compatibility
runthismodel-gpu-compatibility
RunThisModel.com — GPU Compatibility Database
A curated, machine-readable dataset of 145+ open-source AI models with exact
VRAM requirements per quantization, plus crowd-sourced inference benchmarks
across 100+ consumer and datacenter GPUs.
Maintained by RunThisModel.com — refreshed daily.
Files
File
Description
curated-models.json
145+ models with full quantization table, license, HF download counts, file sizes
community-benchmarks.json… See the full description on the dataset page: https://huggingface.co/datasets/WilliamJiamin/runthismodel-gpu-compatibility.gpu-compatibility
Self-Hosted AI — GPU Compatibility, Recipes and Catalogue
Which open-weight AI models actually run on which consumer GPU, and what it takes
to get them running. 2 700 model×GPU verdicts across 100 models
and 27 cards, plus 999 full setup guides
(19 MB of markdown) written against specific hardware.
This is the machine-readable form of smeltcore.com. Every row carries a
url back to the page it came from.
Generated 2026-09-23T12:36:58+00:00 from the public read API… See the full description on the dataset page: https://huggingface.co/datasets/Smeltcore/gpu-compatibility.job-compatibilitypypi-dependency-compatibility-mvd
PyPI Dependency Compatibility MVD
Colección versionada de pares ordenados de versiones de paquetes Python usada
en un TFM sobre clasificación de incompatibilidades en grafos de dependencias.
Cada observación representa pa@va → pb@vb; la etiqueta indica si ambos pins
pueden coexistir según una ejecución contrafactual del resolver uv.
La colección publica todas las etapas procesadas para documentar por qué el
protocolo cambió. mvd_v2_2 es la configuración recomendada y la… See the full description on the dataset page: https://huggingface.co/datasets/keyduu/pypi-dependency-compatibility-mvd.sdocx-compatibility
SDOCX Compatibility Corpus
This dataset contains paired Samsung Notes .sdocx documents and reference PDF exports for parser, renderer, and visual-regression testing. Each pair has a numeric ID and descriptive name recorded below.
The .sdocx file is the source fixture. The matching PDF is the expected visible result exported from Samsung Notes; it is a visual reference, not a byte-for-byte rendering requirement.
Files
ID
Source
Reference
Coverage… See the full description on the dataset page: https://huggingface.co/datasets/twangodev/sdocx-compatibility.process-compatibility-coatings-adhesives-treatments
Galvanic series and surface energy of engineering materials
Canonical, always-current version: https://referencesource.org/process-compatibility-coatings-adhesives-treatments/
Machine-readable: https://referencesource.org/process-compatibility-coatings-adhesives-treatments/data.json — this mirror is a point-in-time copy.
Last verified: 2026-08-04
Stale after: 2028-08-03 (past this date, prefer the canonical copy —
it re-verifies on a cadence this snapshot does not)
Records: 80… See the full description on the dataset page: https://huggingface.co/datasets/referencesource/process-compatibility-coatings-adhesives-treatments.