✷ The archive · 11 labs · 58 dispatches

The labs

No more opening a dozen official blogs every morning. First-hand releases from OpenAI, Anthropic, DeepMind and the rest, each with its substance pulled out.

01

Ollama Introduces Transparent Per-Token Pricing for Pro, Max, and Team Plans

Ollama announced per-token pricing with monthly usage credits for its Pro, Max, and Team plans, simplifying cost prediction for open model access.

02

Claude Desktop integration with Ollama enables local and cloud model switching

Ollama now lets Claude Desktop act as a third‑party gateway, so users can run Claude alongside any local or cloud model in Ollama without sending data to Anthropic.

03

NVIDIA Nemotron 3.5 Lightning Release

NVIDIA Nemotron 3.5 Lightning is a 30B parameter open model with 3B active parameters per token, designed for local agentic workflows and multi-step tasks with a 1M token context window.

04

Muse Glimmer Release: Meta Superintelligence Labs' 30B Agentic Multimodal Model

Meta Superintelligence Labs has released Muse Glimmer, a 30B multimodal model optimized for local agent workloads with a 128K+ context length, now available via Ollama.

05

Ollama Funding and Open Model Platform Expansion

Ollama has raised $88M to expand its platform for running and scaling open AI models, serving 8.9 million developers and 85% of the Fortune 500.

06

Ollama 0.31: Faster Gemma 4 Performance via Multi-Token Prediction

Ollama 0.31 introduces multi-token prediction for Gemma 4 on Apple Silicon, increasing token generation speed by nearly 90% on coding-agent benchmarks without altering model output.

07

Ollama MLX Engine Update for Apple Silicon

Ollama has updated its MLX engine to improve performance on Apple Silicon through NVFP4 support, kernel fusion, and a new state snapshot system for agentic workflows.

08

Ollama 0.30 Release Adds GGUF Model Support and Up to 20% Faster NVIDIA Performance

Ollama 0.30 introduces GGUF model compatibility via llama.cpp and delivers up to 20% faster throughput on NVIDIA GPUs, expanding hardware support through default Vulkan acceleration.

09

NVIDIA Nemotron 3 Ultra Release

NVIDIA Nemotron 3 Ultra is a 550B parameter open model optimized for long-running agentic workflows, featuring a 1M token context window and NVFP4 quantization for high efficiency.

10

OpenJarvis 1.0 Release: Local-First Personal AI via Ollama

OpenJarvis 1.0 is an open-source framework for building local-first personal AI agents that integrates with Ollama to run models on personal hardware.

11

Ollama 0.19 Preview: MLX Integration for Apple Silicon Acceleration

Ollama 0.19 introduces a preview integration with Apple's MLX framework, significantly accelerating performance on Apple Silicon devices through unified memory optimization and NVFP4 support.

12

Ollama 0.17: Simplified Setup for OpenClaw AI Assistant

Ollama 0.17 introduces a single-command installation process for OpenClaw, a personal AI assistant capable of managing emails, calendars, and messaging apps on local hardware.

13

Ollama adds Subagents and Web Search to Claude Code

Ollama now supports subagents and web search within Claude Code, allowing models to run parallel tasks and access real-time information without requiring MCP servers or API keys.

14

OpenClaw personal AI coding assistant launch by Ollama

Ollama announced OpenClaw, a locally‑run personal AI assistant that connects WhatsApp, Telegram, Slack, Discord, iMessage and other messaging platforms to AI coding agents via a centralized gateway, enabling private, cross‑platform code assistance.

15

Ollama launch command release

Ollama has introduced the 'ollama launch' command in version 0.15+, allowing users to set up and run coding tools like Claude Code and OpenCode without manual environment variables or configuration files.

16

Ollama adds experimental image generation with Z-Image Turbo and FLUX.2 Klein

Ollama announced experimental macOS image generation using the 6B‑parameter Z‑Image Turbo model and Black Forest Labs’ FLUX.2 Klein models, marking the first native text‑to‑image capability in the Ollama ecosystem.

17

Ollama v0.14.0: Anthropic API Compatibility and Claude Code Support

Ollama v0.14.0 introduces compatibility with the Anthropic Messages API, enabling the use of Claude Code and other Anthropic SDK applications with local and cloud open-source models.

18

OpenAI Codex with Ollama Integration

Ollama now enables the OpenAI Codex CLI to use open-weight models, allowing for local code execution and modification using models like gpt-oss:20b and gpt-oss:120b.

19

OpenAI gpt-oss-safeguard models released via Ollama

OpenAI and Ollama released the open‑source gpt-oss-safeguard safety‑reasoning models (20B and 120B) under Apache 2.0, enabling organizations to run policy‑driven content classification with transparent reasoning.

20

MiniMax M2 Release on Ollama Cloud

MiniMax M2 is a high-performance model optimized for coding and agentic workflows, now available on Ollama's cloud platform.

21

NVIDIA DGX Spark Performance with Ollama

Ollama has released performance benchmarks for the NVIDIA DGX Spark, demonstrating throughput for various models including gpt-oss and gemma3 using firmware version 580.95.05.

22

Ollama Coding Models and Integrations Update

Ollama has introduced cloud access to GLM-4.6 and Qwen3-Coder-480B, alongside updates to Qwen3-Coder-30B and expanded integrations for VS Code, Zed, and Droid.

23

Qwen3-VL Release Notes

Ollama has released Qwen3-VL, a powerful vision language model featuring advanced spatial perception, expanded OCR support for 32 languages, and native 256K context for long-video understanding.

24

NVIDIA DGX Spark and Ollama Integration

Ollama has partnered with NVIDIA to optimize the NVIDIA DGX Spark, powered by the GB10 Grace Blackwell Superchip, for running local language models with 1 petaFLOP of performance and 128GB of memory.

25

Ollama Web Search and Web Fetch API Release

Ollama has released a new web search and web fetch API to reduce hallucinations and provide LLMs with real-time web data via REST and library integrations.

26

Ollama New Model Scheduling Update

Ollama has introduced a new model scheduling system that replaces memory estimation with exact memory measurement to reduce crashes and increase GPU utilization.

27

Ollama Cloud Models Preview

Ollama has introduced Cloud models in preview, enabling users to run large-scale models on datacenter-grade hardware while maintaining the same local toolset and API integration.

28

OpenAI gpt-oss Release on Ollama

Ollama has partnered with OpenAI to integrate the gpt-oss open weight models, offering 20B and 120B parameter versions optimized for local execution via the MXFP4 quantization format.

29

Ollama App Release for macOS and Windows

Ollama has released a new application for macOS and Windows that provides a graphical user interface for downloading and chatting with local AI models, including support for file uploads and multimodal capabilities.

30

Secure Minions protocol enables encrypted Ollama‑frontier model collaboration

Ollama and Stanford’s Hazy Research lab announced Secure Minions, an end‑to‑end encrypted protocol that lets local Ollama models work with frontier cloud models while keeping all data confidential.

31

Ollama Thinking Feature Release

Ollama has introduced the ability to enable or disable a model's thinking process, allowing users to separate internal reasoning from final output for models like DeepSeek R1 and Qwen 3.

32

Ollama adds streaming tool calling support

Ollama now supports streaming responses with tool calling, letting chat applications receive partial model output and invoke functions in real time.

33

Ollama Multimodal Engine Release

Ollama has introduced a new multimodal engine to improve the reliability and accuracy of local inference for vision models, supporting Llama 4, Gemma 3, Qwen 2.5 VL, and Mistral Small 3.1.

34

Ollama Minions: Hybrid Local and Cloud LLM Collaboration

Ollama introduces Minions, a framework developed by Stanford Hazy Research that reduces cloud LLM costs by delegating workloads to local models like Llama 3.2 while maintaining high performance.

35

Ollama Structured Outputs Release

Ollama now supports structured outputs, allowing users to constrain model responses to a specific format defined by a JSON schema for increased reliability and consistency.

36

Ollama Python Library 0.4 Release Notes

Ollama Python library 0.4 introduces the ability to pass Python functions directly as tools, automating JSON schema generation via Pydantic and docstring parsing.

37

Llama 3.2 Vision available in Ollama

Ollama has released support for Llama 3.2 Vision in 11B and 90B parameter sizes, enabling local execution of multimodal capabilities including OCR and image analysis.

38

IBM Granite 3.0 Models on Ollama

IBM Granite 3.0 models, including dense and Mixture of Experts (MoE) variants, are now available on Ollama under the Apache 2.0 license.

39

Llama 3.2 Support in Ollama

Ollama now supports Meta's Llama 3.2, introducing lightweight 1B and 3B text-only models for edge devices and upcoming 11B and 90B vision-capable models.

40

Bespoke-Minicheck: Reducing LLM Hallucinations via Grounded Factuality Checking

Ollama has integrated Bespoke-Minicheck, a grounded factuality checking model from Bespoke Labs that detects hallucinations by verifying claims against source documents.

41

Ollama Tool Support Release

Ollama has introduced tool calling support for models like Llama 3.1, allowing local LLMs to interact with external APIs, functions, and code interpreters.

42

Google Gemma 2 release on Ollama

Google Gemma 2, available in 2B, 9B, and 27B parameter variants, launches on Ollama with a new architecture that delivers class‑leading performance and efficiency, outperforming larger open models.

43

Ollama and Continue: Setting Up an Open-Source AI Code Assistant

Ollama and Continue enable developers to build a fully open-source, local AI coding assistant within VS Code and JetBrains using models like Codestral, Llama 3, and DeepSeek Coder.

44

Firebase Genkit with Ollama Support

Google has released Firebase Genkit, an open-source framework for building AI-powered apps, featuring native support for Ollama to run Google's Gemma model locally.

45

Llama 3 Refusal Rates and Censorship Comparison

Llama 3 exhibits significantly lower false refusal rates than Llama 2, reducing over-refusals on benign prompts while still providing technical assistance.

46

Llama 3 Availability on Ollama

Ollama has released support for Llama 3, providing access to the 8B and 70B parameter models with significant improvements in training data, context length, and token efficiency over Llama 2.

47

Ollama Embedding Models Support

Ollama now supports embedding models, enabling the creation of local retrieval augmented generation (RAG) applications by converting text into vector embeddings.

48

Ollama AMD Graphics Card Support Preview

Ollama has introduced preview support for AMD graphics cards on Windows and Linux, enabling hardware acceleration for all Ollama features across a wide range of Radeon, Radeon PRO, and Instinct series cards.

49

Ollama Windows Preview Release

Ollama has launched a preview version for Windows, enabling users to run, pull, and create large language models locally with native GPU acceleration and API access.

50

Ollama OpenAI Compatibility Update

Ollama has introduced built-in compatibility with the OpenAI Chat Completions API, allowing users to run local models using existing OpenAI-compatible tools and libraries.