AI Model Library: LLMs, Agents & Dev Tools

Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.

Expert analysisUpdated regularlyRSS Feed

Tag: Model Inference

84 article(s) found · Clear tag

2 months agoModel InferenceLLMTool Calling

Ling-3.0-tiny – Ant Ling's Native Hybrid Inference Model

Ling-3.0-tiny is a native hybrid inference model introduced by the Ant Ling team, utilizing a sparse mixture-of-experts architecture (MoE). With a total of 7.9B parameters, it activates only 1.3B para...

Read more
Ling-3.0-tiny – Ant Ling's Native Hybrid Inference Model cover image
2 months agoImage GenerationVideo AIModel Inference

JoyAI-Video-Edit – JD.com's Open-Source Real-Time Streaming Video Editing Model

JoyAI-Video-Edit is a real-time streaming video editing model developed and open-sourced by JD.com. It is based on a self-regressive diffusion architecture with 16B parameters, achieving end-to-end in...

Read more
JoyAI-Video-Edit – JD.com's Open-Source Real-Time Streaming Video Editing Model cover image
3 months agoAI AgentModel InferenceBenchmark

Orchard – Microsoft Research's Open-Source Agentic AI Modeling Framework

Orchard is an open-source Agentic AI modeling framework introduced by Microsoft Research. At its core is the Kubernetes-based Orchard Env environment service, which enables cross-domain reuse of sandb...

Read more
Orchard – Microsoft Research's Open-Source Agentic AI Modeling Framework cover image
3 months agoAI CodingModel InferenceLLM

Instella-MoE – AMD's Open-Source Mixture-of-Experts Language Model Series

Instella-MoE is AMD's open-source Mixture-of-Experts (MoE) language model series, with a total parameter count of 16B and an activated parameter count of 2.8B. It employs a 27-layer decoder architectu...

Read more
Instella-MoE – AMD's Open-Source Mixture-of-Experts Language Model Series cover image
3 months agoAI CodingModel Inference

AngelSpec – An End-to-End Speculative Decoding Training Framework Open-Sourced by Tencent HunYuan Team

AngelSpec is an end-to-end speculative decoding training framework open-sourced by the Tencent HunYuan team, built upon TorchSpec. It supports six types of draft architectures, including MTP autoregre...

Read more
AngelSpec – An End-to-End Speculative Decoding Training Framework Open-Sourced by Tencent HunYuan Team cover image
3 months agoSpeech AIVideo AIModel Inference

MAI-Voice-2-Flash – Microsoft's High-Speed Text-to-Speech Model

MAI-Voice-2-Flash is a high-speed text-to-speech (TTS) model introduced by Microsoft's AI team for high-concurrency, low-latency scenarios. While maintaining natural tone and high audio quality, its i...

Read more
MAI-Voice-2-Flash – Microsoft's High-Speed Text-to-Speech Model cover image
3 months agoAI AgentAI CodingModel Inference

Nanbeige4.2-3B – A General-Purpose Agent Small Model from Nanbeige Lab

Nanbeige4.2-3B is a general-purpose agent small model from BOSS Zhipin’s Nanbeige Lab. With only 3B parameters, it surpasses larger models such as Qwen3.5-9B and Gemma4-12B on code agents, office work

Read more
Nanbeige4.2-3B – A General-Purpose Agent Small Model from Nanbeige Lab cover image
3 months agoAI AgentSpeech AIModel Inference

Step Edge – The Edge Model Suite from StepFusion

Step Edge is StepFusion's edge model suite, comprising four core components: Base, Audio, GUI, and Gen, designed for mobile phones and automotive terminals. Through an edge-cloud collaborative archite...

Read more
Step Edge – The Edge Model Suite from StepFusion cover image
3 months agoVideo AIModel InferenceEdge Deployment

ABot-World Studio – A General-Purpose World Model Workshop Launched by AutoNavi

ABot-World Studio is a general-purpose world model workshop launched by AutoNavi Maps. It innovatively unifies interactive video generation with 3DGS (3D Gaussian Splatting) scene generation within th...

Read more
ABot-World Studio – A General-Purpose World Model Workshop Launched by AutoNavi cover image
3 months agoVideo AIModel Inference

X2.0 – Xmax AI Launches the World's First Real-Time Interactive Video Generation Model

X2.0 is the world's first real-time interactive video generation model introduced by Xmax AI, supporting millisecond-level streaming generation. Users can replace character clothing in real time via a...

Read more
X2.0 – Xmax AI Launches the World's First Real-Time Interactive Video Generation Model cover image
Page 5 of 9 (84 articles total)

Subscribe to AI Model Reviews

Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.

We never share your email. Unsubscribe anytime.