Lossless MoE Expert Pruning — 12.5% of experts removed with zero quality loss.
Pruned from OpenAI GPT-OSS-20B using GOBA-AI-Labs' proprietary expert optimization methodology.
| Property | Value |
|---|---|
| Base Model | openai/gpt-oss-20b |
| Total Parameters | ~17.5B |
| Active Parameters | 3.6B per token |
| Experts per Layer | 28 (from 32, uniform) |
| MoE Layers | 24 |
| Routing | Top-4, sigmoid activation |
| Context Length | 128K tokens |
| Quantization | Q4_K_M |
| License | Apache 2.0 |
| Benchmark | Original (32 experts) | Pruned (28 experts) | Delta |
|---|---|---|---|
| MMLU (0-shot, 100Q) | 78% | 78% | 0 pp |
| GSM8K (0-shot, 50Q) | 70%* | 92% | — |
| HumanEval (50Q) | 80% | 78% | -2 pp |
| Inference Speed (M4 Pro) | ~55 tok/s | ~55 tok/s | — |
*GSM8K original baseline measured with reasoning budget constraints.
| Metric | Original | Pruned | Savings |
|---|---|---|---|
| File Size | 11.67 GB | 10.40 GB | -10.9% |
| Experts/Layer | 32 | 28 | -12.5% |
| Total Experts | 768 | 672 | -96 experts |
This model uses uniform expert counts and is fully compatible with llama.cpp:
llama-server -m PrunedHub-GPT-OSS-20B-28x-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-28x-Q4_K_M.gguf 512 \
--prompt "Explain quantum computing" --stream
# OpenAI-compatible HTTP server
moe-stream-server --model PrunedHub-GPT-OSS-20B-28x-Q4_K_M.gguf --port 11434
This model was created using GOBA-AI-Labs' expert optimization pipeline:
@misc{goba-ai-labs-prunedhub-gptoss-28x,
title={PrunedHub GPT-OSS-20B-28x: Lossless MoE Expert Pruning},
author={GOBA-AI-Labs},
year={2026},
url={https://huggingface.co/GOBA-AI-Labs/PrunedHub-GPT-OSS-20B-28x}
}
openai/gpt-oss-20b