At a glance

Which variant should I pick?

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:

1. Router gate-values — how often and how strongly the router selects each expert
2. 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

---

Benchmark Results

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

Coding (EvalPlus, greedy, 0-shot)

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

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

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

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

---

Memory Footprint

---

Usage

python
Copy code
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:

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

---

Reproducing

bash
Copy code
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.

bibtex
Copy code
@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}
}

Sponsors

Made possible by NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle.