int8 开源项目推荐（270 个）

intel /neural-compressor

SOTA低比特LLM量化（INT 8/FP 8/MXFP 8/INT 4/MXFP 4/NVFP 4）和稀疏性; PyTorch、TensorFlow和ONNX SYS上领先的模型压缩技术

StartLuxLabs /StartLux-Prism

该项目在 GitHub 上没有填写描述

intel /neural-speed

An innovative library for efficient LLM inference via low-bit quantization

Dicklesworthstone /franken_ocr

纯锈、仅CPU的OCR引擎，适用于百度无限OCR（一款基于DeepSeek-OCR的3B MoE VLM）。一个固定模型，定制的int4/int8内核，没有机器学习框架，没有GPU。前阶段0的支架。

clancylian /retinaface

Reimplement RetinaFace use C++ and TensorRT

Wulingtian /yolov5_tensorrt_int8_tools

tensorrt int8 量化yolov5 onnx模型

Wulingtian /yolov5_tensorrt_int8

TensorRT int8 量化部署 yolov5s 模型，实测3.3ms一帧！

Video-Rebirth /hyperflow-h3-flash

HyperFlow H3 Flash: Video Rebirth's 13.7B, 4- to 8-step compressed MiniMax-H3 for joint video and audio generation (INT8 and GGUF)

Saganaki22 /ComfyUI-Viggle-Animate-H3

ComfyUI nodes for Viggle-Animate minimax H3 finetune

xuanandsix /Tensorrt-int8-quantization-pipline

a simple pipline of int8 quantization based on tensorrt.

EricRollei /Comfy_HunyuanImage3

Nodes to run Hunyuan Image 3 locally with BF16 and NF4 quantized options in Comfyui

Wulingtian /RepVGG_TensorRT_int8

RepVGG TensorRT int8 量化，实测推理不到1ms一帧！

the0807 /YOLOv8-ONNX-TensorRT

👀 Apply YOLOv8 exported with ONNX or TensorRT(FP16, INT8) to the Real-time camera

BoumedineBillal /yolo26n_esp

World's First NMS-Free YOLOv26n on ESP32-P4. Features end-to-end Int8 QAT and custom C++ optimizations achieving 30% faster inference than the official ESP-DL YOLOv11n (1.7s vs 2.4s).

sylvesterkaczmarek /phisat2-trustworthy-onboard-ai

Trustworthy onboard satellite AI in PyTorch→ONNX→INT8 with calibration, telemetry, and a PhiSat-2 EO tile-filter demo.

yzfly /edgejev

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev

Wulingtian /nanodet_tensorrt_int8

nanodet int8 量化，实测推理2ms一帧！

kdrkdrkdr /faster-enhancer.c

Pure C implementation of FastEnhancer. 3.3x faster than the ONNX Runtime graph, same quality.

ppogg /ncnn-yolov4-int8

NCNN+Int8+YOLOv4 quantitative modeling and real-time inference

Egorundel /int8_calibrator_cpp

INT8 calibrator for ONNX model with dynamic batch_size at the input and NMS module at the output. C++ Implementation.