3862 related articles

Ollama is a free, open-source LLM management platform that lets you deploy open-source models like DeepSeek locally with one click. It supports macOS, Windows, Linux, and Docker, with both API and CLI modes to build private AI apps at zero cost.

GLM-5.2 enters internal testing; Moore Threads open-sources MUSA Coder, China's first code LLM trained on domestic GPUs; Google backs Anthropic with $35B in guarantees.

A hands-on comparison of 6 open-source LLMs (DeepSeek, Qwen3, Zhipu GLM, Kimi K2, MiniMax M3, Tencent Hunyuan 3) for on-premise deployment—covering hardware cost, inference efficiency, and deployment difficulty.

A deep dive into DeepSeek Coder V1 to V2: MoE architecture, 128K context, 90.2% HumanEval pass rate, and how it became the first open-source model to beat GPT-4 Turbo.

An in-depth analysis of the open-source LLM control plane tool Otari—covering unified multi-model access, cost observability, and security compliance governance to help teams build manageable, production-grade AI infrastructure.

Ollama is a free, open-source local LLM platform supporting macOS, Windows, Linux, and Docker. Easily deploy DeepSeek and other open-source models with API and CLI support — no complex GPU setup required.

Deep dive into OpenLLMVTuber, a 10K-star open-source AI virtual character framework integrating ASR, LLM, TTS, and Live2D with voice interruption, visual perception, and modular architecture.

Deep dive into OpenAgent, an open-source AI assistant featuring Computer Use, Browser Use, and Coding Agent capabilities, built on LLM + RAG + Agent Loops.

Deep dive into LlamaFactory, an open-source unified fine-tuning framework supporting 100+ LLMs and VLMs with LoRA, QLoRA, RLHF methods, Web UI, 71K+ GitHub Stars, accepted at ACL 2024.

Deep dive into Cherry Studio, an open-source AI client supporting 300+ LLMs including OpenAI, Claude, and Gemini, with autonomous agents and pre-built assistants. Nearly 47K GitHub Stars.
TutorialsA detailed guide to Ollama's core features: free open-source local LLM management with cross-platform support, intelligent GPU/CPU scheduling, and API integration for running DeepSeek and other open-source models locally at zero cost.
TutorialsDeep dive into how EasyLLM CLI modifies Gemini CLI to support any LLM including local models, solving account barriers, model lock-in, and data security issues with code-level API integration.
Product ReviewsMeta releases Llama 3.3 70B open-source model with just 70B parameters rivaling 405B performance. Tested on 13 logic, math, and coding questions, it passed 12 — reshaping the open-source model landscape.
Product ReviewsOne API is an open-source LLM API gateway that unifies 30+ LLM providers including OpenAI, Claude, Gemini, and DeepSeek through an OpenAI-compatible interface. Features Key management, quota control, load balancing, and one-command Docker deployment. 32k+ GitHub Stars.
Product ReviewsOne API is an open-source LLM API gateway with 32K+ GitHub Stars, supporting unified access to 30+ models including OpenAI, Claude, and DeepSeek. Complete guide covering Docker deployment, Key management, and load balancing.
Product ReviewsOne API is an open-source LLM API gateway with 32K+ GitHub Stars, unifying 30+ models like OpenAI, Claude, Gemini & DeepSeek into one OpenAI-compatible interface.
TutorialsA detailed guide to One API, the open-source LLM gateway. Unify 30+ models (OpenAI, Claude, Gemini, DeepSeek) into one OpenAI-compatible format with load balancing and usage tracking.
Product ReviewsOne API is an open-source LLM API gateway with 32K GitHub stars, supporting unified management of 30+ models including OpenAI, Claude, and DeepSeek via OpenAI-compatible format.
Product ReviewsOne API is an open-source LLM API management & distribution system supporting 30+ models including OpenAI, Claude, Gemini, and DeepSeek with unified access, key management, load balancing, and usage monitoring. Docker deployable, 32,000+ GitHub Stars.
Product ReviewsOne API is an open-source LLM API gateway with 32K+ GitHub Stars that unifies 30+ models (OpenAI, Claude, DeepSeek, Qwen) into OpenAI-compatible format. Learn its core features, Docker deployment, and key management.