RRepoGEO

REPOGEO REPORT · LITE

turboderp/exllama

Default branch master · commit 3b013cd5 · scanned 5/21/2026, 6:47:55 PM

GitHub: 2,920 stars · 223 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
35 /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
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 turboderp/exllama, 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
  • hightopics#1
    Add specific topics to the repository

    Why:

    COPY-PASTE FIX
    llama, llm, gptq, 4-bit, quantization, inference, cuda, python, deep-learning, machine-learning, gpu
  • mediumabout#2
    Update the repository description for clarity and specificity

    Why:

    CURRENT
    A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
    COPY-PASTE FIX
    A fast, memory-efficient Python/C++/CUDA implementation of Llama for 4-bit GPTQ quantized weights on modern NVIDIA GPUs.
  • lowhomepage#3
    Add a homepage URL to the repository

    Why:

    COPY-PASTE FIX
    https://github.com/turboderp/exllama

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 turboderp/exllama
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
vLLM
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. vLLM · recommended 2×
  2. oobabooga/text-generation-webui · recommended 1×
  3. llama.cpp · recommended 1×
  4. ExLlamaV2 · recommended 1×
  5. AutoGPTQ · recommended 1×
  • CATEGORY QUERY
    How can I run large language models with 4-bit weights efficiently on consumer GPUs?
    you: not recommended
    AI recommended (in order):
    1. oobabooga/text-generation-webui (oobabooga/text-generation-webui)
    2. llama.cpp
    3. ExLlamaV2
    4. AutoGPTQ
    5. vLLM
    6. Hugging Face `transformers` library
    7. bitsandbytes

    AI recommended 7 alternatives but never named turboderp/exllama. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a high-performance Python library for fast LLM inference on modern NVIDIA GPUs.
    you: not recommended
    AI recommended (in order):
    1. vLLM
    2. NVIDIA TensorRT-LLM
    3. Hugging Face Transformers with BetterTransformer (Optimum)
    4. DeepSpeed-MII
    5. TGI (Text Generation Inference) by Hugging Face
    6. OpenVINO

    AI recommended 6 alternatives but never named turboderp/exllama. 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 turboderp/exllama?
    pass
    AI named turboderp/exllama explicitly

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

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

Subscribe to Pro for deep diagnoses

turboderp/exllama — 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
turboderp/exllama — RepoGEO report