LiteObject/llm-quantization-playground
A hands-on demo project that compares multiple quantization methods for LLMs, including FP16, INT8, and 4-bit (GPTQ, AWQ, GGML, bitsandbytes). The goal is to understand real-world tradeoffs between model size, latency, throughput, GPU memory usage, and output quality.
Stars
—
Forks
—
Language
—
License
MIT
Category
Last pushed
Nov 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/LiteObject/llm-quantization-playground"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
intel/auto-round
🎯An accuracy-first, highly efficient quantization toolkit for LLMs, designed to minimize quality...
ModelCloud/GPTQModel
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD...
pytorch/ao
PyTorch native quantization and sparsity for training and inference
Picovoice/picollm
On-device LLM Inference Powered by X-Bit Quantization
NVIDIA/kvpress
LLM KV cache compression made easy