Gptq Python Packages

gptqmodel

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

neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

quantfit

Quantize an LLM and check it still refuses what it should — a GPU-aware quantization CLI that measures the safety drift of the quantization it just performed.

octuma

Cuantiza modelos de lenguaje a INT4/INT8 (GPTQ + AWQ) y los exporta a GGUF para llama.cpp y Android.

neural-compressor-pt

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-compressor-tf

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-compressor-jax

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

xllm

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

turbopress

Certified low-bit LLM weight quantization: rotation + derived-exponent equilibration + trellis-coded quantization with Hessian error feedback, a packed Triton runtime, and a KL/top-1/perplexity harness.

lpot

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-insights

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-solution

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

neural-compressor-full

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

model-quantizer

Effortlessly quantize, benchmark, and publish Hugging Face models with cross-platform support for CPU/GPU. Reduce model size by 75% while maintaining performance.

grit-datatype

GRIT — Grouped Reduced-precision Interchange Type: a checkable 64-byte descriptor + contract for block-scaled, sparse, sub-byte tensors. Spec, conformance vectors, and 5 zero-dependency implementations (C, C++, Rust, Python, TypeScript). grit scan audits GGUF/safetensors files you already have.

bampe-weights

This repository is for profiling, extracting, visualizing and reusing generative AI weights to hopefully build more accurate AI models and audit/scan weights at rest to identify knowledge domains for risk(s).

ilit

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

quantbenchx

Quantization quality analyzer - benchmark GGUF/GPTQ/AWQ quantization accuracy.

quantcrush

Compress Any LLM Up to 6x in One Command. Unified CLI for GGUF, GPTQ, and AWQ quantization.

neural-compressor-3x-tf

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime