Benchmarked REAP checkpoints with >=500 all-time downloads. GLM/Qwen/MiniMax/DeepSeek/Kimi/gemma. • 20 items • Updated • 10
Support this work → · X · GitHub · REAP paper · Cerebras REAP
Qwen3.6-28B
REAP-pruned Qwen/Qwen3.6-35B-A3B.
At a glance
| Base model | Qwen/Qwen3.6-35B-A3B |
| Format | BF16 |
| Total params | 28B |
| Active / token | — |
| Experts / layer | — |
| Layers | — |
| Hidden size | — |
| Context | — |
| On-disk size | 56 GB |
Which variant should I pick?
| Variant | Format | Link |
|---|---|---|
Qwen3.6-28B (this) |
BF16 | link |
Qwen3.6-28B-GGUF |
GGUF | link |
Qwen3.6-35B-GGUF |
GGUF | link |
Please support my work: https://donate.sybilsolutions.ai
Qwen3.6-28B-REAP20-Opus-A3B
A 20%-expert-pruned + Opus-trace fine-tuned variant of Qwen/Qwen3.6-35B-A3B, produced via Cerebras REAP (Router-weighted Expert Activation Pruning, arXiv:2510.13999) followed by LoRA SFT on public Claude Opus reasoning traces.
Headline numbers
| Metric | Base Qwen3.6-35B-A3B | This model (20% REAP + Opus SFT) | Δ |
|---|---|---|---|
| MMLU (200-sample lite) | {{MMLU_BASE}} |
{{MMLU_THIS}} |
{{MMLU_DELTA}} |
| GSM8K (100-sample lite) | {{GSM_BASE}} |
{{GSM_THIS}} |
{{GSM_DELTA}} |
| HumanEval (50 parse-rate) | {{HE_BASE}} |
{{HE_THIS}} |
{{HE_DELTA}} |
| Structured JSON parse (20) | {{JSON_BASE}} |
{{JSON_THIS}} |
{{JSON_DELTA}} |
| Mermaid render (10) | {{MERM_BASE}} |
{{MERM_THIS}} |
{{MERM_DELTA}} |
| AdvBench refusal (32) | {{REFUSE_BASE}} |
{{REFUSE_THIS}} |
{{REFUSE_DELTA}} |
Architecture
- Base: Qwen3.6-35B-A3B (40 layers, 256 experts/layer, 8 routed + 1 shared active,
qwen3_5_moe) - After 20% REAP: 205 experts/layer kept, 51 experts/layer pruned → 3B active**
- Fine-tune: LoRA rank 32, α 64 on
q,k,v,o,gate,up,downprojections. bf16 weights after merge.
Pipeline
- Calibration merge — 5,000 stratified samples from:
/Users/sero/.../reap-expert-swap/dataset/calibration-20k.jsonl(general, coding, reasoning, etc.)0xSero/structured-outputs-calibration-v1(JSON / Mermaid / schema)
- REAP observation (this fork's Qwen3_5Moe-aware observer, multi-GPU layerwise on 8× A100-40GB): {{OBS_DURATION}}
- REAP prune @ 20% using
reapsaliency metric, renormalized router weights, seed 42. - Opus-trace SFT via LLaMA-Factory + DeepSpeed ZeRO-3 (8× A100). LoRA 2 epochs on
nohurry/Opus-4.6-Reasoning-3000x-filtered(2,326 reasoning trajectories with explicit<think>…</think>\nanswerstructure). - GGUF — bf16, Q8_0, Q6_K, Q5_K_M, Q4_K_M with imatrix from merged calibration.
Sidecar observations
REAP observation artifacts live in the separate dataset repo
0xSero/qwen3.6-35b-a3b-reap-observations.
Known limitations
- Refusal behavior follows the base model plus Opus SFT; no explicit abliteration was applied in this release. The model will refuse straight adversarial probes at roughly base-model rates.
- Reasoning quality on GSM8K-style problems depends on the
<think>chain-of-thought; short max-tokens limits hurt accuracy. - Structured-output calibration is oversampled vs. base mix (JSON/Mermaid experts preferentially retained).
License
Apache 2.0, inherited from base model. This checkpoint is a derivative work; please preserve attribution.
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}
}
Sponsors
Made possible by NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle.
- Downloads last month
- 1,142
Safetensors
Model size
28B params
Tensor type
BF16
·
Model tree for 0xSero/Qwen3.6-28B
Base model
Qwen/Qwen3.6-35B-A3B