What Is vLLM? The Open Source AI Model Server, Explained
vLLM is free, open source software that serves open AI models to many users at once. What PagedAttention does, how it differs from Ollama, and who should use it.

News on open-weight AI models whose weights can be downloaded and run. Recent releases covered here include Nvidia's Nemotron 3.5 Super VL, DeepSeek V4.1-Flash, Z.ai's GLM-5.3 and Tencent's Hy4-Preview, along with their license terms.
vLLM is free, open source software that serves open AI models to many users at once. What PagedAttention does, how it differs from Ollama, and who should use it.

LongCat is Meituan's AI model family: 560B Flash models, 1.6T LongCat-2.x, plus image, video and speech models, mostly open weights under MIT.

What AI parameters are, how weights and biases are learned, what 7B means, why bigger is not always better, and how size affects running models at home.

Free apps can run open AI models on your iPhone or Android phone with no internet. How to set up AI Edge Gallery or PocketPal AI and pick a model.

Phi is Microsoft's family of small open AI models built to run on your own device. Here is each Phi-4 model, its MIT license, and how to run it locally.

Downloadable weights help, but the OSI definition of open source AI also asks for data information and training code. Say open weights, and check the license.

StepFun is a Shanghai AI lab behind the Step models. Here is what Step 5 Preview and the Apache 2.0 Flash models are, and what the StepFun license says.

gpt-oss is OpenAI's pair of downloadable open-weight models, gpt-oss-120b and gpt-oss-20b. Here are the specs, license, safety notes and how to run them.

Continuous Intelligence released ci-proto on 12 November 2026, a 167M open-weight time-series model. The lab and a public board differ on its fev-bench rank.

MiniCPM is OpenBMB's family of open-weight models for phones and PCs, from MiniCPM5 and MiniCPM-V 4.7 to MiniCPM-OCR 1.0. Sizes, licenses, and how they differ.

MBZUAI's IFM released PAN 2, an open world model that turns a starting scene and an action in words into a video of what happens next. Apache 2.0.

NVIDIA's 2B-class Alpamayo 2 Edge drives at 160 to 190 ms on DRIVE AGX Thor, and GR00T 2 Turbo runs at 124 ms on a humanoid's Jetson Thor.

Runway released Praxis-1, a 27B world action model that turns its video pretraining into robot arm control, with open weights under Apache 2.0.

MiniMax released open weights for H3-Image, a 16-megapixel text-to-image and editing model. Its license excludes the EU, UK, South Korea and US.

Baidu opened ERNIE 5.5 Flash Preview on Qianfan: 280B parameters, 14B active, 1M-token context. Apache 2.0 weights are due by Nov 25.

Zyphra's ZONOS3-Mini is a small open voice-cloning model that runs in a browser. What you can control, how fast Zyphra says it is, and what it costs.

Olmo is Ai2's family of fully open AI models: weights, training data, code and checkpoints are public. Here are the models, the licenses, and who should use it.

Tencent Hy, formerly Hunyuan, is Tencent's AI model family. Here is how Hy3 and Hy4 fit together, what you can download, and where Hy runs.

llama.cpp is a free, open source program that runs AI language models on your own computer. Learn what it does, GGUF files, quantization, and how to try it.

iFLYTEK, a Chinese speech AI firm founded in 1999, makes the Spark (Xinghuo) models, including small open-weight X2.6 and X2.5 models under Apache 2.0.
