Home / MACaQ
huawei-csl/MACaQ
SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch.
C++Categories: AI videoLocal AI
Our summary
MACaQ is a model-agnostic quantization project that compresses text, image, video and audio models. It produces GGUF files for llama.cpp and checkpoints for vLLM, Diffusers and PyTorch.
Who it is for: Developers who want to quantize and run local or served AI models
What the README claims
- Can quantize a 122B-parameter model in 64 minutes using 32.5 GB of device memory
MACaQ can quantize a **122B-parameter model in 64 minutes using just 32.5 GB of device memory**
Not checked - Achieves lower perplexity than MR-GPTQ and DuQuant++, or matches their best Llama-3-8B perplexity with 11× less quantization time
You can get lower perplexity than MR-GPTQ and DuQuant++, or match their best Llama-3-8B perplexity with **11× less quantization time**.
Not checked - Produces MACaQ-R GGUFs that run with a standard llama.cpp installation
Its GGUFs run with a [standard llama.cpp installation]
Not checked - Qwen3.6-35B-A3B MACaQ-R Q4_K_XL has lower KL divergence to FP16 than Unsloth UD-Q4_K_XL at the same file size
| **MACaQ-R Q4_K_XL** | **22.36 GB** | **0.013367** |
Not checked - Quantizes speech generators to W4A4 and saves compact checkpoints that load without repeating calibration
Saved checkpoints load without repeating calibration.
Not checked
Written by AI from the project's README on 2026-11-12. It does not affect the verdict.
Watching: no other rule matched yet.
Gaining 96 stars this week. Last push 5 days ago.
Verdict
TOO EARLY scored 1h ago
There is not enough data on this project yet to call it. The numbers below are shown anyway.
Too close to call Hype Gap between +29 and +70.
Early read: we are missing data on the size of the team behind it and how widely it is used. This is an estimate and will be replaced by a verdict once we have the data. How early reads work.
- Hype
- 94
- Reality
- 31
- Hype Gap
- +63
- Momentum
- -
- Confidence
- 60%
- Responsive moves Reality -13 points.
- Maintained moves Reality -2 points.
Rule verdict-2.0, scoring score-2.0. How we score. Backtest.
Repository on GitHub Project homepage
Maintained by
Maintained by 1 primary developer, 0 external contributors in the last 90 days.
- huawei-csl is a GitHub organization.
- Official organization: verified by GitHub.
- GitHub account created September 2025.
- Top contributors by commits: philippebich 100%.
Why now 25% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
- Stars StarsThe number of GitHub stars on the repository at our latest reading.
- 387
- Gain 7d Gain 7dStars gained since our latest reading from at least 7 days ago.
- +96
- Pace Velocity (Nx usual pace)This week's star gain divided by the project's usual weekly gain. The usual gain is the average weekly gain over the 4 weeks before (days 8 to 35 ago), counted as at least 10 stars. 2.0x means twice the usual pace. Without a reading from 35 days ago, the ranking assumes 2% of the stars the project had 7 days ago as its usual weekly gain. More on the methodology page
- 9.6x
- HN points HN pointsHacker News points added up across posts that mention the project, published in the last 7 days.
- 0 7 days
- Downloads DownloadsDownloads per day of the project's package, as the registry (npm or PyPI) reports them.
- n/a
- Contributors Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.
- 1
- Last release Latest releaseDays since the latest GitHub release was published.
- n/a
Gain 24h Gain 24hStars gained since our latest reading from at least 24 hours ago. +4. Forks ForksThe number of GitHub forks of the repository at our latest reading. 22. Open issues Open issuesThe number of open issues on the repository at our latest reading, as GitHub counts them. 6. Days since push Days since pushDays since the last push to the repository. 5 days. Archived ArchivedWhether the owner has archived the repository on GitHub. An archived repository is read-only. no. Hacker News posts in 7 days Hacker News postsThe number of Hacker News posts that mention the project, published in the last 7 days.: 0. Watchers WatchersThe number of GitHub users watching the repository for notifications, at our latest reading. 3.
Facts
Nerd stuff
Python
- Runs on
- Python >=3.10 (detected)
- Local models
- vLLM: referenced (detected)
- Docs
- docs/ folder (detected), examples/ folder (detected)
- License
- Apache-2.0 (detected)
- Package ecosystem
- Python packaging (detected)
The Receipts
| Source | Evidence | Date |
|---|---|---|
| Hacker News | Thread, 135 points, 33 comments | 11 Nov 2026 |
What changed recently
GitHub release dates we stored. We do not track license changes yet.
Cite this
MACaQ is a GitHub project at https://github.com/huawei-csl/MACaQ written mainly in C++, described there as "SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run text, image, video and audio models with llama.cpp, vLLM, Diffusers and PyTorch".
Source: https://midorreal.com/project/huawei-csl-macaq, checked 22 November 2026. The same facts as JSON: /project/huawei-csl-macaq.json.
Rank history
Peak day: +125 stars on 12 Nov 2026, 10 days ago.
Best rank on Blowing up: #30 on 19 Nov 2026.
Stars
Events in this window
Dated items we stored, last 30 days. They sit near the chart, they do not explain it.
Packages
- We checked npm, PyPI, Docker Hub, crates.io and Homebrew and found no package that links to this repository.
Signals
| Source | What we measured | Checked |
|---|---|---|
| GitHub | 387 stars, 96 gained in 7 days | 22 Nov 2026 |
| Hacker News | 1 post stored, 0 points in the last 7 days | 18 Nov 2026 |
| Feed mentions | Not tracked yet | - |
| npm | No linked package found | - |
| PyPI | No linked package found | - |
| Docker Hub | No linked package found | - |
| crates.io | No linked package found | - |
| Homebrew | No linked package found | - |
| deps.dev | Not tracked yet | - |
| Hugging Face | Not tracked yet | - |
| Bluesky | Not tracked yet | - |
| Stack Exchange | Not tracked yet | - |
| YouTube | Not tracked yet | - |
Attention vs adoption
Attention: above 94% of tracked projects
Star velocity against all tracked projects
Adoption: not enough data to rank
Downloads, dependents and pulls
Not enough comparable data yet to set attention against adoption. This describes the numbers; it is not a verdict.
Compared with AI video
| Measure | This project | Category median |
|---|---|---|
| Star velocity | 9.6 | 0.8 |
| Days since release | no data | 24.4 |
| Contributors, all time | 1 | 2 |
| Median time to first reply on issues | no data | 15 hours |
| Commits in the last 30 days | 23 | 10 |
Star velocity: above 90% of AI video projects
Contributors, all time: above 0% of AI video projects
Commits in the last 30 days: above 66% of AI video projects
Compared with the project's first category only. A percentile line appears only where at least 30 projects in the category have the measure. This describes the numbers; it is not a verdict.
Compare with
Hacker News
| Post | Points PointsThe points the post has on Hacker News. | Comments CommentsThe number of comments on the post on Hacker News. | Date |
|---|---|---|---|
| Hacker News post | 135 | 33 | 11 Nov 2026 |
Caveats
Repo health
- Languages LanguagesShare of the repository's code by bytes, as GitHub's language detection reports it. The five biggest languages are named and the rest are grouped as Other.C++ 55%, C 15%, Python 9%, Cuda 5%, TypeScript 4%, Other 12%
- License LicenseThe SPDX license id GitHub detects, and a class: Open source (OSI) if the license is on the Open Source Initiative approved list, Source-available if the code is readable but the license limits use, Unclear if GitHub cannot match a known license, No license detected if it finds none. A public repository without a license is not open source.Apache-2.0, Open source (OSI)
- Repository age Repository ageTime since the repository was created on GitHub. This is the repository, not necessarily the project, which may have existed elsewhere before.11 days, created 10 Nov 2026
Development
- Commits in the last 7 days Commits in the last 7 daysCommits to the repository in the last 7 days, as GitHub counts them.1
- Commits in the last 30 days Commits in the last 30 daysCommits to the repository in the last 30 days, as GitHub counts them.23
- Commits in the last 90 days Commits in the last 90 daysCommits to the repository in the last 90 days, as GitHub counts them.23
- Contributors, all time Contributors, all timePeople and anonymous contributors who have ever committed to the repository, as GitHub counts them. A small number is context, not a flaw: many solid projects are kept by one or two people.1, a small team
- Releases ReleasesThe number of GitHub releases, and how many days ago the latest one was published.0
- Issues in the last 30 days Issues in the last 30 daysIssues opened and issues closed in the last 30 days, as GitHub search counts them.3 opened, 0 closed
- Pull requests merged in the last 30 days Pull requests merged in the last 30 daysPull requests merged in the last 30 days, as GitHub search counts them.0
Maintenance
- Stale open issues Stale open issuesOpen issues with no update in the last 90 days, as GitHub search counts them.0
- Open pull requests Open pull requestsPull requests open now, as GitHub search counts them.3
Hygiene
- Automated tests or builds (CI) Automated tests or builds (CI)Whether the repository has at least one GitHub Actions workflow file in .github/workflows.No
- A tests folder A tests folderWhether the repository has a top-level folder named tests, test, __tests__ or spec.No
- A license A licenseWhether GitHub detects a license file in the repository.Yes
- Contributing guide Contributing guideWhether the repository has a contributing guide.No
- Code of conduct Code of conductWhether GitHub finds a code of conduct in the repository.No
- CODEOWNERS file CODEOWNERS fileWhether the repository has a CODEOWNERS file, which names who reviews changes to which files.No
- A Dockerfile A DockerfileWhether the repository has a Dockerfile at its top level.No
Security
- Security policy Security policyWhether the repository has a SECURITY.md or SECURITY.rst file.No
- Unpatched high or critical advisories Unpatched high or critical advisoriesPublished GitHub security advisories rated high or critical on this repository that list a vulnerable version with no patched version.0
Badge
For maintainers: one measured fact, no verdict.
Markdown
[](https://midorreal.com/project/huawei-csl-macaq)
HTML
<a href="https://midorreal.com/project/huawei-csl-macaq"><img src="https://midorreal.com/badge/huawei-csl-macaq.svg" alt="Mid or Real"></a>
Verdict badge: It shows the verdict as this page shows it today.
Markdown
[](https://midorreal.com/project/huawei-csl-macaq)
HTML
<a href="https://midorreal.com/project/huawei-csl-macaq"><img src="https://midorreal.com/badge/huawei-csl-macaq.svg?style=verdict" alt="Mid or Real: too early"></a>
Passport
Copy these facts into a post, a README or a page. Cite as "Source: Mid or Real". Full record: JSON.
First tracked 11 Nov 2026 at 63 stars.
- GitHub data 2 h old
- Hacker News data 3 d old
Is this your project? Claim it
Figures by method 1.0