Self-Hosted AI

AutoTrust’s decision models return choices, yes/no probabilities, and ratings for the questions you supply

pplx-decider-flash is a 4B decision model from Perplexity, built on Qwen3.5-4B

MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows

Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

Turn text, structured data, and images into scored choices, yes/no answers, and ratings.

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

a single end-to-end model that understands text, images, video and audio, and answers in text and speech

LFM3-Audio-2B is a compact, fully featured audio model.

LFM3-VL-2B is a vision-language model for on-device visual understanding.

LFM3-1.7B is a tri-hybrid model for local agents and specialized applications.

d1 is a 3B decision model from Liquid AI, built on LFM2.5-VL-3B

d1-omni is a multimodal 600M decision model from Liquid AI

Phonon is Gradium’s text-to-speech family. It turns written text into spoken audio as it generates, making it useful for reading assistant replies, narrating passages, and adding a voice to local apps.

Nemotron 3.5 Bolt is NVIDIA’s compact vision-language model for local coding, reasoning, and tool use.

Flint is a 39.8 billion-parameter mixture-of-experts model from Recursive, built for coding agents.

Chirp Chirp! 🐦 We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement.

The most powerful vision-language model in the Qwen model family to date.

An open 30B MoE model from NVIDIA with 3B activated parameters that delivers strong reasoning and agentic capabilities.

NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B

Kev scores answers to structured questions about a supplied text state in a single forward pass.

Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

NVIDIA Nemotron 3.5 Lightning is an open 30B mixture-of-experts (MoE) model with 3B active parameters built for always-on agents.

Bonsai 2 from Prism ML is a family of vision models built for ternary weights – smaller models with close to full-precision quality.

Nemotron 3.5 Super is NVIDIA’s vision-language model for coding, reasoning, tool use, and document understanding

LFM2.5-8B-A1B, an edge model built for fast, reliable tool calling on consumer hardware.

Gemma 3n models are designed for efficient execution on everyday devices such as laptops, tablets or phones.

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

A 4B decision model from Together AI for fast classification.

A 9B decision model from Bespoke Labs for fast, typed classification.