From: mlc-ai <github.com/mlc-ai>Newsgroups: alt.freeweights.toolsSubject:

MLC LLM

Release: noneCommit: 3b7663aLicense: Apache-2.0

Compiles and runs language models on phones, browsers, laptops and GPUs from one stack.

inference engineno releasereleaseMLC LLMPythonApache-2.0

FactsLicenseApache-2.0LanguagePythonKindinference engineReleasenonePlatformsLinux, macOS, Windows, iOS, Android, WebLinks to the projectpermissive

$ python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-cpu mlc-ai-nightly-cpu
# use with Freeweights
$ mlc_llm chat HF://<id>

Overview

Compiles and runs language models on phones, browsers, laptops and GPUs from one stack.

Topicslanguage-modelllmmachine-learning-compilationtvm

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

$ python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-cpu mlc-ai-nightly-cpu
# use with Freeweights
$ mlc_llm chat HF://<id>

$ python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-cpu mlc-ai-nightly-cpu

Checked against the project's README on 2026-11-14. The project's own instructions win when they differ: install docs

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

Run a catalog model

$ mlc_llm chat HF://<id>

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

and 3077 more.

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

From: mlc-ai <github.com/mlc-ai>Newsgroups: alt.freeweights.toolsSubject: MLC LLMRelease: noneCommit: 3b7663aLicense: Apache-2.0

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

Get it

Works with

3137 catalog models. See the list