RRepoGEO

REPOGEO REPORT · LITE

cactus-compute/needle

Default branch main · commit 1c6fa930 · scanned 5/21/2026, 6:13:16 AM

GitHub: 2,347 stars · 151 forks

Scan history for this repo

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.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 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 cactus-compute/needle, 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 README H1 to explicitly state it's an LLM

    Why:

    CURRENT
    # Needle
    COPY-PASTE FIX
    # Needle: A 26M Parameter On-Device LLM for Function Calling
  • mediumreadme#2
    Add a concise 'About' section to the README

    Why:

    COPY-PASTE FIX
    ## About Needle

Needle is a highly efficient, 26 million parameter (26M) function call model, distilled from Gemini 3.1. Designed for on-device AI, it runs at high speeds on incredibly small devices and can be finetuned locally on personal computers. It's ideal for applications requiring compact, performant language models.
  • lowreadme#3
    Add a 'Key Features' section emphasizing on-device capabilities

    Why:

    COPY-PASTE FIX
    ## Key Features

*   **Ultra-Compact:** A 26M parameter model, making it one of the smallest function call LLMs available.
*   **On-Device Performance:** Achieves 6000 toks/sec prefill and 1200 decode speed on small hardware.
*   **Local Finetuning:** Easily finetune the model on your personal Mac/PC.
*   **Open Weights & Dataset:** Fully open-source weights and dataset generation for transparency and community contribution.

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.

Recall
0 / 2
0% of queries surface cactus-compute/needle
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
TinyLlama 1.1B
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. TinyLlama 1.1B · recommended 2×
  2. Phi-2 · recommended 2×
  3. Mistral 7B Instruct v0.2 · recommended 1×
  4. Gemma 2B Instruct · recommended 1×
  5. OpenLLaMA 3B/7B · recommended 1×
  • CATEGORY QUERY
    What are efficient, open-source language models for on-device inference on small hardware?
    you: not recommended
    AI recommended (in order):
    1. TinyLlama 1.1B
    2. Phi-2
    3. Mistral 7B Instruct v0.2
    4. Gemma 2B Instruct
    5. OpenLLaMA 3B/7B
    6. Pythia 160M/410M/1B

    AI recommended 6 alternatives but never named cactus-compute/needle. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a compact LLM that can be finetuned locally on a personal computer.
    you: not recommended
    AI recommended (in order):
    1. Mistral 7B
    2. Llama 2 7B
    3. TinyLlama 1.1B
    4. Phi-2
    5. Gemma 2B
    6. Gemma 7B
    7. Falcon 7B

    AI recommended 7 alternatives but never named cactus-compute/needle. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    pass

  • 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 cactus-compute/needle?
    pass
    AI named cactus-compute/needle explicitly

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

  • If a team adopts cactus-compute/needle in production, what risks or prerequisites should they evaluate first?
    pass
    AI named cactus-compute/needle 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 cactus-compute/needle solve, and who is the primary audience?
    pass
    AI named cactus-compute/needle 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 cactus-compute/needle. 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/cactus-compute/needle.svg)](https://repogeo.com/en/r/cactus-compute/needle)
HTML
<a href="https://repogeo.com/en/r/cactus-compute/needle"><img src="https://repogeo.com/badge/cactus-compute/needle.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

cactus-compute/needle — 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
cactus-compute/needle — RepoGEO report