Search Results for "32-bit"
Sort By:
33 projects for "32-bit" with 2 filters applied:
-
$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.
-
Paessler: Easy to Use With Enterprise Power. Free TrialYou shouldn't have to choose between a monitoring tool that's easy to use and one that's powerful enough for a complex environment. PRTG's low-code interface lets any admin build dashboards, set alerts and monitor devices without scripting, while custom sensors and full API access are there when your team needs deeper control. One platform, no compromise. Download a free 30-day trial now.
-
1
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. -
2
openTPU
An open-source AI accelerator, developed by AI
openTPU is an open-source AI accelerator project that exposes an entire inference hardware stack in one readable repository. It includes SystemVerilog RTL, a custom instruction set, a bit-exact simulator, a kernel language, compiler tooling, host software, and profiling utilities. The hardware design runs on a Xilinx Kintex-7 PCIe FPGA card and has been demonstrated with modern language models including Qwen, LFM, Gemma, SmolLM, and Phi variants. Both int8 and compact 4-bit weight formats are supported to trade memory use, accuracy, and throughput. ... -
3
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
Kimi K2 is Moonshot AI’s advanced open-source large language model built on a scalable Mixture-of-Experts (MoE) architecture that combines a trillion total parameters with a subset of ~32 billion active parameters to deliver powerful and efficient performance on diverse tasks. It was trained on an enormous corpus of over 15.5 trillion tokens to push frontier capabilities in coding, reasoning, and general agentic tasks while addressing training stability through novel optimizer and architecture design strategies. The model family includes variants like a foundational base model that researchers can fine-tune for specific use cases and an instruct-optimized variant primed for general-purpose chat and agent-style interactions, offering flexibility for both experimentation and deployment. ... -
4
1D Visual Tokenization and Generation
This repo contains the code for 1D tokenizer and generator
The 1D Visual Tokenization and Generation project from ByteDance introduces a novel “one-dimensional” tokenizer designed for images: instead of representing images with large grids of 2D tokens (as in many prior generative/image-modeling systems), it compresses images into as few as 32 discrete tokens (or more, optionally) — thereby achieving a very compact, efficient representation that drastically speeds up generation and reconstruction while retaining strong fidelity. This compact representation makes sampling and generation many times faster compared to previous tokenization methods (claims of ~410× speedups relative to heavyweight models) while still producing competitive image quality. ... -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
FLUX.2
Official inference repo for FLUX.2 models
FLUX.2 is a state-of-the-art open-weight image generation and editing model released by Black Forest Labs aimed at bridging the gap between research-grade capabilities and production-ready workflows. The model offers both text-to-image generation and powerful image editing, including editing of multiple reference images, with fidelity, consistency, and realism that push the limits of what open-source generative models have achieved. It supports high-resolution output (up to ~4 megapixels),... -
6
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. ... -
7
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... -
8
Code World Model (CWM)
Research code artifacts for Code World Model (CWM)
CWM (Code World Model) is a 32-billion-parameter open-weights language model. It is developed by Meta for enhancing code generation and reasoning about programs. It is explicitly trained on execution traces, action-observation trajectories, and agentic interactions in controlled environments. It has been developed to better capture how code, actions, and state interact over time. -
9
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... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
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... -
11
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... -
12
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. ... -
13
FLUX.1 Krea
Powerful open source image generation model
...It is a rectified-flow model distilled from the original Krea 1, providing enhanced sampling efficiency through classifier-free guidance distillation. The model supports generation at resolutions between 1024 and 1280 pixels with recommended inference steps between 28 and 32 for optimal balance of speed and quality. FLUX.1 Krea is fully compatible with the FLUX.1 architecture, making it easy to integrate into existing workflows and pipelines. The repository offers easy-to-use inference scripts and a Jupyter Notebook example to facilitate quick experimentation and adoption. Users can run the model locally after downloading weights from Hugging Face and benefit from a live demo available on krea.ai. -
14
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 . ... -
15
GLM-4-32B-0414
Open Multilingual Multimodal Chat LMs
GLM-4-32B-0414 is a powerful open-source large language model featuring 32 billion parameters, designed to deliver performance comparable to leading models like OpenAI’s GPT series. It supports multilingual and multimodal chat capabilities with an extensive 32K token context length, making it ideal for dialogue, reasoning, and complex task completion. The model is pre-trained on 15 trillion tokens of high-quality data, including substantial synthetic reasoning datasets, and further enhanced with reinforcement learning and human preference alignment for improved instruction-following and function calling. ... -
16
LLaMA INT8
Quantized inference code for LLaMA models
LLaMA INT8 is an experimental fork of Meta’s original LLaMA code for running large models with reduced memory through 8-bit quantization. It relies heavily on bitsandbytes and the LLM.int8() technique for compressed inference. The implementation quantizes weights on the host and loads them incrementally to avoid large memory spikes. Parallelism constructs from the original code were removed to simplify single-machine execution. The author demonstrated LLaMA 13B running within roughly 24 GiB of GPU memory on an RTX 4090. ... -
17
HiFi-GAN
Generative Adversarial Networks for Efficient and High Fidelity Speech
...In experiments on LJSpeech, HiFi-GAN was shown to achieve mean opinion scores close to human recordings while synthesizing 22.05 kHz audio up to ~168× faster than real time on an NVIDIA V100 GPU. A smaller configuration trades a bit of quality for even higher speed and can run more than 13× faster than real time on CPU, making it suitable for deployment scenarios without powerful GPUs. -
18
Immutable Sparse Wave Trees (WaveTree)
Realtime bigdata tool for bit strings up to 2^63 based on AVL forest
Realtime bigdata tool at the bit level based on immutable AVL forest which can be run in memory or, in future versions, as a merkle forest like a blockchain. Main object is a sparse bit string (Bits) that efficiently scales up to 2^63 bits normally compressed as forest has duplicated substrings. Bits objects support reading bit, byte, short, int, or long (Java primitives) at any bit index in 64 bit range. -
19
-
20
Delayed Response Network
Neural network based on signal delays.
An artificial neural network, currently specialized to save a specific bit pattern, mainly by changing the signal propagation delays in links. More features, variables and algorithms will be added in time. -
21
EZvolve Foundation Classes
Data types and utility classes for use with evolutionary algorithms.
EZvolve Foundation Classes is a set of data types and utility classes for use with evolutionary algorithms. Currently implemented support for bit string encoding, populations, fitnesses, fitness functions, probabilities, and probability vectors. -
22
Open BEAGLE
Evolutionary Computation Framework in C++
Open BEAGLE is a C++ Evolutionary Computation (EC) framework. It provides an high-level software environment to do any kind of EC, with support for tree-based genetic programming; bit string, integer-valued vector, and real-valued vector genetic algorithms; and evolution strategy. The Open BEAGLE architecture follows strong principles of object oriented programming, where abstractions are represented by loosely coupled objects and where it is common and easy to reuse code. Open BEAGLE is designed to provide an EC environment that is generic, user friendly, portable, efficient, robust, elegant, and free. -
23
This is a Robot simulation game that allows you to write a robot in any language you might want. The robot communicates with the game using the internet and up to 32 robots can be run at a time. WARNING: The current version is not complete!
-
24
This project focuses on experiments of AI using JAVA, but with just that bit of extra effort that might make those experiments become of use for others as well.
-
25
Nemotron 3
Large language model developed and released by NVIDIA
NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 is a state-of-the-art large language model developed and released by NVIDIA as part of its Nemotron 3 family, optimized for high-efficiency inference and strong reasoning performance in open AI workloads. It is the post-trained and FP8-quantized variant of the Nemotron 3 Nano model, meaning its weights and activations are represented in 8-bit floating point (FP8) to dramatically reduce memory usage and computational cost while retaining high accuracy. The base Nano architecture uses a hybrid Mamba-Transformer Mixture-of-Experts (MoE) design, allowing the model to activate only a small fraction of its 31.6 billion parameters per token, which improves speed and efficiency without sacrificing quality on complex queries. ...
