects each expert
Expert activation norms — the magnitude of each expert's output contribution

Router logit weights are renormalized to sum to 1 after pruning (critical for maintaining output scale). Pruning is applied layer-by-layer (layerwise mode).

Calibration Data

Observations were collected over a mixed calibration dataset of 1,000 samples per category:

theblackcat102/evol-codealpaca-v1 (250 samples)
open-r1/Mixture-of-Thoughts[code] (250 samples)
open-r1/Mixture-of-Thoughts[math] (250 samples)
open-r1/Mixture-of-Thoughts[science] (250 samples)

Max sequence length: 4096 tokens. Angular distance measure for expert similarity.

Pruning Config

Parameter	Value
Compression ratio	20% (51 experts removed)
Original experts	256
Remaining experts	205
Pruning method	REAP
Router weight renormalization	✓
Seed	42
Calibration samples	1,000 total

Benchmark Results

All evaluations run with vLLM (tensor-parallel across 8x RTX 3090), greedy decoding, 0-shot.

Coding (EvalPlus, greedy, 0-shot)

Benchmark	Original	Pruned (20%)	Delta
HumanEval (pass@1)	76.2%	73.2%	-3.0%
HumanEval+ (pass@1)	72.0%	70.1%	-1.9%

Multiple Choice / Reasoning (lm-eval, 0-shot, 250 samples/task)

Benchmark	Original	Pruned (20%)	Delta
MMLU	84.34%	80.89%	-3.45%
MMLU - Humanities	82.40%	76.35%	-6.05%
MMLU - Social Sciences	90.04%	88.38%	-1.66%
MMLU - STEM	81.46%	78.88%	-2.58%
MMLU - Other	84.52%	81.05%	-3.47%
ARC-Challenge	60.00%	60.40%	+0.40%
ARC-Easy	84.00%	83.20%	-0.80%
BoolQ	88.00%	89.20%	+1.20%
HellaSwag (norm)	76.40%	75.60%	-0.80%
OpenBookQA (norm)	45.20%	47.20%	+2.00%
RTE	81.20%	82.00%	+0.80%
WinoGrande	77.20%	76.80%	-0.40%

Perplexity (WikiText-2, 10k tokens, llama.cpp)

Model	PPL
Original (256 experts)	6.83
Pruned 20% (205 experts)	9.51

Throughput (4x RTX 3090, TP=4, vLLM, enforce_eager)

Batch Size	Original tok/s	Pruned tok/s	Speedup
1	12.3	12.5	1.02x
4	37.0	36.0	0.97x
8	74.4	70.3	0.95x
16	89.3	86.0	0.96x

Note: throughput speedup is minimal at this compression level with current vLLM routing overhead. The primary benefit is reduced VRAM footprint.

Memory Footprint

Model	Size	Shards
Original	~71 GB (bf16)	14 safetensors
Pruned 20%	~53 GB (bf16)	2 safetensors

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "0xSero/Qwen3.5-35B-A3B-REAP-20pct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "Write a quicksort in Python."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

With vLLM:

vllm serve 0xSero/Qwen3.5-35B-A3B-REAP-20pct \
    --tensor-parallel-size 4 \
    --gpu-memory-utilization 0.9 \
    --max-model-len 32768

Reproducing

git clone https://github.com/cerebras/reap
cd reap
bash scripts/build.sh

python -m reap.layerwise_prune \
    --model_name Qwen/Qwen3.5-35B-A3B \
    --dataset_name "theblackcat102/evol-codealpaca-v1:250,open-r1/Mixture-of-Thoughts[code]:250,open-r1/Mixture-of-Thoughts[math]:250,open-r1/Mixture-of-Thoughts[science]:250" \
    --compression_ratio 0.20 \
    --prune_method reap \
    --seed 42 \
    --renormalize_router_weights true

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}
}