RRepoGEO

REPOGEO REPORT · LITE

noonghunna/club-3090

Default branch master · commit 5ec40c65 · scanned 5/7/2026, 10:03:27 PM

GitHub: 621 stars · 39 forks

AI VISIBILITY SCORE
28 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

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 noonghunna/club-3090, 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.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README H1 and first sentence to clarify purpose

    Why:

    CURRENT
    # club-3090
    
    **Recipes for serving LLMs locally on RTX 3090s.** Multi-engine (vLLM, llama.cpp, SGLang), multi-model, model-agnostic by design.
    COPY-PASTE FIX
    # club-3090: Community Recipes for Serving LLMs on RTX 3090 GPUs
    
    This repository provides **recipes for serving LLMs locally on RTX 3090s.** It's a collection of multi-engine (vLLM, llama.cpp, SGLang), multi-model, and model-agnostic configurations.
  • hightopics#2
    Add relevant topics to the repository

    Why:

    CURRENT
    (none)
    COPY-PASTE FIX
    llm, large-language-models, rtx-3090, gpu-inference, vllm, llama-cpp, sglang, deep-learning, machine-learning, ai-inference
  • lowhomepage#3
    Add the repository URL as the homepage

    Why:

    CURRENT
    (none)
    COPY-PASTE FIX
    https://github.com/noonghunna/club-3090

Category GEO backends resolved for this scan: google/gemini-2.0-flash-001, deepseek/deepseek-chat

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.0-flash-001. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface noonghunna/club-3090
Avg rank
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
TensorRT
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. TensorRT · recommended 1×
  2. vLLM · recommended 1×
  3. Nvidia Triton Inference Server · recommended 1×
  4. ONNX Runtime · recommended 1×
  5. DeepSpeed · recommended 1×
  • CATEGORY QUERY
    How to serve large language models efficiently on consumer-grade RTX 3090 GPUs?
    you: not recommended
    AI recommended (in order):
    1. TensorRT
    2. vLLM
    3. Nvidia Triton Inference Server
    4. ONNX Runtime
    5. DeepSpeed
    6. Optimum
    7. llama.cpp

    AI recommended 7 alternatives but never named noonghunna/club-3090. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Compare LLM serving frameworks for maximizing context and robustness on RTX 3090.
    you: not recommended
    AI recommended (in order):
    1. vLLM (vllm-project/vllm)
    2. NVIDIA TensorRT-LLM (NVIDIA/TensorRT-LLM)
    3. Ray Serve (ray-project/ray)
    4. Triton Inference Server (triton-inference-server/server)
    5. FastServe
    6. ONNX Runtime (microsoft/onnxruntime)
    7. DeepSpeed Inference (microsoft/DeepSpeed)

    AI recommended 7 alternatives but never named noonghunna/club-3090. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

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 noonghunna/club-3090?
    pass
    AI did not name noonghunna/club-3090 — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts noonghunna/club-3090 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named noonghunna/club-3090 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 noonghunna/club-3090 solve, and who is the primary audience?
    pass
    AI named noonghunna/club-3090 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 noonghunna/club-3090. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/noonghunna/club-3090.svg)](https://repogeo.com/en/r/noonghunna/club-3090)
HTML
<a href="https://repogeo.com/en/r/noonghunna/club-3090"><img src="https://repogeo.com/badge/noonghunna/club-3090.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

noonghunna/club-3090 — 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