Public record
Software health reportschema 0.12.0 · metrics 2.10.0 · 2026-07-17 22:01 UTC

ModelCloud / GPTQModel

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

Python · CudaCustom license★ 1,207 stars⑂ 192 forkssince Jun 2024View on GitHub ↗
KindLibraryhow this is determined
#gptq#optimum#peft#quantization#sglang#transformers#vllm

ModelCloud/GPTQModel holds a health index of 89 out of 100, placing it in the Excellent band. It scores highest on Vitality (95/100) and lowest on AI Readiness (30/100). It was last updated 1 day ago. 2 contributors account for most of its recent work.

89
overall / 100
Excellent

Software health index

Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.

89
Exceptional93-100The record's top tier (≈ top 5%); essentially all checked criteria met
Excellent80-92Strong across the board; minor gaps
Good65-79Healthy; gaps are limited and manageable
Moderate50-64Acceptable with notable gaps; review recommended
Weak35-49Material weaknesses across several areas
At Risk20-34Significant weaknesses; adoption warrants caution
Critical1-19Severe problems (abandoned, single-maintainer, no hygiene)
VitalityCommunity &AdoptionSustainability &GovernanceEngineeringQualitySecurityAI Readiness

Score profile

Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.

The weighted overall 75 is calibrated to 89 on the published index scale (record calibration 2026-08-02).

Ownership

ModelCloud.aiOrganization
63 followers18 public repossince Jun 2024

This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.

Package ecosystems

RegistryPackageVersionDownloads / moVersionsLast publishTags
PyPIGPTQModel7.1.0-5539 days agogptqawqqqqautogptqautoawqeoragarquantizationlarge-language-modelstransformersllmmoecompression

Metrics by category

Vitality

Is the project alive — is code being written and are releases shipping?

95Exceptional · 21% of overall

Development activity

98Exceptional
How it's scored
36/36Push recency — last push 1 days ago
33.9/36Commit cadence — 49/52 weeks with commits
18/18Commit volume — 1,087 commits in the last year
10/10OpenSSF Scorecard: Maintained — 30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10
Inputs used
commits_last_year1,087
human_commit_share—
days_since_last_push1
active_weeks_last_year49

Release discipline

90Excellent
How it's scored
27/27Ships releases — 68 releases published
36/36Release recency — latest release 14 days ago
27/27Release cadence — a release every ~22.2 days
0/10OpenSSF Scorecard: Signed-Releases — Project has not signed or included provenance with any releases.
Inputs used
releases_count68
latest_release_tagv7.2.0
releases_from_tagsno
days_since_latest_release14
mean_days_between_releases22.2

Community & Adoption

Does the project have users, downloads, attention, and a welcoming setup for contributors?

62Moderate · 17% of overall

Popularity & adoption

72Good
How it's scored
50/60Stars — 1,207 stars
19/25Forks — 192 forks
3.3/15Watchers — 5 watchers
Inputs used
forks192
stars1,207
watchers5
growth_stateunverified
growth_factor_pct100
growth_unverified_reasonno_history

Community health

51Moderate
How it's scored
22.5/22.5README
16.9/22.5License — license file present, not a recognized license
0/18CONTRIBUTING guide
0/13.5Code of conduct
0/7.2Issue template
6.3/6.3PR template
Inputs used
has_readmeyes
has_licenseyes
readme_badges—
has_contributingno
has_issue_templateno
has_code_of_conductno
readme_badge_services—
has_pull_request_templateyes

Sustainability & Governance

Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?

80Excellent · 23% of overall

Maintainer resilience (bus factor)

64Moderate
How it's scored
25.2/54Bus factor — 2 contributor(s) cover half of all commits
15.1/22.5Commit distribution — top contributor authored 33% of commits
13.5/13.5Contributor breadth — 90 contributors
10/10OpenSSF Scorecard: Contributors — project has 3 contributing companies or organizations -- score normalized to 10
Inputs used
bus_factor2
contributors_sampled90
top_contributor_share0.327

Issue & PR responsiveness

91Excellent
How it's scored
37/42Issue resolution — 88% of issues closed
28.4/30PR acceptance — 2,445/2,579 decided PRs merged
0/13Newcomer PR acceptance — no first-time contributor's PR decided in 30d
13.5/15OpenSSF Scorecard: Code-Review — Found 27/29 approved changesets -- score normalized to 9
Inputs used
merged_prs2,445
open_issues43
closed_issues315
prs_merged_7d—
prs_decided_7d—
prs_merged_30d—
prs_decided_30d—
issue_closed_ratio0.88
closed_unmerged_prs134
first_time_authors_30d—
first_time_prs_merged_30d—
first_time_prs_decided_30d—
Excluded from scoring (no data or not applicable): Newcomer PR acceptance. Remaining weights renormalized.

Ownership & stewardship

71Good
How it's scored
30/30Ownership backing — organization-owned
0/20Verified domain — verified-domain status not read for this organization
13/25Owner reach — 63 followers of ModelCloud
13.5/25Track record — 18 public repos, account ~2 yr old
Inputs used
followers63
owner_typeOrganization
is_verified—
owner_loginModelCloud
public_repos18
account_age_days763
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.

Package maintenance

100Exceptional
How it's scored
25/25Published & resolvable — 1 package(s) on pypi
35/35Publish recency — latest publish 39 days ago
20/20Version history — 55 published versions
20/20Not deprecated — active, not deprecated or yanked
Inputs used
packagesGPTQModel
ecosystemspypi
any_deprecatedno
min_days_since_publish39

Engineering Quality

Are baseline engineering and documentation practices in place?

84Excellent · 19% of overall

Engineering practices

80Excellent
How it's scored
24/24CI workflows — 6 workflow(s)
24/24Tests present
16/16Linter config — ruff.toml
0/9.6Pre-commit hooks
0/6.4.editorconfig
16/20OpenSSF Scorecard: CI-Tests — 25 out of 30 merged PRs checked by a CI test -- score normalized to 8
Inputs used
has_ciyes
has_testsyes
has_editorconfigno
has_linter_configyes
has_precommit_configno

Documentation

90Excellent
How it's scored
30/30README
25/25Documentation directory
15/15Documentation / homepage site — https://x.com/Qubitium
10/10Repository description
10/10Topics — 7 topics
0/10Wiki
Inputs used
topicsgptq, optimum, peft, quantization, sglang, transformers, vllm
has_wikino
homepagehttps://x.com/Qubitium
docs_sitehttps://x.com/Qubitium
has_readmeyes
has_docs_diryes
has_descriptionyes

Security

Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?

58Moderate · 16% of overall

Security posture

58Moderate
How it's scored
7.5/7.5Binary-Artifacts — no binaries found in the repo
2.2/7.5Branch-Protection — branch protection is not maximal on development and all release branches
2/2.5CI-Tests — 25 out of 30 merged PRs checked by a CI test -- score normalized to 8
0/2.5CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected
6.8/7.5Code-Review — Found 27/29 approved changesets -- score normalized to 9
2.5/2.5Contributors — project has 3 contributing companies or organizations -- score normalized to 10
10/10Dangerous-Workflow — no dangerous workflow patterns detected
7.5/7.5Dependency-Update-Tool — update tool detected
0/5Fuzzing — project is not fuzzed
2.2/2.5License — license file detected
7.5/7.5Maintained — 30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10
0/5Packaging — no data
0/5Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
3.5/5SAST — SAST tool is not run on all commits -- score normalized to 7
0/5Security-Policy — security policy file not detected
0/7.5Signed-Releases — Project has not signed or included provenance with any releases.
6.8/7.5Token-Permissions — detected GitHub workflow tokens with excessive permissions
0/7.5Vulnerabilities — 28 existing vulnerabilities detected
Inputs used
sourceopenssf_scorecard
checks_evaluated17
scorecard_versionv5.5.0
checks_inconclusive1
scorecard_aggregate5.8
Excluded from scoring (no data or not applicable): Packaging. Remaining weights renormalized.

AI Readiness

How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.

30At Risk · 4% of overall

Agent context & guidance

1Critical
How it's scored
0/45Agent instructions — no CLAUDE.md / AGENTS.md / editor rules
0/15Machine-readable docs (llms.txt)
0/40Legible commit history — no data
Inputs used
has_llms_txtno
llms_txt_url—
legible_history_share—
agent_instruction_files—
agent_instruction_max_bytes—
Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.

Verify loop (build / test / typecheck)

42Weak
How it's scored
0/18One-command bootstrap
22/22Automated tests
11/11Lint / format config — ruff.toml
0/11Static type checking
0/10Reproducible environment
0/10Demonstrated agent practice — no data
5/8Automated maintenance — dependency automation configured, none observed in the sampled commits
0/10OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0
Inputs used
has_nixno
has_testsyes
lockfiles—
has_dockerfileno
typed_languageno
bootstrap_files—
has_devcontainerno
has_linter_configyes
typecheck_configs—
agent_commit_share—
toolchain_manifests—
dependency_bot_commit_share0
Excluded from scoring (no data or not applicable): Demonstrated agent practice. Remaining weights renormalized.

Code legibility for models

54Moderate
How it's scored
0/45Type-checkable code — Python without a type-check config
53.6/55Manageable file sizes — 21/820 source files over 60KB
Inputs used
primary_languagePython
largest_source_bytes429,650
source_files_sampled820
oversized_source_files21

Key facts

1,207GitHub stars
90contributors
1,087commits, last 12 months
1days since last push
68releases
2bus factor
43open issues
PyPIpackage ecosystems

More detail

OpenSSF Scorecard 5.8 / 10
5.8aggregate

Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).Scorecard v5.5.0 · 2026-07-17 22:01 UTC

10Binary-Artifactsno binaries found in the repo
3Branch-Protectionbranch protection is not maximal on development and all release branches
8CI-Tests25 out of 30 merged PRs checked by a CI test -- score normalized to 8
0CII-Best-Practicesno effort to earn an OpenSSF best practices badge detected
9Code-ReviewFound 27/29 approved changesets -- score normalized to 9
10Contributorsproject has 3 contributing companies or organizations -- score normalized to 10
10Dangerous-Workflowno dangerous workflow patterns detected
10Dependency-Update-Toolupdate tool detected
0Fuzzingproject is not fuzzed
9Licenselicense file detected
10Maintained30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10
n/aPackagingpackaging workflow not detected
0Pinned-Dependenciesdependency not pinned by hash detected -- score normalized to 0
7SASTSAST tool is not run on all commits -- score normalized to 7
0Security-Policysecurity policy file not detected
0Signed-ReleasesProject has not signed or included provenance with any releases.
9Token-Permissionsdetected GitHub workflow tokens with excessive permissions
0Vulnerabilities28 existing vulnerabilities detected
All dependencies 41

Full resolved dependency set from the GitHub dependency graph: 0 direct and 41 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.

RegistryPackageVersionRelation
PyPIaccelerate—indirect
PyPIbitblas0.1.0.post1indirect
PyPIbitsandbytes—indirect
PyPIdatasets—indirect
PyPIdefuser—indirect
PyPIdevice-smi—indirect
PyPIdill—indirect
PyPIflashinfer-python—indirect
PyPIjinja2—indirect
PyPIlogbar—indirect
PyPImaturin—indirect
PyPImlx-lm—indirect
PyPIninja—indirect
PyPInumpy2.2.6indirect
PyPInvidia-cublas—indirect
PyPInvidia-cublas-cu1212.9.1.4indirect
PyPInvidia-cuda-runtime—indirect
PyPInvidia-cuda-runtime-cu1212.9.79indirect
PyPInvidia-cusolver—indirect
PyPInvidia-cusolver-cu1211.7.5.82indirect
PyPInvidia-cusparse—indirect
PyPInvidia-cusparse-cu1212.5.10.65indirect
PyPIoptimum—indirect
PyPIpackaging—indirect
PyPIpillow—indirect
PyPIprotobuf—indirect
PyPIpyarrow—indirect
PyPIpypcre—indirect
PyPIpytest—indirect
PyPIpytest-timeout—indirect
PyPIruff0.14.2indirect
PyPIsafetensors—indirect
PyPIsetuptools—indirect
PyPIsglang—indirect
PyPIthreadpoolctl—indirect
PyPItokenicer—indirect
PyPItorch—indirect
PyPItorchao—indirect
PyPItransformers—indirect
PyPItriton—indirect
PyPIvllm—indirect
Raw JSON report machine-readable

Feedback

Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.

The message is kept through sign-in.

Related records

Inspected repositories sharing catalogue tags or ecosystems with ModelCloud/GPTQModel. Read them side by side →

99openvinotoolkit/nncfNeural Network Compression Framework for enhanced OpenVINO™ inferenceExceptional97intel/auto-roundA SOTA quantization algorithm for high-accuracy low-bit LLM inference, seamlessly optimized for CPU/XPU/CUDA, with multi-datatype support and full compatibility with vLLM, SGLang, and Transformers.Exceptional96vllm-project/llm-compressorTransformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLMExceptional94modelscope/ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).Exceptional99ai-dynamo/dynamoA Datacenter Scale Distributed Inference Serving FrameworkExceptional98kvcache-ai/MooncakeMooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.Exceptional

Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.

Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.12.0 — full methodology · metrics wiki.

How one result sits in the wider record: aggregate statistics — PyPI.