From: ztxz16 <github.com/ztxz16>Newsgroups: alt.freeweights.toolsSubject:

fastllm

Release: v1.9.1 (2026-11-06)Commit: 10ae14dLicense: Apache-2.0

C++ inference engine for language models on CPU and GPU.

inference enginev1.9.1releasefastllmC++Apache-2.0
FactsLicenseApache-2.0LanguageC++Kindinference engineRelease2026-11-06PlatformsLinux, Windows, AndroidLinks to the projectpermissive
$ python -m pip install -U ftllm

Overview

C++ inference engine for language models on CPU and GPU.

Kind
inference engine
License
Apache-2.0
Language
C++
Platforms
Linux, Windows, Android
Latest release
v1.9.1 (2026-11-06)
Repository
ztxz16/fastllm

Freeweights links to the project and does not host tool binaries.

Install

$ python -m pip install -U ftllm
$ python -m pip install -U ftllm

Checked against the project's README on 2026-11-15. The project's own instructions win when they differ: install docs

Freeweights links to the project and does not host tool binaries.

Use with Freeweights

Run a catalog model

Download the weights from Freeweights first (HF_ENDPOINT or fw.py), then point the tool at the folder.

Catalog models it can run (3137)

and 3077 more.

License

License
Apache-2.0
Class
Permissive

Read the license

Freeweights links to the project and does not host tool binaries.

Provenance

From: ztxz16 <github.com/ztxz16>Newsgroups: alt.freeweights.toolsSubject: fastllmRelease: v1.9.1 (2026-11-06)Commit: 10ae14dLicense: Apache-2.0
Repository
ztxz16/fastllm
Pinned release
v1.9.1, 2026-11-06
Release commit
10ae14dcd2d0e32e4462bbae75e11f04657d092a
Default branch
master 66e1435258e9fc40d79c083b22d1562a10c5f863
Fetched
2026-11-15
Takedowns
None.

Freeweights links to the project and does not host tool binaries.

Works with

3137 catalog models. See the list