GPTQModel: LLM quantization toolkit (GitHub: ModelCloud/GPTQModel)

Fields

id

sources/qhw-src-gptqmodel-repo

URL

https://github.com/ModelCloud/GPTQModel

Publisher

ModelCloud

Kind

repo

Accessed

2026-10-04

notes

GPTQModel GitHub repository. Extensible platform for LLM quantization with HW acceleration for NVIDIA, AMD, Intel GPU and CPU. Supports GPTQ, AWQ, ParoQuant, GGUF, FP8, EXL3, QQQ. References Marlin, Swordfish, and Machete kernels. Includes device-aware kernel selection and hardened Machete runtime caching.

Notes

GPTQModel GitHub repository. Extensible platform for LLM quantization with HW acceleration for NVIDIA, AMD, Intel GPU and CPU. Supports GPTQ, AWQ, ParoQuant, GGUF, FP8, EXL3, QQQ. References Marlin, Swordfish, and Machete kernels. Includes device-aware kernel selection and hardened Machete runtime caching.

Cross-references

This record references no other records.