Search Results for "bit"
Sort By:
Showing 37 open source projects for "bit"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
Bonsai 27B
Run Bonsai (1-bit) and Ternary-Bonsai language models locally
Bonsai 27B is a repository for downloading, configuring, and running PrismML’s highly compressed Bonsai language models on local hardware. It supports the 1-bit Bonsai and higher-quality Ternary-Bonsai families in 1.7B, 4B, 8B, and 27B sizes. The models can run on macOS, Linux, and Windows through CPU, Metal, CUDA, Vulkan, ROCm, llama.cpp, or MLX backends. Its 27B models process text, images, screenshots, and PDFs while supporting reasoning and long-context conversations. They also provide OpenAI-compatible tool calling and optional MCP server integration for agentic workflows. ... -
2
bitnet.cpp
Official inference framework for 1-bit LLMs
...The project’s focus on extreme quantization dramatically reduces memory footprint and energy consumption compared with traditional 16-bit or 32-bit LLMs, making it practical to deploy advanced language understanding and generation models on everyday machines. BitNet is built to scale across architectures, with configurable kernels and tiling strategies that adapt to different hardware, and it supports large models with impressive throughput even on modest resources. -
3
AIMET
AIMET is a library that provides advanced quantization and compression
...Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed. -
4
Z80-μLM
Z80-μLM is a 2-bit quantized language model
Z80-μLM is a retro-computing AI project that demonstrates a tiny language model (Z80-μLM) engineered to run on an 8-bit Z80 CPU by aggressively quantizing weights down to 2-bit precision. The repository provides a complete workflow where you train or fine-tune conversational models in Python, then export them into a format that can be executed on classic Z80 systems. A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
Text Generation Web UI
Oobabooga - The definitive Web UI for local AI, with powerful features
...Markdown output for GALACTICA, including LaTeX rendering. Custom chat characters. Advanced chat features (send images, get audio responses with TTS). Very efficient text streaming. Parameter presets, 8-bit mode. Layers splitting across GPU(s), CPU, and disk. CPU mode, FlexGen, DeepSpeed ZeRO-3, API with streaming and without streaming. LLaMA model, including 4-bit GPTQ. RWKV model, LoRA (loading and training), Softprompts, and extensions. -
6
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch
bitsandbytes is an open-source library designed to make training and inference of large neural networks more efficient by dramatically reducing memory usage. Built primarily for the PyTorch ecosystem, the library introduces advanced quantization techniques that allow models to operate using reduced numerical precision while maintaining high accuracy. These optimizations enable large language models and other deep learning architectures to run on hardware with limited memory resources,... -
7
VibeVoice ComfyUI
ComfyUI integration for Microsoft's VibeVoice text-to-speech model
VibeVoice ComfyUI is a comprehensive wrapper that integrates Microsoft’s VibeVoice text-to-speech models directly into ComfyUI workflows. It exposes VibeVoice as a set of custom nodes so you can build single-speaker and multi-speaker voice generation pipelines visually, combining TTS with other audio or generative components. The integration supports high-quality single-speaker synthesis as well as scripted multi-speaker conversations, with optional voice cloning from audio samples for each... -
8
SageAttention
NeurIPS2025 Spotlight] Quantized Attention
SageAttention is an open-source optimization library designed to accelerate the attention mechanism used in transformer-based neural networks. Since attention operations are often the most computationally expensive component of modern AI models, SageAttention introduces quantization techniques that significantly reduce computational overhead while preserving model accuracy. The system achieves this by using low-precision numerical formats such as INT4, FP8, or INT8 to represent key matrices... -
9
esp32-ai
Running a 28.9M parameter LLM on an $8 microcontroller
esp32-ai is an experimental language-model project that runs a 28.9-million-parameter model entirely on an ESP32-S3 microcontroller. The quantized model occupies about 14.9 MB and generates text without sending data to a server. Most parameters remain in flash through a Per-Layer Embeddings design, while active computation uses SRAM and PSRAM. This memory layout allows the device to retrieve only the embedding rows required for each token. The implementation reaches roughly 9.5 tokens per... -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
10
ChatGLM3
ChatGLM3 series: Open Bilingual Chat LLMs | Open Source Bilingual Chat
...The family includes base and long-context variants (8K/32K/128K). The repo ships Python APIs, CLI and web demos (Gradio/Streamlit), an OpenAI-format API server, and a compact fine-tuning kit. Quantization (4/8-bit), CPU/MPS support, and accelerator backends (TensorRT-LLM, OpenVINO, chatglm.cpp) enable lightweight local or edge deployment. -
11
Papermerge
Open Source Document Management System for Digital Archives
Papermerge is an open source document management system (DMS) primarily designed for archiving and retrieving your digital documents. Instead of having piles of paper documents all over your desk, office or drawers - you can quickly scan them and configure your scanner to directly upload to Papermerge DMS. Store, organize and index scanned documents in PDF, JPEG and TIFF formats. Instantly find relevant information using full text, tags and metadata-based search. Papermerge is free and... -
12
Ludwig AI
Low-code framework for building custom LLMs, neural networks
...Comprehensive config validation detects invalid parameter combinations and prevents runtime failures. Automatic batch size selection, distributed training (DDP, DeepSpeed), parameter efficient fine-tuning (PEFT), 4-bit quantization (QLoRA), and larger-than-memory datasets. Retain full control of your models down to the activation functions. Support for hyperparameter optimization, explainability, and rich metric visualizations. Experiment with different model architectures, tasks, features, and modalities with just a few parameter changes in the config. ... -
13
TurboDiffusion
100–200× Acceleration for Video Diffusion Models
TurboDiffusion is an advanced open-source framework designed to dramatically accelerate video diffusion model generation, aiming for performance improvements on the order of 100–200× compared with traditional implementations while retaining high output quality. It achieves this by combining a suite of algorithmic and engineering optimizations, including attention acceleration techniques, efficient step distillation methods, and quantization strategies that reduce computational overhead. The... -
14
Watermark Anything
Official implementation of Watermark Anything with Localized Messages
Watermark Anything (WAM) is an advanced deep learning framework for embedding and detecting localized watermarks in digital images. Developed by Facebook Research, it provides a robust, flexible system that allows users to insert one or multiple watermarks within selected image regions while maintaining visual quality and recoverability. Unlike traditional watermarking methods that rely on uniform embedding, WAM supports spatially localized watermarks, enabling targeted protection of... -
15
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
FastDeploy is an open-source inference and deployment toolkit designed to simplify the process of running and serving deep learning models across a wide range of hardware platforms. Developed within the PaddlePaddle ecosystem, the toolkit focuses on providing high-performance deployment capabilities for modern AI models including large language models and vision-language systems. The platform enables developers to deploy trained models quickly using optimized inference pipelines that support... -
16
Transformer Engine
A library for accelerating Transformer models on NVIDIA GPUs
Transformer Engine (TE) is a library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper GPUs, to provide better performance with lower memory utilization in both training and inference. TE provides a collection of highly optimized building blocks for popular Transformer architectures and an automatic mixed precision-like API that can be used seamlessly with your framework-specific code. -
17
BitNet
BitNet: Scaling 1-bit Transformers for Large Language Models
BitNet is a machine learning research implementation that explores extremely low-precision neural network architectures designed to dramatically reduce the computational cost of large language models. The project implements the BitNet architecture described in research on scaling transformer models using extremely low-bit quantization techniques. In this approach, neural network weights are quantized to approximately one bit per parameter, allowing models to operate with far lower memory usage than traditional 16-bit or 32-bit neural networks. The architecture introduces specialized layers such as BitLinear, which replace standard linear projections in transformer networks with quantized operations. ... -
18
Qwen2.5-Omni
Capable of understanding text, audio, vision, video
Qwen2.5-Omni is an end-to-end multimodal flagship model in the Qwen series by Alibaba Cloud, designed to process multiple modalities (text, images, audio, video) and generate responses both as text and natural speech in streaming real-time. It supports “Thinker-Talker” architecture, and introduces innovations for aligning modalities over time (for example synchronizing video/audio), robust speech generation, and low-VRAM/quantized versions to make usage more accessible. It holds... -
19
CogVLM
A state-of-the-art open visual language model
...The flagship CogVLM-17B combines ~10B visual parameters with ~7B language parameters and supports 490×490 inputs; CogAgent-18B extends this to 1120×1120 and adds plan/next-action outputs plus grounded operation coordinates for GUI tasks. The repo provides multiple ways to run models (CLI, web demo, and OpenAI-Vision–style APIs), along with quantization options that reduce VRAM needs (e.g., 4-bit). It includes checkpoints for chat, base, and grounding variants, plus recipes for model-parallel inference and LoRA fine-tuning. The documentation covers task prompts for general dialogue, visual grounding (box→caption, caption→box, caption+boxes), and GUI agent workflows that produce structured actions with bounding boxes. -
20
Admin365 AI Re-Edition
TechNews365 OS Admin AI intègre un Assistant Vocal IA 100% local !
...Système : Mint 22.3 Cinnamon, kernel 7.0 stable, support UEFI/Legacy, live session + installation, menus optimisés. Compatibilité Windows : Wine 9.x préconfiguré, Winetricks intégré, préfixe 64‑bit optimisé, support des applications Windows pro, tests installation/exécution validés. WinBoat : environnement Windows conteneurisé via Docker + RDP, isolation complète, compatible Cinnamon, installation et lancement validés. IA : Ollama + Phi‑3, Assistant Vocal IA (Whisper), Page Assist, Murmure . Admin & Réseau : GNS3, Wireshark, iperf3, phpIPAM, X2Go, AnyDesk, Docker + Compose, Portainer . ... -
21
ollama_manager_gui
A graphical manager for ollama that can manage your LLMs
This app will help install ollama and LLMs using the gui provided by this app. It checks for ollama when launched and if it doesn't exist it will help by bringing you to the ollama site for download. This app is heavily upgraded and now also works properly on Linux. It now has progress bars and many many many improvements. It can launch the LLM by clicking the link. it can launch multiple LLMs in separate windows. It can also remove an installed LLM. There is a confirmation... -
22
Curated Transformers
PyTorch library of curated Transformer models and their components
...Supports state-of-the-art transformer models, including LLMs such as Falcon, Llama, and Dolly v2. Implementing a feature or bugfix benefits all models. For example, all models support 4/8-bit inference through the bitsandbytes library and each model can use the PyTorch meta device to avoid unnecessary allocations and initialization. -
23
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis
AutoGPTQ is an implementation of GPTQ (Quantized GPT) that optimizes large language models (LLMs) for faster inference by reducing their computational footprint while maintaining accuracy. -
24
FastChat
Open platform for training, serving, and evaluating language models
...This requires 8-bit compression to be enabled and the bitsandbytes package to be installed, which is only available on linux operating systems. -
25
LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant
Visual instruction tuning towards large language and vision models with GPT-4 level capabilities.
