dropbox/hqq

• highreadme#1

  Reposition the README's opening paragraph to highlight LLM focus and key differentiators

  Why:

  CURRENT

  ## Half-Quadratic Quantization (HQQ)
  This repository contains the official implementation of Half-Quadratic Quantization (<b>HQQ</b>) presented in our articles: 
  * HQQ: https://dropbox.github.io/hqq_blog/
  * HQQ+: https://dropbox.github.io/1bit_blog/
  
  ### What is HQQ?
  <b>HQQ</b> is a fast and accurate model quantizer that skips the need for calibration data. Quantize the largest models, without calibration data, in just a few minutes at most 🚀.

  COPY-PASTE FIX

  Copy

  ## Half-Quadratic Quantization (HQQ)
  This repository contains the official implementation of Half-Quadratic Quantization (<b>HQQ</b>), a fast and accurate post-training quantization method for large language models (LLMs) that uniquely skips the need for calibration data. Quantize the largest models, without calibration data, in just a few minutes at most 🚀. HQQ supports 8,4,3,2,1 bits and is compatible with PEFT training and `torch.compile` for faster inference and training. Learn more in our articles: 
  * HQQ: https://dropbox.github.io/hqq_blog/
  * HQQ+: https://dropbox.github.io/1bit_blog/

  OpenDoneDismiss
• mediumtopics#2

  Add more specific topics to improve keyword matching for LLM quantization

  Why:

  CURRENT

  llm, machine-learning, quantization

  COPY-PASTE FIX

  Copy

  llm, machine-learning, quantization, post-training-quantization, low-bit-quantization, llm-inference, peft-compatible

  OpenDoneDismiss
• lowreadme#3

  Move the 'Why use HQQ' comparison out of the FAQ details tag

  Why:

  CURRENT

  <details>
    <summary>FAQ </summary>
   <b> Why should I use HQQ instead of other quantization methods? </b><br>
  <ul>
  <li> HQQ is very fast to quantize models.</li>
  <li> It supports 8,4,3,2,1 bits.</li>
  <li> You can use it on any model (LLMs, Vision, etc.).</li>
  <li> The dequantization step is a linear operation, this means that HQQ is compatbile with various optimized CUDA/Triton kernels.</li>
  <li> HQQ is compatible with peft training.</li>
  <li> We try to make HQQ fully compatible `torch.compile` for faster inference and training.</li>
  </ul>
    
    <b>What is the quality of the quantized models? </b><br>

  COPY-PASTE FIX

  Copy

  ### Why use HQQ instead of other quantization methods?
  <ul>
  <li> HQQ is very fast to quantize models.</li>
  <li> It supports 8,4,3,2,1 bits.</li>
  <li> You can use it on any model (LLMs, Vision, etc.).</li>
  <li> The dequantization step is a linear operation, this means that HQQ is compatbile with various optimized CUDA/Triton kernels.</li>
  <li> HQQ is compatible with peft training.</li>
  <li> We try to make HQQ fully compatible `torch.compile` for faster inference and training.</li>
  </ul>
  
  <details>
    <summary>FAQ </summary>
    <b>What is the quality of the quantized models? </b><br>

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  How to quickly quantize large language models without needing extensive calibration data?

  you: not recommended
  AI recommended (in order):

  1. GPTQ
  2. AutoGPTQ
  3. optimum
  4. AWQ
  5. LLM.int8()
  6. SmoothQuant
  7. OFT
  8. ZeroQuant

  AI recommended 8 alternatives but never named dropbox/hqq. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  Looking for an LLM quantization library supporting low bit-widths and fine-tuning compatibility.

  you: not recommended
  AI recommended (in order):

  1. AWQ
  2. GPTQ
  3. bitsandbytes
  4. Hugging Face Optimum
  5. NVIDIA TensorRT-LLM

  AI recommended 5 alternatives but never named dropbox/hqq. This is the gap to close.

  Show full AI answer

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of dropbox/hqq?

  pass
  ✓AI named dropbox/hqq explicitly

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

• If a team adopts dropbox/hqq in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named dropbox/hqq 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 dropbox/hqq solve, and who is the primary audience?

  pass
  ✓AI named dropbox/hqq explicitly

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