REPOGEO REPORT · LITE
horseee/LLM-Pruner
Default branch main · commit 128a07d9 · scanned 5/19/2026, 7:07:56 AM
GitHub: 1,127 stars · 132 forks
Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.
2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).
Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface horseee/LLM-Pruner, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.
Action plan — copy-paste fixes
3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.
- highreadme#1Reposition README's opening to highlight its tool nature
Why:
CURRENTThe README starts with the paper title 'On the Structural Pruning of Large Language Models' under the main project title.
COPY-PASTE FIXAdd a concise, tool-oriented sentence immediately after the main project title, e.g., 'LLM-Pruner is a comprehensive framework for the structural pruning of Large Language Models, supporting various architectures like Llama-3/3.1, Llama-2, BLOOM, and Vicuna.'
- mediumreadme#2Add a 'Key Features' or 'Why LLM-Pruner' section highlighting differentiators
Why:
CURRENTThe 'Why LLM-Pruner' section lists 'Task-agnostic compression,' 'Less training corpus,' and 'Efficient compression.'
COPY-PASTE FIXExpand the 'Why LLM-Pruner' section to explicitly state: '- [x] **Gradient-free and Data-free Structural Pruning**: Unlike many methods, LLM-Pruner identifies redundant structures without requiring gradients or extensive datasets for calibration/fine-tuning.'
- lowtopics#3Add 'llm-optimization' and 'model-optimization' topics
Why:
CURRENTbaichuan, bloom, chatglm, compression, language-model, llama, llama-2, llama3, llm, neurips-2023, pruning, pruning-algorithms, vicuna
COPY-PASTE FIXbaichuan, bloom, chatglm, compression, language-model, llama, llama-2, llama3, llm, llm-optimization, model-optimization, neurips-2023, pruning, pruning-algorithms, vicuna
Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash
Category visibility — the real GEO test
Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?
Same questions for every model — switch tabs to compare answers and rankings.
- DistilBERT · recommended 2×
- TinyBERT · recommended 2×
- TensorFlow Model Optimization Toolkit · recommended 2×
- bitsandbytes · recommended 1×
- ONNX Runtime · recommended 1×
- CATEGORY QUERYHow can I reduce the size of large language models for efficient deployment?you: not recommendedAI recommended (in order):
- bitsandbytes
- ONNX Runtime
- PyTorch native quantization
- Hugging Face Transformers
- DistilBERT
- TinyBERT
- PaddlePaddle's PaddleSlim
- PyTorch native pruning
- TensorFlow Model Optimization Toolkit
- ALBERT
- Evolved Transformer
- DistilBERT
- TinyBERT
- MobileBERT
- Phi-2
- Gemma 2B/7B
- LoRA
- QLoRA
- AdaLoRA
AI recommended 19 alternatives but never named horseee/LLM-Pruner. This is the gap to close.
Show full AI answer
- CATEGORY QUERYWhat tools are available for structurally pruning large language models to optimize performance?you: not recommendedAI recommended (in order):
- Hugging Face Optimum
- NVIDIA/apex (NVIDIA/apex)
- Intel Neural Compressor
- PyTorch Pruning Utilities
- TensorFlow Model Optimization Toolkit
- OpenVINO Post-training Optimization Toolkit
AI recommended 6 alternatives but never named horseee/LLM-Pruner. This is the gap to close.
Show full AI answer
Objective checks
Rule-based audits of metadata signals AI engines weight most.
- Metadata completenesspass
- README presencepass
Self-mention check
Does AI even know your repo exists when asked about it directly?
- Compared to common alternatives in this category, what is the core differentiator of horseee/LLM-Pruner?passAI named horseee/LLM-Pruner explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- If a team adopts horseee/LLM-Pruner in production, what risks or prerequisites should they evaluate first?passAI named horseee/LLM-Pruner explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
- In one sentence, what problem does the repo horseee/LLM-Pruner solve, and who is the primary audience?passAI named horseee/LLM-Pruner explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
Embed your GEO score
Drop this badge into the README of horseee/LLM-Pruner. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.
Live preview[](https://repogeo.com/en/r/horseee/LLM-Pruner)<a href="https://repogeo.com/en/r/horseee/LLM-Pruner"><img src="https://repogeo.com/badge/horseee/LLM-Pruner.svg" alt="RepoGEO" /></a>Subscribe to Pro for deep diagnoses
horseee/LLM-Pruner — Lite scans stay free; this card itemizes Pro deep limits vs Lite.
- Deep reports10 / month
- Brand-free category queries5 vs 2 in Lite
- Prioritized action items8 vs 3 in Lite