12 free resources on this topic. Everything here is free and hand-picked. You can also search within this topic.
A KDnuggets article by Shittu Olumide describing seven open models under 10 billion parameters, each built for one task such as transcription, OCR, routing or speech, and comparing them with much larger general-purpose models. Performance claims come from the models' publishers and cited benchmarks.
An explainx.ai roundup of 20 projects people reported building with Claude Fable 5.2 after its November 9, 2026 release, drawing on Matt Shumer, Anthropic's launch post and Ethan Mollick, with each item labeled verified, live or claim. Claude Fable 5.2 is a paid model; the article is free to read.
Baseten's blog post introducing its Mammoth-1 and Elephant-1 decision models, which it positions against generative LLMs on structured decision tasks; the rankings are the company's own claims.
NVIDIA's organization page on Hugging Face, hosting publicly listed AI models, datasets, and related resources, including the Nemotron dataset family. Individual assets carry their own license terms.
A repository to explore machine learning models.
Explains that Google Antigravity now lists Claude Opus 5.5 and Sonnet 5.5 for non-trial Google AI Pro and Ultra subscribers, and that Claude 4.6 and GPT-OSS-120b are removed on November 2, with who is affected and what to do.
Sakana AI's release post for its Fugu models, explaining how it orchestrates models along the quality-versus-cost "Pareto frontier".
Why I recommend it: A lab's own announcement of its own models — the performance claims are self-reported and not independently verified.
Open-source "System 1" decision engine: typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Why I recommend it: Free and open source, but an individual developer's project — check the commit history and issue activity before relying on it for anything important.
A Jev-like family of small decision models built on Qwen that you can train and run on your own hardware, from Jared Palmer.
Why I recommend it: Free and open source. Running it yourself means paying for your own compute; the models are small enough for a laptop or a cheap server.
An arXiv paper showing how message-passing techniques let language models reason more efficiently, with the full text free to read and download.
Why I recommend it: A preprint — not yet peer-reviewed, so treat the results as preliminary until the work is replicated or published.
Personal site of Ian Duncan, a software engineer and entrepreneur writing about engineering, AI and life. Essays range from a beginner-friendly guide to AI models to critical takes on AI culture and the apocalypse narrative.
From the site: I
Independent benchmarking of the major AI models on speed, price and quality, with the numbers side by side. Free to read.
From the site: Comparison and analysis of AI models and API hosting providers. Independent benchmarks across key performance metrics including quality, price, output speed & latency.
Why I recommend it: Where I check what a model actually costs per million words before believing a "cheap" claim.
