Search Results for "kimi"
Sort By:
Showing 22 open source projects for "kimi"
View related business solutions-
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
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
Kimi-K3
Open Frontier Intelligence
Kimi K3 is an open-weight, native multimodal agentic model from Moonshot AI for advanced reasoning, coding, and knowledge work. It uses a 2.8-trillion-parameter mixture-of-experts architecture while activating 104 billion parameters per token. Its design combines Kimi Delta Attention, gated multihead latent attention, Attention Residuals, and Stable LatentMoE routing. -
2
Kimi K2.5
Moonshot's most powerful AI model
Kimi K2.5 is Moonshot AI’s open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed vision and text tokens. Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. -
3
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
...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. With its high-dimensional attention mechanisms and expert routing, Kimi-K2 excels across benchmarks in live coding, math reasoning, and problem solving. -
4
Kimi k1.5
Scaling Reinforcement Learning with LLMs
...By using techniques like partial rollouts to improve training efficiency and applying sophisticated policy optimization methods, the developers demonstrate that strong ability can emerge without relying on complex solutions like Monte Carlo tree search or value functions. Kimi-k1.5 is trained jointly on text and vision data, giving it true multimodal reasoning capabilities where it can interpret and generate content across modalities in a unified way. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
Kimi-Audio
Audio foundation model excelling in audio understanding
Kimi-Audio is an ambitious open-source audio foundation model designed to unify a wide array of audio processing tasks — from speech recognition and audio understanding to generative conversation and sound event classification — within a single cohesive architecture. Instead of fragmenting work across specialized models, Kimi-Audio handles automatic speech recognition (ASR), audio question answering, automatic audio captioning, speech emotion recognition, and audio-to-text chat in one system, enabling developers to build rich, multimodal audio applications without stitching together disparate components. ... -
6
Kimi Linear
An expressive, efficient attention architecture
Kimi Linear is a hybrid linear attention architecture developed for efficient language modeling across short, long-context, and reinforcement learning workloads. Its core mechanism, Kimi Delta Attention, refines the gated delta rule with fine-grained controls for managing finite-state recurrent memory. The architecture combines KDA and global Multi-head Latent Attention layers at a 3:1 ratio to preserve model quality while reducing memory demands. -
7
Kimi K3 in C
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU
Kimi K3 in C is a portable C99 inference engine built to run the 2.78-trillion-parameter Kimi K3 model on CPUs without BLAS, machine-learning frameworks, or GPUs. It demonstrates inference from a roughly 1.56 TB checkpoint with measured memory use as low as 8.24 GB. The runtime streams model trunk layers and routed experts from disk instead of keeping all weights resident in memory. -
8
Kimi Code CLI
Kimi Code CLI is your next CLI agent
Kimi CLI is a command-line AI agent that brings an intelligent software development assistant directly into your terminal, helping you with coding tasks, shell operations, and workflow automation without leaving your command prompt. It supports an interactive shell-like user interface where you can chat with the agent, request code edits, run shell commands, and receive contextual suggestions as you work, creating a seamless blend of AI-augmented development and traditional terminal usage. ... -
9
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
...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 no third-party runtime dependency on its CPU inference path and exposes both a CLI and C library. An optional server provides an OpenAI-compatible chat API with streaming, tools, structured output, and image support. Validation compares layers, logits, vision output, and prompt rendering against reference implementations. -
Veeam Data Platform v13.1 - Get Your Free TrialTry 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
FlashKDA
High-performance Kimi Delta Attention kernels
FlashKDA is an open-source library of high-performance CUDA kernels for Kimi Delta Attention, implemented on NVIDIA CUTLASS. It is intended to accelerate the forward pass used by KDA-based language models on modern NVIDIA GPUs. The package integrates with flash-linear-attention and can be selected automatically as the backend for chunk_kda during inference. It supports recurrent state input and output, variable-length batches, internal gating, query-key normalization, and beta activation. ... -
11
Ollama
Run models like Kimi-K2.5, GLM-5, DeepSeek, gpt-oss, Gemma, Qwen etc.
Ollama is an open-source platform that enables developers to run large language models locally on their own machines. It simplifies working with modern AI models by providing a unified interface to download, manage, and interact with them. Users can run models like Llama, Gemma, Qwen, and others directly from the command line or through APIs. Ollama also integrates with popular developer tools and AI agents, allowing seamless workflows across coding environments and applications. It supports... -
12
Mooncake
Mooncake is the serving platform for Kimi
Mooncake is an open-source infrastructure platform designed to optimize large language model serving by focusing on efficient management and transfer of model data and KV cache. The platform was originally developed as part of the serving infrastructure for the Kimi large language model system. Its architecture centers on a high-performance transfer engine that provides unified data transfer across different storage and networking technologies. This engine enables efficient movement of tensors and model data across heterogeneous environments such as GPU memory, system memory, and distributed storage systems. ... -
13
Kirara AI
DIY multimodal AI chatbot
...It supports multi-turn conversation, persona presets, keyword-triggered replies, administrator commands, and conditional automation. The project can work with model providers such as OpenAI, DeepSeek, Claude, Gemini, Qwen, Mistral, Kimi, Minimax, and others. It also supports image generation models, voice replies, cross-platform message sending, and custom workflows. A WebUI helps users manage models, workflows, plugins, and platform settings without editing every detail manually. Kirara AI is especially useful for users who want a configurable AI bot that can run across multiple messaging environments. -
14
Wandesk
Give intelligence shape. Let AI sculpt your desktop
...Its App Workshop can generate a React UI, backend API, and SQLite storage together, allowing users to create usable local tools without manually writing the whole application. Wandesk is local-first, works without signup, and can connect to providers such as Claude, Codex, DeepSeek, OpenAI, Kimi, Qwen, or any OpenAI-compatible endpoint. Built-in apps include Chat, Notebook, Ledger, Memory, Files, Tasks, Settings, Claude Code, Codex, and Open Source Radar. It is useful for users who want an AI workspace where apps, memory, and coding agents share context instead of living in separate chat threads. -
15
Ai-Assistant
Open-source novel writing & AI coding assistant aggregating top models
This is an open‑source, powerful novel‑writing and AI programming assistant with the following core strengths: Model Aggregation: Natively supports the latest DeepSeek and seamlessly integrates with top‑tier models such as Gemini, Claude, GPT, Tongyi Qianwen, Kimi, and others—both domestic and international—delivering a one‑stop intelligent experience. Multimodal Capability: Accurately interprets images and PDF content, and supports invoking advanced models for high‑quality text‑to‑image generation. Security & Management: Conversation records are encrypted and stored locally (SQLite), with convenient history search, bookmarking, and categorization. ... -
16
Luna AI
Virtual AI anchor that combines state-of-the-art technology
...It is built around a core assistant persona called “Luna AI,” which can be driven by a wide range of large language models and platforms, including GPT-style APIs, Claude, LangChain-based backends, ChatGLM, Kimi, Ollama, and many others. The project supports multiple rendering backends for the avatar, such as Live2D, Unreal Engine (UE), and “xuniren,” and can output to streaming platforms like Bilibili, Douyin, Kuaishou, WeChat Channels, Pinduoduo, Douyu, YouTube, Twitch, and TikTok. For voice, it integrates with numerous TTS engines (Edge-TTS, VITS-Fast, ElevenLabs, VALL-E-X, OpenVoice, GPT-SoVITS, Azure TTS, fish-speech, ChatTTS, CosyVoice, F5-TTS, MultiTTS, MeloTTS, and others), and can optionally pass the output through voice conversion systems like so-vits-svc or DDSP-SVC to change timbre. -
17
AutoGameKiller ona verilmiş vaxt intervallarında verilmiş oyun və digər proqramları bağlamaq üçün qurulub. Bir çoxları üçün problem yaratsa da mənə və məncə mənim kimi bir çoxunun işinə yarayacaq.
-
18
Kimi K3
Powerful, native multimodal AI agentic model
Kimi K3 combines native text and image understanding deliver frontier-level performance more efficiently. -
19
Kimi K2.6
Multimodal agent model for coding, orchestration, and autonomy
Kimi K2.6 is an open-source native multimodal agentic model built for advanced autonomous execution, long-horizon coding, and large-scale task orchestration. It is designed to handle complex end-to-end software workflows across multiple languages and domains, including front-end development, DevOps, performance optimization, and coding-driven design. -
20
Kimi K2.7 Code
Coding-focused Kimi model for long-horizon agent workflows
Kimi K2.7 Code is a coding-focused agentic model built on Kimi K2.6, designed for long-horizon software engineering, autonomous coding workflows, and complex tool-based execution. It improves end-to-end task completion across real-world programming scenarios while reducing thinking-token usage by about 30% compared with K2.6. Architecturally, it uses a 1T-parameter Mixture-of-Experts design with 32B activated parameters, 61 layers, 384 experts, a 256K-token context window, and a MoonViT vision encoder. ... -
21
Azerbaycandaki zeyif media sektorunun inkifına kömek etmek üçün hazırlanan Xeber Skripti. Esas Xususiyyetleri: Çox Dillidir, Müxtelif icazeli çoxlu quruplar ve bu quruplara üzv istifadeçiler, MVC destekli, anket vs kimi xeber sistemlerinde eht
-
22
Ling 3.0 Tiny
Lightweight MoE model for local reasoning, coding, and AI agents
Ling-3.0-tiny is inclusionAI’s lightweight hybrid reasoning Mixture-of-Experts model, designed to provide capable reasoning and agentic performance at low inference cost. It contains 7.9B total parameters while activating only 1.3B per token, using a hybrid architecture that alternates Kimi Delta Attention and Multi-Head Latent Attention with a sparse 128-expert MoE. The model supports both fast responses and configurable multi-step thinking, covering general agents, coding, mathematics, scientific reasoning, and instruction following. It is specifically optimized for local and resource-constrained deployment and has been validated on NVIDIA DGX Spark, Apple Silicon MacBooks, and Mac mini systems. ...
- Previous
- You're on page 1
- Next
