turboderp-org/exllamav3

exllamav3

✅ Recently maintained

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

1,785Stars
282Forks
+317-day stars

Python · MIT · Last push 2026-11-03

Official repository & installation ↗

GitValue · Value evidence

Unscored · Evidence coverage 0%

Provisional rubric; documentation and runtime testing are separate. Missing evidence does not imply low value.

Star history

2025-09-292026-11-03
View historical data
DateStars
2026-10-051,586
2026-10-061,594
2026-10-071,607
2026-10-081,615
2026-10-091,626
2026-10-101,633
2026-10-111,644
2026-10-121,652
2026-10-131,657
2026-10-141,664
2026-10-151,669
2026-10-161,677
2026-10-171,684
2026-10-181,695
2026-10-191,707
2026-10-201,713
2026-10-211,722
2026-10-221,729
2026-10-231,736
2026-10-241,742
2026-10-251,749
2026-10-261,753
2026-10-271,757
2026-10-281,761
2026-10-291,767
2026-10-301,767
2026-10-311,772
2026-11-011,776
2026-11-021,784
2026-11-031,785

Get the project

git clone https://github.com/turboderp-org/exllamav3.git

Cloning downloads the source. For dependencies and installation, follow the project README.

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.