ExLlamaV3: Releases and Overview

September 17, 2026September 18, 2026

Inference library tuned for consumer NVIDIA GPUs. Its EXL3 quantization format fits large models into limited VRAM.

Category: Quantization, model formats and fine-tuning. Part of our engine and tool tracker.

At a Glance

The project describes itself as: “An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs ”

Release History

Compiled by Local Model Watch from the project’s GitHub releases. Pre-releases are omitted. Where we wrote an article about a release, it is linked in the last column; smaller releases are tracked here only.

Articles on Local Model Watch

No articles yet.

Last updated 2026-09-18 (JST). Facts above come from the GitHub API; the one-paragraph summary is written by the site’s editors.