awesome-model-quantization
github.com/efficient-ml/awesome-model-quantization ↗A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me 2021 resources from awesome-model-quantization"
Installation instructions →What's inside
Related Repositories
- AIMETQuantization and training toolkits
Post-training and quantization-aware model optimization.
- Awesome Efficient AIGCPaper collections
Efficient language and generative models; formerly Awesome Efficient LLM & Diffusion.
- Awesome Quantization PapersPaper collections
A complementary collection of neural network quantization papers.
- BitNetInference and hardware
Inference framework for supported native low-bit BitNet models.
- bitsandbytesQuantization and training toolkits
Low-bit linear layers and quantized optimizers, including implementations used by LLM.int8() and QLoRA.
- BrevitasQuantization and training toolkits
PyTorch quantization-aware training with configurable quantizers and hardware export.
Benchmarks
- An empirical study of LLaMA3 quantization: from LLMs to MLLMsCodeScholar
LLMs + multimodal Examines low-bit behavior across LLaMA3 language and multimodal models.
- An Empirical Study of Qwen3 QuantizationCodeScholar
Dense + MoE LLMs Studies quantization across Qwen3 model sizes, architectures and reasoning settings.
- BiBench: Benchmarking and Analyzing Network BinarizationCodeScholar
Binary networks Compares binarization methods across tasks, architectures and deployment settings.
Survey Papers
- A Survey of Low-bit Large Language Models: Basics, Systems, and AlgorithmsScholar
LLM algorithms + systems Connects low-bit LLM algorithms with numerical formats and inference systems.
- A Survey of Quantization Methods for Efficient Neural Network InferenceScholar
Foundations + taxonomy Reviews quantization design choices, mixed precision and the trade-offs between model accuracy and efficient inference.
- A White Paper on Neural Network QuantizationScholar
Practical PTQ + QAT Explains quantizer design, common failure modes and practical post-training and quantization-aware training workflows.
- Binary Neural Networks: A SurveyScholar
Binary networks Surveys binary network representations, training methods and applications.
Showing a sample of 782 resources. View the full list on GitHub →