ModelCloud/GPTQModel

GPTQModel

✅ Recently maintained

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

1,284Stars
213Forks
+57-day stars

Python · License unverified · Last push 2026-10-30

Official repository & installation ↗
gptqoptimumpeftquantizationsglangtransformersvllm

Star history

2025-09-292026-11-01
View historical data
DateStars
2026-10-031,265
2026-10-041,266
2026-10-051,266
2026-10-061,267
2026-10-071,267
2026-10-081,267
2026-10-091,268
2026-10-101,268
2026-10-111,269
2026-10-121,270
2026-10-131,270
2026-10-141,271
2026-10-151,272
2026-10-161,272
2026-10-171,272
2026-10-181,272
2026-10-191,273
2026-10-201,274
2026-10-211,275
2026-10-221,277
2026-10-231,277
2026-10-241,277
2026-10-251,278
2026-10-261,280
2026-10-271,281
2026-10-281,281
2026-10-291,281
2026-10-301,283
2026-10-311,283
2026-11-011,284

Get the project

git clone https://github.com/ModelCloud/GPTQModel.git

Related projects & alternative candidates

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

LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

★ 75,832rea

Use AI agents to reverse engineer app behavior and native binaries with tool integrations.

★ 419,787openclaw

Cross-platform open-source personal AI assistant focused on data ownership, written in TypeScript for self-hosting.

★ 393,671