AwesomeRepos
Sign in

Tags / Machine learning /

Model quantization

A tool that makes models smaller or faster by quantization, pruning, or distillation, including LLM quantization.

Repositories

10

Net stars gained, last 7 days

+1,245

Top-level Tag

Machine learning

Net stars gained each day, last 90 days

2026-10-19: +300 net stars. Most from zjwfufu/SMD, +148.2026-10-20: +234 net stars. Most from mw00/project-maya, +183.2026-10-23: +282 net stars. Most from mw00/project-maya, +168.2026-10-28: +397 net stars. Most from undrgrnd-labs/hunch, +183.2026-10-29: +263 net stars. Most from undrgrnd-labs/hunch, +97.

Peak days

  1. 1

    Oct 19, 2026 +300 net stars (median day +54)

  2. 2

    Oct 20, 2026 +234 net stars (median day +54)

  3. 3

    Oct 23, 2026 +282 net stars (median day +54)

  4. 4

    Oct 28, 2026 +397 net stars (median day +54)

  5. 5

    Oct 29, 2026 +263 net stars (median day +54)

A peak day has at least 2 times the net stars of the median day of this chart, and at least 100 more. For each peak day, the list shows the repositories that gained the most net stars that day. It also shows their GitHub releases of that day or the day before (UTC), and their creation date when it was 14 days or less before. These events occur near the same day. They do not show why the stars came.

Largest

Most stars in total now.

  1. microsoft/nniarchived · 14K

    readme: Pruning Level L1 Norm Taylor FO Weight Movement AGP Auto Compress More... Quantization Naive QAT LSQ Observer DoReFa BNN

  2. PaddlePaddle/PaddleNLP13K

    readme: DeepSeek V3/R1完整版支持 FP8、INT8、4-bit 量化推理，MTP 投机解码

  3. intel/ipex-llmarchived · 8.8K

    readme: **LLM optimizations**, **XPU acceleration** and **low-bit (FP8/FP6/FP4/INT4) support**

  4. ml-explore/mlx-lm7.5K

    readme: The `mlx-lm` package also comes with functionality to quantize and optionally upload models to the Hugging Face Hub.

  5. syv-ai/HyperQwen2.5K

    readme: a patch series against a pinned vLLM plus a model-preparation pipeline — requantized heads, a calibrated draft vocabulary

  6. mw00/project-maya2.5K

    readme: Maya's own quants of GLM-5.3-Flash keep 97.7-99.2% of the FP8 model's zero-shot accuracy

  7. haolpku/Omni-Edu538

    readme: The FP8 releases use LLM Compressor and `compressed-tensors` with the `FP8_BLOCK` scheme

  8. undrgrnd-labs/hunch296

    readme: hunch sits in front of your judge (its teacher) and learns from its answers.

  9. zjwfufu/SMD266

    readme: SMD is a simple and scalable method for few-step diffusion distillation across image, video, audio-video and 3D generation.

  10. ForeverBlue816/PrismQuant154

    readme: It combines calibrated orthogonal rotations, compact-WY representations and groupwise asymmetric INT4 quantization.

Newest Admissions

Entered the index by the rising rule, newest first.

  1. haolpku/Omni-Edu538

    readme: The FP8 releases use LLM Compressor and `compressed-tensors` with the `FP8_BLOCK` scheme

  2. undrgrnd-labs/hunch296

    readme: hunch sits in front of your judge (its teacher) and learns from its answers.

  3. ForeverBlue816/PrismQuant154

    readme: It combines calibrated orthogonal rotations, compact-WY representations and groupwise asymmetric INT4 quantization.

  4. zjwfufu/SMD266

    readme: SMD is a simple and scalable method for few-step diffusion distillation across image, video, audio-video and 3D generation.

  5. mw00/project-maya2.5K

    readme: Maya's own quants of GLM-5.3-Flash keep 97.7-99.2% of the FP8 model's zero-shot accuracy

  6. syv-ai/HyperQwen2.5K

    readme: a patch series against a pinned vLLM plus a model-preparation pipeline — requantized heads, a calibrated draft vocabulary

All 10 in the Repository Index

How a repository gets this Tag

An agent reads the description, the GitHub topics, and the start of the README of each repository. It chooses Tags only from the Tag list in the AwesomeRepos source code. For each Tag, it quotes the text. A code check keeps the Tag only when the quote is in that text. The quote under each repository is that evidence. A Tag does not rank repositories. It does not say that one repository can replace another. To report a wrong Tag, use "Report a problem with this page" on the page of the repository. All numbers on this page count only visible repositories.