spandrel-extra-arches
Implements extra model architectures for spandrel
Decision gist · record as of 2026-08-14
Yes, if you are working on a private or non-commercial open-source project and need the specific architectures this library provides. No, if you are building a commercial or closed-source product without first auditing the individual architecture licenses. The dormant maintenance status (no updates in 697 days) is acceptable for a stable, narrow-purpose extension, but signals that new architectures or bug fixes are unlikely.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires spandrel to be installed first; torch and torchvision are runtime dependencies that must be available in your environment.
- Low friction installation as a pure Python wheel.
- Dormant maintenance status (last release 697 days ago) means no active development, though the package remains functional for its narrow purpose.
License · maintenance · safety
MIT (permissive) — MIT-licensed wrapper, but the architectures it implements carry non-commercial and copyleft licenses. Commercial or closed-source projects must review individual architecture licenses before use; private and non-commercial open-source projects are unrestricted.
last release 2024-09-16 (697 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 285,220 downloads/mo, #8,056 on PyPI
Alternatives
Verify before relying
pip install spandrel spandrel_extra_arches
import spandrel
import spandrel_extra_arches
spandrel_extra_arches.install()
model = spandrel.ModelLoader().load_from_file("path/to/model.pth")- Which specific architectures are included and their exact license restrictions (fact sheet references external documentation).
- Whether the package works with recent PyTorch versions beyond those listed in classifiers.
- Active maintenance status or plans for future updates given dormant status.
What it is and what it does
Spandrel-extra-arches is a companion library to spandrel that extends its model loader with support for additional PyTorch architectures. These architectures are bundled separately because they carry restrictive licenses—primarily non-commercial or copyleft terms—that differ from spandrel's own licensing. The package works by registering these architectures with spandrel's model loading system, allowing you to load and use models built on these architectures once the registration function is called.
The library is designed for developers working with spandrel who need access to architectures beyond the main library's scope. It depends on torch, torchvision, numpy, einops, and typing-extensions. Installation is straightforward, but users must understand the license implications: private projects and non-commercial open-source work face no restrictions, while commercial or closed-source projects need to audit the individual architecture licenses before deployment.
Use it for
- Load pre-trained models built on restricted-license architectures within spandrel's unified model loader interface.
- Extend a non-commercial research or open-source project with additional model architecture support beyond spandrel's core.
- Evaluate or prototype with model architectures that are not available in the main spandrel library.
- Build a private tool or service that relies on specific restricted-license architectures registered via spandrel.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are working on a private or non-commercial open-source project and need the specific architectures this library provides.
No, if you are building a commercial or closed-source product without first auditing the individual architecture licenses. The dormant maintenance status (no updates in 697 days) is acceptable for a stable, narrow-purpose extension, but signals that new architectures or bug fixes are unlikely.
Install
spandrel-extra-arches on PyPI
Before you install
Low friction installation as a pure Python wheel. Dormant maintenance status (last release 697 days ago) means no active development, though the package remains functional for its narrow purpose.
Requires spandrel to be installed first; torch and torchvision are runtime dependencies that must be available in your environment.
License in practice
MIT-licensed wrapper, but the architectures it implements carry non-commercial and copyleft licenses. Commercial or closed-source projects must review individual architecture licenses before use; private and non-commercial open-source projects are unrestricted.
Quickstart
pip install spandrel spandrel_extra_arches
import spandrel
import spandrel_extra_arches
spandrel_extra_arches.install()
model = spandrel.ModelLoader().load_from_file("path/to/model.pth")Verify before relying
- Which specific architectures are included and their exact license restrictions (fact sheet references external documentation).
- Whether the package works with recent PyTorch versions beyond those listed in classifiers.
- Active maintenance status or plans for future updates given dormant status.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 6 packagesspandreltorchtorchvisionnumpyeinopstyping-extensions |
| Maintenance | Dormant 697 days since the last release |
| First released | |
| Downloads | 285,220 / month, #8,056 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 2 - Pre-AlphaIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseOperating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: OnlyProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Software Development :: Libraries |
Evidence: spandrel_extra_arches-0.2.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “pytorch model architectures”
- spandrel-extra-archesRegisters additional PyTorch model architectures with spandrel's…
- pytorchcvProvides a collection of pretrained computer vision models for…
- spandrelSpandrel loads and runs pre-trained PyTorch models by automatically…
Give your agent the search over MCP, or paste the wish link into any chat.
More Libraries packages
urllib3 is an HTTP client library that provides thread-safe connection pooling, SSL/TLS verification, multipart file uploads, request retries, compression support, and proxy handling for Python applications.
Requests is a Python HTTP library that simplifies sending HTTP/1.1 requests with automatic handling of headers, authentication, cookies, and response parsing.
Pluggy provides a plugin system that lets you define hook specifications and register implementations to be called in sequence, enabling extensible Python applications without tight coupling.
Install it if you're building an extensible application or framework.
Provides parsing, arithmetic, and recurrence rule computation for dates and times, with timezone support and iCalendar RFC compliance.
Install it if you need to parse flexible date strings, compute relative dates, handle timezones, or work with recurrence rules—it's the de facto choice for these tasks.
Six provides utility functions to write Python code that runs on both Python 2.7 and Python 3.3+, smoothing over language differences between the two versions.
pytest is a testing framework that lets you write test functions using plain assert statements and automatically discovers and runs them, with detailed failure reporting.
See also spandrel · xformers · extra-platforms · torchsr · torchvision · accelforge · torch-npu · pytorchcv · hoptorch · inference-models