Experimental — Near-lossless MoE pruning with proprietary router optimization.
15.6% of experts removed with only -1pp quality loss, achieved through GOBA-AI-Labs' Zerobias router optimization technique.
| Property | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Total Parameters | ~16.5B |
| Active Parameters | 3.6B per token |
| Experts per Layer | 27 (from 32, uniform) |
| MoE Layers | 24 |
| Routing | Top-4, sigmoid activation, bias-optimized |
| Context Length | 128K tokens |
| Quantization | Q4_K_M |
| License | Apache 2.0 |
| Benchmark | Original (32 experts) | 28x (standard) | 27x Zerobias |
|---|---|---|---|
| MMLU (0-shot, 100Q) | 78% | 78% | 77% (-1pp) |
| GSM8K (0-shot, 50Q) | — | 92% | 84% |
Standard MoE pruning at this compression level causes a sharp quality cliff (-10pp). GOBA-AI-Labs' Zerobias technique recovers most of the lost quality, turning a -10pp cliff into only -1pp.
This is an experimental release demonstrating the technique. For production use, we recommend the 28x model which achieves lossless compression.
| Metric | Original | 28x | 27x Zerobias |
|---|---|---|---|
| File Size | 11.67 GB | 10.40 GB | ~9.4 GB |
| Experts/Layer | 32 | 28 | 27 |
| Size Reduction | — | -10.9% | -19.5% |
This model uses uniform expert counts and is fully compatible with llama.cpp:
llama-server -m PrunedHub-GPT-OSS-20B-27x-Zerobias-Q4_K_M.gguf --port 8090 -ngl 99 -c 4096
Also supported by moe-stream, which offers GPU-resident inference and OpenAI-compatible HTTP API:
# CLI inference
moe-stream PrunedHub-GPT-OSS-20B-27x-Zerobias-Q4_K_M.gguf 512 \
--prompt "Explain quantum computing" --stream
# OpenAI-compatible HTTP server
moe-stream-server --model PrunedHub-GPT-OSS-20B-27x-Zerobias-Q4_K_M.gguf --port 11434
@misc{goba-ai-labs-prunedhub-gptoss-27x-zerobias,
title={PrunedHub GPT-OSS-20B-27x-Zerobias: Near-Lossless MoE Pruning with Router Optimization},
author={GOBA-AI-Labs},
year={2026},
url={https://huggingface.co/GOBA-AI-Labs/PrunedHub-GPT-OSS-20B-27x-Zerobias}
}
openai/gpt-oss-20b