Search Results for "mona server mac"
Sort By:
Showing 25 open source projects for "mona server mac"
View related business solutions-
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.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
x64dbg-MCP Server
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin
x64dbg-MCP Server is a native Model Context Protocol plugin that lets AI assistants control x64dbg through HTTP. It exposes debugger operations for loading programs, stepping execution, setting breakpoints, reading memory, inspecting registers, and analyzing modules. The toolset also covers threads, call stacks, symbols, references, pattern scans, PE structures, dumps, tracing, and process internals. Event callbacks let clients react to debugger state changes such as exceptions, pauses, DLL... -
2
Strata
Qwen3.8-Flash-Next on any consumer hardware
Strata is an open-source local inference system for running Qwen3.8-Flash-Next on consumer Windows and Linux PCs. It is designed to make a very large mixture-of-experts model practical with one NVIDIA GPU, system RAM, and local storage instead of server-class hardware. Frequently used experts remain on the GPU while other model components are shared across RAM, CPU, and SSD resources. Speculative decoding uses a smaller helper component to propose tokens that the main model verifies in... -
3
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... -
4
DramaBox
super expressive prompting model based on ltx2.3
DramaBox is an expressive text-to-speech and voice cloning project from Resemble AI built on top of the LTX-2.3 audio branch. It generates speech from prompts that control not only the spoken text, but also speaker identity, emotion, delivery style, laughs, sighs, pauses, and transitions. Users can optionally provide a voice reference of around 10 seconds or more to clone the target timbre while still guiding performance through scene-style prompting. The project includes a warm inference... -
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
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. Both models use a native MXFP4 quantization for... -
6
FastSD CPU
Fast stable diffusion on CPU and AI PC
FastSD CPU is an optimized fork of Stable Diffusion designed to run efficiently on CPUs and devices without dedicated GPUs by leveraging Latent Consistency Models and Adversarial Diffusion Distillation techniques that accelerate inference. It focuses on bringing fast text-to-image generation to mainstream hardware like desktop CPUs, lower-end laptops, or edge devices without requiring high-end graphics processors. The repository contains multiple interfaces including a desktop GUI for simple... -
7
Anthropic SDK TypeScript
Access to Anthropic's safety-first language model APIs
anthropic-sdk-typescript is the TypeScript / JavaScript client library for the Anthropic REST API, enabling backend or Node.js usage of models like Claude. It wraps API endpoints for creating messages, streaming responses, and managing parameters in a type-safe TS environment. The library is designed for server-side use, interfacing with REST, and is stable for integration in web services or backend agents. Example usage shows how to instantiate the Anthropic client, call... -
8
MCPB
One-click local MCP server installation in desktop apps
MCPB (MCP Bundles) defines a packaging format and toolchain for one-click installation of local Model Context Protocol (MCP) servers in desktop apps like Claude for macOS and Windows. An .mcpb file is a zip archive containing your server and a manifest.json that declares capabilities, entry points, permissions, and configuration inputs, much like how .crx packages Chrome extensions or .vsix packages VS Code extensions. The goal is to make local tool servers easy for end users to install,... -
9
TurboFieldfare
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
...Instead of loading the entire model, it keeps the shared core and KV cache in RAM while streaming only the routed experts required for each token from SSD. This approach reduces active memory use to roughly 2 GB while the installed model occupies about 14.3 GB of storage. The project includes a native Mac application, command-line tools, a streaming installer, a Swift library, and an experimental OpenAI-compatible local server. Quantized weights, custom Metal kernels, chunked prefill, and a bounded expert cache improve efficiency. The installer downloads and repacks model ranges without staging a second full checkpoint. Its current scope is text-only Gemma inference on macOS 26 and Apple Silicon hardware. -
Veeam Data Platform v13.1Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
10
HY-MT
Hunyuan Translation Model Version 1.5
HY-MT (Hunyuan Translation) is a high-quality multilingual machine translation model suite developed to support mutual translation across dozens of languages with strong performance even at smaller model scales. It ships with both an 1.8 B parameter model and a larger 7 B model, the latter optimized not only for direct translation but also for formatted and contextualized output, allowing better handling of terminology and mixed-language content. The project emphasizes both speed and... -
11
Transformer Debugger
Tool for exploring and debugging transformer model behaviors
Transformer Debugger (TDB) is a research tool developed by OpenAI’s Superalignment team to investigate and interpret the behaviors of small language models. It combines automated interpretability methods with sparse autoencoders, enabling researchers to analyze how specific neurons, attention heads, and latent features contribute to a model’s outputs. TDB allows users to intervene directly in the forward pass of a model and observe how such interventions change predictions, making it... -
12
MiMo-V2-Flash
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation
MiMo-V2-Flash is a large Mixture-of-Experts language model designed to deliver strong reasoning, coding, and agentic-task performance while keeping inference fast and cost-efficient. It uses an MoE setup where a very large total parameter count is available, but only a smaller subset is activated per token, which helps balance capability with runtime efficiency. The project positions the model for workflows that require tool use, multi-step planning, and higher throughput, rather than only... -
13
gemini-web2api
Convert Google Gemini web into OpenAI-compatible API
gemini-web2api is a Python bridge that exposes Google Gemini web access through OpenAI-compatible API endpoints. It is designed to let OpenAI-style clients connect to Gemini-like models through routes such as chat completions, models, responses, and native Gemini-compatible endpoints. The project can run as a simple local server and uses a mostly single-file design with an optional dependency for streaming. It supports model aliases for Flash, Thinking, Pro-style routing, Auto, and Lite... -
14
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
WASTE is an embeddable C inference engine for running extremely large mixture-of-experts models when the weights exceed available RAM. It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has... -
15
Kev
Jev-like family of decision models built on top of Qwen3.5/3.8
Kev is a family of open decision models inspired by Jev and built on Qwen3.5 and Qwen3.8 foundations. It processes a document together with multiple typed questions and returns probabilities instead of generated prose. Supported question formats include yes-or-no, multiple choice, and ordered scoring. Checkpoints range from a compact 0.8B model for smaller hardware to a 27B version for high-end systems. The models include probability calibration and can run through CUDA, ROCm, or MLX... -
16
Anthropic SDK Python
Provides convenient access to the Anthropic REST API from any Python 3
The anthropic-sdk-python repository is the official Python client library for interacting with the Anthropic (Claude) REST API. It is designed to provide a user-friendly, type-safe, and asynchronous/synchronous capable interface for making chat/completion requests to models like Claude. The library includes definitions for all request and response parameters using Python typed objects, automatically handles serialization and deserialization, and wraps HTTP logic (timeouts, retries, error... -
17
Antigravity Claude Proxy
Proxy that exposes Antigravity provided claude / gemini models
Antigravity Claude Proxy is a purpose-built proxy server that enables developers to interface with Claude models through a standardized RESTful API, allowing tools and workflows that expect generic HTTP APIs to operate on Anthropic’s Claude without native support. The project acts as a translation layer, receiving web requests in common formats (such as OpenAI-style endpoints) and forwarding them to Anthropic’s API in the required structure, while converting responses back into a familiar... -
18
Open-XiaoAI
Let the Xiaoai speaker "hear your voice"
Open-XiaoAI is an open-source framework that takes deeper control of compatible Xiaomi XiaoAI smart speakers by accessing their audio input and output paths. It extends the earlier MiGPT concept beyond cloud API responses and enables developers to build custom voice experiences directly around the speaker hardware. Demonstrations include custom wake words, Xiaozhi AI integration, MiGPT integration, Gemini Live API access, and stereo pairing. The architecture uses separate client and server... -
19
FastViT
This repository contains the official implementation of research
FastViT is an efficient vision backbone family that blends convolutional inductive biases with transformer capacity to deliver strong accuracy at mobile and real-time inference budgets. Its design pursues a favorable latency-accuracy Pareto curve, targeting edge devices and server scenarios where throughput and tail latency matter. The models use lightweight attention and carefully engineered blocks to minimize token mixing costs while preserving representation power. Training and inference... -
20
OpenTinker
OpenTinker is an RL-as-a-Service infrastructure for foundation models
OpenTinker is an open-source Reinforcement Learning-as-a-Service (RLaaS) infrastructure intended to democratize reinforcement learning for large language model (LLM) agents. Traditional RL setups can be monolithic and difficult to configure, but OpenTinker separates concerns across agent definition, environment interaction, and execution, which lets developers focus on defining the logic of agents and environments separately from how training and inference are run. It introduces a... -
21
ChatGPT Retrieval Plugin
The ChatGPT Retrieval Plugin lets you easily find personal documents
The chatgpt-retrieval-plugin repository implements a semantic retrieval backend that lets ChatGPT (or GPT-powered tools) access private or organizational documents in natural language by combining vector search, embedding models, and plugin infrastructure. It can serve as a custom GPT plugin or function-calling backend so that a chat session can “look up” relevant documents based on user queries, inject those results into context, and respond more knowledgeably about a private knowledge... -
22
GLM-130B
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
GLM-130B is an open bilingual (English and Chinese) dense language model with 130 billion parameters, released by the Tsinghua KEG Lab and collaborators as part of the General Language Model (GLM) series. It is designed for large-scale inference and supports both left-to-right generation and blank filling, making it versatile across NLP tasks. Trained on over 400 billion tokens (200B English, 200B Chinese), it achieves performance surpassing GPT-3 175B, OPT-175B, and BLOOM-176B on multiple... -
23
Rampart
Lightweight on-device model for private AI text redaction
Rampart is a lightweight, on-device privacy protection model developed by the National Design Studio to detect and redact personally identifiable information (PII) before text leaves a user's device. Rather than relying on server-side filtering, Rampart performs token-level PII detection locally, enabling privacy-preserving AI interactions with minimal latency and without exposing sensitive information to external services. The released model is a 14.7 MB ONNX artifact based on a fine-tuned... -
24
Grok-2.5
Large-scale xAI model for local inference with SGLang, Grok-2.5
Grok-2.5 is a large-scale AI model developed and released by xAI in 2024, made available through Hugging Face for research and experimentation. The model is distributed as raw weights that require specialized infrastructure to run, rather than being hosted by inference providers. To use it, users must download over 500 GB of files and set them up locally with the SGLang inference engine. Grok-2.5 supports advanced inference with multi-GPU configurations, requiring at least 8 GPUs with more... -
25
Mistral Large 3 675B Instruct 2512 Eagle
Speculative-decoding accelerator for the 675B Mistral Large 3
Mistral Large 3 675B Instruct 2512 Eagle is the dedicated speculative-decoding draft model for the full Mistral Large 3 Instruct system, designed to significantly speed up generation while preserving high output quality. It works alongside the primary 675B instruct model, enabling faster response times by predicting several tokens ahead using Mistral’s Eagle speculative method. Built on the same frontier-scale multimodal Mixture-of-Experts architecture, it complements a system featuring 41B...
- Previous
- You're on page 1
- Next
