World Wire

UC Berkeley’s Sky Computing Lab built LEANN , an open-source vector index that stores almost no embeddings. The LEANN vector index recomputes embeddings at query time instead of saving them to disk. The repo benchmark shows a 60 million chunk Wikipedia index dropping from 201 GB to 6 GB. The research paper won the Best Research Paper award at MLSys 2026 . So, it brings semantic search and RAG over personal data, on a laptop. TL;DR Size: 6 GB for 60M chunks ( repo ); 4 GB in the paper’s 76 GB Wikipedia setup. Default embedder: Contriever (110M params). It is an index, not an LLM, so no context length applies. Runs on: laptops and workstations. The paper tested an RTX 4090 box with 32 GB RAM and an M1 Ultra Mac. A CPU-only Linux install exists, with no published CPU latency. Performance: matches HNSW downstream accuracy at 90% recall, using under 5% of raw-data storage. Best: 25.5% NQ accuracy, identical to HNSW, using 4 GB instead of 188 GB. ...

Mirendil has released Fern , its first AI model. Mirendil Fern is a from-scratch coding model with a context window of up to 10M tokens. Mirendil explains how that equals about 23 MB of code, or roughly half a million lines. That is a codebase on the scale of Megatron-LM, held in context at once. Fern 0.1 is the first version, built from Mirendil-Base after a short round of post-training. For developers, its like, you load a whole repo, a full training log or days of agent traces at once. TL;DR Size: 0.1 to 0.5T parameters (exact count and active params not disclosed); context up to 10M tokens. Runs on: Hosted early access only; no open weights or quantized builds announced. Performance: Strong long-context retrieval, mid-pack agentic coding versus open-weight models, well behind frontier models. Best: 100% on RULER single-needle retrieval at every length from 32K to 10M tokens (base model). Worst: 6.1% on Terminal Bench 4.0, versus 66.4% for Claude Opus ...

Baidu has released Unlimited OCR 2 , an open-source OCR model built for very long documents. The 3B model parses books, filings and reports of hundreds of pages in one request. Its core change is SR-SWA, a sparse attention scheme that keeps per-step decoding cost nearly flat. Weights ship under the MIT license , with code on GitHub . TL;DR Size: 3.34B parameters . Active parameters not disclosed. Max position length 131,072 tokens. Runs on: 1 CUDA GPU in BF16. Baidu tested on an NVIDIA A800-80GB. BF16 weights total about 6.7 GB. Performance: first place on both multi-page benchmarks Baidu tested, against 9 other models (self-reported). Best: 77.1 overall on MarathonDocBench (hundreds of pages). The next model, Kimi-K3, scores 33.7. Worst: 48.2 on heading hierarchy (TEDS) on MarathonDocBench, its lowest sub-score. What is Unlimited OCR 2? Unlimited OCR 2 is a 3B vision-language model from Baidu that turns ordered page images into structured text. ...

OpenAI has released GPT-6.1 Terra , a fast model for visual reasoning, computer use and writing. It replaces GPT-5.6 Terra and is live in the API as gpt-6.1-terra . Standard pricing is $1 per million input tokens and $5 per million output tokens . For teams automating screens, forms and documents at volume, GPT-6.1 Terra changes the cost math. TL;DR Size: 1.05M-token context, 128K max output. Runs on: OpenAI-hosted only (API, ChatGPT Work, Codex). Closed weights. Performance: Near GPT-6.1 Sol and GPT-6 Astra on vision and computer use, at lower cost. Best: 85.5% on MMMU-Pro (Vision) at max effort, 1.2 points behind GPT-6 Astra. Worst: 50.3% on Terminal-Bench 4.0, behind GPT-6.1 Sol (55.9%) and Claude Sonnet 5.5 (70.6%). What is GPT-6.1 Terra? GPT-6.1 Terra is an OpenAI reasoning model built for high-volume visual and computer-use work. It accepts text and image input and returns text . The context window is 1,050,000 tokens, with up to 128,000 ou...