wowsuch ai
Weekly brief2026-W39 UTC
Xiaomi MiMo released MiMo-V2.6-Flash-MOPD, a multimodal sparse MoE model with a 1M-token context length and an upgrade aimed at mitigating repeated tool calls. [1] NaiveAI introduced Naive-N0.5-Flash, an open-weight 309B mixture-of-experts model with a native 1M-token context window, designed for coding and AI R&D. [2] Several releases target typed decisions, including JevK5 v0.3, GLiNER2.5-multi-Decide, Open-Jev-27B-v1.1 and deepopen; they return or score choices, labels or probabilities rather than relying on free-form generation. [6] [8] [14] [15]
Ollaya offers local serving for decision models through a CLI, daemon, API and desktop app, while Rizzo Flow provides local typed decisions with probabilities through an API, CLI and browser playground. [17] [20] Cohere introduced Compass Cloud, a managed private-beta enterprise search and retrieval service available through APIs, an MCP server and a Python SDK. [18] JevHarness helps create task-specific Jev harnesses, and Unreal Agent coordinates LLM turns, tools, persisted session history and asynchronous operations. [19] [22]
Runway brought its tools into DaVinci Resolve through a plugin available on paid plans. [23] Astra-Ares is an experimental CLI tool that adapts reasoning effort for selected GPT-6 models during Codex tasks; ZCode offers an AI coding workspace across desktop, browser and terminal-agent interfaces. [24] [25]
Each numbered link above points to one of these catalog records, with its sources.
MiMo-V2.6-Flash-MOPD is a multimodal sparse MoE model with 309B total parameters and 15B activated parameters. It has a 1M-token context length and is an MOPD upgrade of the MiMo-V2.6-Flash-RL checkpoint that mitigates repeated tool calls.
Sources: Hugging Face
Naive-N0.5-Flash is an open-weight 309B mixture-of-experts model with 15.5B active parameters, designed for coding and AI R&D. It has a native 1M-token context window and uses hybrid Sliding-Window Attention and DeepSeek Sparse Attention.
Sources: Hugging Face
This preview checkpoint is a tile-score predictor for MiniMax-H3 text-to-audio-video generation at eight denoising steps. It selects attention tiles for block-sparse attention at a 10% keep ratio, with twelve geometry plans packed into the weights file.
Sources: Hugging Face
Nanosaur2-670M is a 670-million-parameter diffusion transformer for text-to-image illustration generation. It is released with ComfyUI support and model files for local inference.
Sources: Hugging Face
Agate Preview 001 is a 260-million-parameter text-to-image model that generates 256 × 256 images from English prompts. Its weights are available under the MIT licence, and the release is identified as a research preview.
Sources: Hugging Face
JevK5 v0.3 is an open-weight model based on Qwen3.5-4B, fine-tuned for typed decisions. It returns probabilities for options in one forward pass without generating tokens.
Sources: Hugging Face
Swift 1.5 Qwen3.8-Flash-Next is UkisAI’s reasoning-efficient derivative of Qwen3.8-Flash-Next, released as a BF16 checkpoint with quantized variants. UkisAI reports 63.4% fewer median thinking tokens and 1.8× speedup at xhigh, with less than 1% accuracy loss compared with the base model.
Sources: Hugging Face
GLiNER2.5-multi-Decide is a 287M-parameter multilingual classification model in the GLiNER2.5 family. It accepts caller-provided labels and can score multiple classification heads in one forward pass.
Sources: Hugging Face
LFM2.5-VL-DSpark is an experimental vision-language draft model for speculative decoding with LFM2.5-VL-3B. Liquid AI reports decoding throughput improvements of up to 2.66× on GPUs and 3.13× on edge devices, with output quality unchanged.
Sources: Liquid AI, Hugging Face
Bespoke-Nimble-9B is a Qwen3.5-9B LoRA adapter for context-grounded choices, booleans, and rubric score levels. It scores allowed answer tokens directly rather than generating reasoning or free-form answers.
Sources: Bespoke Labs
Meridian is a geometry-guided video model released as two LoRA adapters for the MiniMax-H3 transformer. It generates new camera viewpoints of existing video, and can also create camera movement from a single image.
Sources: Viggle
Qwen-Image-2.1-viggle-turbo v0.2.1 is a LoRA adapter distilled from Qwen-Image-2.1 for text-to-image generation and instruction-driven image editing. It supports editing with one to three reference images and is sampled in six transformer passes without classifier-free guidance.
Sources: Viggle
Laya Multilingual Core ML ANE is a downloadable FP16 checkpoint for short decisions, listed with CPU and Neural Engine support. The bundle has a B1/L96 capacity and a 96-token total limit.
Sources: GitHub new repositories
Open-Jev-27B-v1.1 produces typed probabilities for decisions from a supplied context, questions, and candidates, without autoregressive answer generation or generated-JSON parsing. Its released package contains LoRA adapters, a trained scalar decision head, and a saved calibration temperature; it requires pinned upstream Qwen weights and the Open-Jev loader.
Sources: GitHub new repositories
deepopen is an open-weight, non-autoregressive model for typed decisions, based on ModernBERT-large with 421 million parameters. It supports a 512-token context and is intended for English-language tasks.
Sources: GitHub new repositories
AgentJev-0.6B is a coding-completion checkpoint that returns a probability distribution about whether an implementation meets stated requirements. It uses a Qwen3-0.6B base and was trained with supervised training and RLCD on executed coding pairs.
Sources: Hugging Face, GitHub new repositories
Ollaya is an open-source local serving platform for decision models, with a CLI, daemon, API, and desktop app. It pulls models by name and returns calibrated decisions from typed questions without generating text.
Sources: GitHub new repositories
Compass Cloud is Cohere’s managed private-beta offering for enterprise search and retrieval. It provides a configurable retrieval service through APIs, an MCP server, and a Python SDK, while Cohere manages the pipeline and model inference.
Sources: Cohere
JevHarness is a Python project and agent skill for creating task-specific Jev harnesses with an authoring LLM. It can optionally use rewards and complete execution traces to improve a harness, then freeze the selected strategy so runtime decisions use the harness code and Jev calls without an authoring LLM on every decision.
Sources: GitHub new repositories
Rizzo Flow is an open-source, local-first tool that turns unstructured state into typed decisions with probabilities using open-weight models. It provides a local API, command-line interface, and browser playground, and generates no output tokens for its decisions.
Sources: GitHub new repositories
Laya-CoreML is an independent Python and CLI package for running Laya typed-decision models with Apple Core ML. It supports local inference on Apple Silicon and can use downloadable model bundles, including Neural Engine variants.
Sources: GitHub new repositories
Unreal Agent is an async-first agent harness with a Go library and executables. It coordinates LLM turns, tools, persisted session history, and asynchronous operations.
Sources: GitHub new repositories
The Runway DaVinci Resolve Plugin brings Runway tools into DaVinci Resolve. It is available on paid plans.
Sources: Runway
Astra-Ares is an experimental CLI tool that adapts reasoning effort for selected GPT-6 models during Codex tasks, using Jev to choose effort and how many generations it lasts. It is distributed as source and runs a separate, patched version of Codex CLI.
Sources: GitHub new repositories
ZCode is an AI coding workspace with desktop, browser, and terminal-agent interfaces. Its public repository contains the client, backend, shared UI, and Agent CLI and runtime source.
Sources: GitHub new repositories
Written by openai/gpt-6-luna from the catalog records listed here; every sentence cites the records it rests on. Which records a brief covers is decided by fixed rules: the new developments and major releases of the window with the strongest evidence.
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.