Ollama

This release introduces the inclusion of tool call indices within parallel tool calls for enhanced tracking and functionality.

This patch release fixes a bug related to the correct parsing of tool calls for Qwen 3 and Qwen 3.5 models when they are emitted during the thinking process.

This release addresses a critical bug where the Windows application would crash on startup if an update was pending.

This release introduces support for the Nemotron architecture and includes several performance and stability improvements, particularly around MLX memory usage and logging. It also updates the mlx-c bindings.

This release introduces support for the nemotron architecture and includes several performance and logging improvements, particularly for MLX-based operations.

This release introduces support for the nemotron architecture and includes several performance and logging improvements, particularly for MLX-based operations. It also updates underlying MLX-C bindings.

This release introduces support for the nemotron architecture and includes several performance and logging improvements, particularly for MLX-based operations. It also updates underlying MLX-C bindings.

This release introduces automatic installation and configuration of OpenClaw via Ollama, enabling easier use with open models, and enables websearch functionality when using cloud models.

This release introduces UI exposure of the server context length and implements OpenClaw onboarding, alongside internal consolidation of the tokenizer.

This release introduces support for several new model architectures (Gemma 3, Llama 3, Qwen 3) in mlxrunner and adds the new `ollama launch` CLI command. Several minor bug fixes related to mlx model display and scheduling were also implemented.

This release introduces the ability to disable cloud models via a new setting or environment variable, and fixes rendering issues in PowerShell along with bugs affecting experimental image models.

This release introduces web search capabilities for Claude cloud models and adds an environment variable to easily disable cloud models for privacy. It also fixes rendering issues in PowerShell and restores functionality for experimental image generation models.

This release improves the installation experience on macOS and Windows and adds support for respecting the OLLAMA_LOAD_TIMEOUT variable for image generation models.

This release introduces significant UX improvements across the CLI and TUI, adds new features like external prompt editing and hidden login/logout aliases, and enhances model support with MLX integration and safetensors quantization.

This release introduces significant improvements to the command-line interface (CLI) and Text User Interface (TUI) experience, adds MLX runner support with safetensors quantization, and includes new login/logout aliases.

Ollama 0.16.0-rc2 introduces the powerful GLM-5 model and a new `ollama` command for simplified application launching. It also includes MLX runner improvements and a new keybinding for prompt editing.

This release improves the launch experience by automatically downloading missing models and fixes context handling bugs for droid and claude commands.

This release introduces two new models, GLM-OCR and Qwen3-Coder-Next, and enhances core functionality with sub-agent support and VRAM-aware context length defaulting.

This release introduces two new powerful models, GLM-OCR and Qwen3-Coder-Next, and significantly enhances `ollama launch` with argument passing and sub-agent support. It also implements VRAM-based dynamic context length setting.

This release introduces the GLM-OCR model and updates default context sizes based on VRAM availability. It also adds support for GLM-4.7-Flash on the MLX engine.

This release introduces the GLM-OCR model and adds support for GLM-4.7-Flash on the MLX engine, while also updating default context sizes based on VRAM.

This release introduces two new models, GLM-OCR and Qwen3-Coder-Next, and enhances core functionality with sub-agent support and VRAM-aware context length defaulting.

This release introduces two new models, GLM-OCR and Qwen3-Coder-Next, and enhances functionality with sub-agent support for `ollama launch` and VRAM-aware default context length settings.

This release introduces two new models, GLM-OCR and Qwen3-Coder-Next, and enhances functionality with sub-agent support for launch commands and VRAM-aware context length defaulting.

This release updates the behavior of the `ollama launch openclaw` command to ensure the OpenClaw onboarding flow is executed if necessary.

This release renames the 'clawdbot' launch command to 'openclaw' and updates how `ollama launch` utilizes the OLLAMA_HOST environment variable. Tool calling for Ministral models has also been improved.

This release introduces a new command for easily launching Clawdbot integrated with Ollama models.

This release includes documentation updates, notably regarding 'ollama launch', and a performance fix by adding -O3 optimization to CGO flags.

This release includes documentation updates, notably regarding 'ollama launch', and a performance fix by adding -O3 optimization to CGO flags.

This release introduces the `ollama config` command and adds image editing capabilities to x/imagegen. It also includes improvements to the CLI handling of model loading and output rendering.

This release introduces the `ollama config` command and adds image editing capabilities to x/imagegen. It also includes improvements to CLI handling during model loading.

This release focuses on internal cleanup of the manifest and model paths, and temporarily removes the qwen_image and qwen_image_edit models from x/imagegen.

This release focuses on internal cleanup, specifically refining the manifest and modelpath handling, and removing the qwen_image and qwen_image_edit models from x/imagegen.

This release introduces an enhancement for the macOS application, allowing it to terminate gracefully during system shutdown.

This release introduces several new powerful image generation and LLM models, including Z-Image Turbo and GLM-4.7-Flash. It also includes several bug fixes related to macOS shutdown, model management, and API usage.

This release introduces the GLM-4.7-Flash model and enables image generation via the /api/generate endpoint, alongside several stability and command fixes.

This release introduces an enhancement for the macOS application to handle system shutdown more gracefully. It primarily focuses on improving application termination behavior on macOS.

This release introduces the GLM-4.7-Flash model and enables image generation via the /api/generate endpoint, alongside several stability and command fixes.

This release focuses on documentation updates, including integrations for Onyx and Marimo, and introduces multi-line input support in the CLI.

This release focuses on documentation updates, including new integrations for Onyx and Marimo, and introduces multi-line input support in the CLI.

This patch release addresses a critical bug affecting macOS auto-updates by fixing signature verification failures. It also welcomes two new contributors.

This release introduces experimental support for image generation models and enhances API compatibility with Anthropic's message format. It also includes stability improvements for VRAM estimation and introduces the `REQUIRES` command for Modelfiles.

This release introduces experimental support for image generation models via MLX and enhances Anthropic API compatibility. It also adds model version requirements via the Modelfile and improves VRAM measurement accuracy.

This release introduces experimental support for image generation models, adds Anthropic API compatibility, and includes several stability improvements related to VRAM estimation and error handling.

This release introduces experimental support for image generation models via MLX, adds Anthropic API compatibility, and includes several stability improvements related to VRAM handling and error reporting.

This release introduces experimental support for image generation models, adds Anthropic API compatibility, and improves VRAM estimation accuracy. It also includes a new `REQUIRES` command for Modelfiles to specify Ollama version requirements.

This release introduces experimental support for image generation models, adds Anthropic API compatibility, and includes several stability improvements related to VRAM estimation and error handling.

This release introduces experimental support for image generation models via MLX and enhances Anthropic API compatibility. It also adds the `REQUIRES` command to Modelfiles for version declaration and improves VRAM estimation accuracy.

This release introduces experimental support for image generation models, adds Anthropic API compatibility, and includes several stability improvements related to VRAM estimation and error handling.

This release introduces support for Google's FunctionGemma model and migrates BERT architecture models to the Ollama engine. It also improves tool parsing for DeepSeek-V3.1 and fixes bugs related to nested tool properties.

This release introduces support for Nemotron 3 Nano and Olmo 3 models, enables Flash Attention by default, and provides critical fixes for Gemma 3 model architectures.

This release introduces support for Devstral-Small-2, rnj-1, and nomic-embed-text-v2 models, while improving embedding truncation logic and fixing image input issues for qwen2.5vl.

This release introduces support for the Qwen3-Next model series and enables Flash Attention by default for vision models. It also includes critical fixes for multi-GPU CUDA detection and DeepSeek-v3.1 thinking behavior.

This release introduces support for Ministral-3 and Mistral-Large-3 models, adds tool calling for cogito-v2.1, and includes several fixes for CUDA detection and error reporting.

This release introduces support for DeepSeek-OCR, Cogito-V2.1, and DeepSeek-V3.1 architecture, alongside a new performance benchmarking tool and significant engine optimizations for KV caching and GPU detection.

Ollama 0.12.11 introduces logprobs support for API responses and adds opt-in Vulkan acceleration for expanded GPU compatibility.

This release enables embedding model support via the CLI, adds tool call IDs to the chat API, and improves Vulkan performance and hardware detection.

This release addresses a performance regression specifically impacting users running Ollama on CPU-only hardware.

This release focuses on performance optimizations for qwen3-vl, including default Flash Attention support, and fixes several issues related to model thinking modes and image processing.

This release introduces support for Qwen3-VL and MiniMax-M2 models, adds file attachments and thinking level adjustments to the app, and provides updated API documentation alongside several embedding and backend bug fixes.

This release introduces search support for tool-calling models, enables Flash Attention for Gemma 3, and adds experimental Vulkan support for broader GPU compatibility alongside several model-specific bug fixes.

This release introduces structured output support for thinking models and improves app startup behavior, while removing support for older macOS versions and specific AMD GPU architectures.

This release enables Flash Attention by default for Qwen 3 models and improves VRAM detection, while dropping support for older macOS versions and specific AMD GPU architectures.

This release adds support for DeepSeek-V3.1-Terminus and Kimi-K2-Instruct-0905 models while fixing critical bugs related to tool call parsing, Unicode rendering, and model loading crashes.

This release introduces a new Web Search API for real-time information retrieval and expands the new engine's capabilities to support Qwen3 architectures and multi-regex pretokenizers.

This release adds support for Qwen3 Embedding and tool calling for Qwen3-Coder, alongside several bug fixes for Gemma3 models, Linux sign-in, and function calling parsing.

This release introduces cloud models in preview, expanding hardware support for larger models, and adds native support for Bert and Qwen 3 architectures within Ollama's engine.

This release adds CUDA 13 support, introduces a dimensions field for embeddings, and improves memory estimation and app UI. It also removes support for loading split vision models in the Ollama engine.

This release introduces support for the EmbeddingGemma model, providing a high-performance open embedding model for Ollama users.

This release focuses on performance optimizations through CPU/GPU overlapping and stability fixes for AMD GPUs and Unix-based installations.

This release enables flash attention by default for gpt-oss models and improves their overall loading performance.

This release introduces the DeepSeek-V3.1 model and the preview of Turbo mode for running large models. Several bugs related to model loading, thinking tags, and tool call parsing have also been resolved.

This release focuses on UI improvements for the Ollama app, including faster chat switching and better layouts, alongside performance optimizations for flash attention and BPE encoding.

This release introduces significant memory management improvements for GPU scheduling and multi-GPU setups, alongside performance optimizations for gpt-oss models and reduced installation sizes.

This release improves OpenAI API compatibility by supporting simultaneous content and tool calls, ensuring tool name propagation, and consistently providing reasoning in responses.

This release fixes a VRAM leak in gpt-oss during multi-device execution and improves Windows stability by statically linking C++ libraries.

This patch release focuses on stability improvements for gpt-oss, specifically fixing crashes related to KV cache quantization and a missing variable definition.

Ollama v0.11 introduces support for OpenAI's gpt-oss models (20B and 120B) featuring native MXFP4 quantization, agentic capabilities, and configurable reasoning effort.

This patch release focuses on bug fixes for international character input and log output accuracy.

Ollama v0.10.0 introduces a new desktop app, significant performance optimizations for gemma3n and multi-GPU setups, and critical fixes for tool calling and API image support.

This release introduces the ability to specify tool names in chat messages and includes a UI fix for the launch screen.

Ollama 0.9.5 introduces a native macOS app with faster startup, network exposure capabilities, and customizable model storage directories. It also raises the minimum macOS requirement to version 12.

This release introduces network exposure and custom model directories, while significantly optimizing the macOS application as a native app with a smaller footprint. It also includes fixes for tool calling and Gemma 3n model quantization.

This release adds support for the multilingual Gemma 3n model family and introduces automatic context length limiting to improve model stability.

This patch release focuses on bug fixes for tool calling, generation errors, and tokenization issues across specific model architectures.

This release introduces tool calling for DeepSeek-R1 and Magistral, alongside a major preview of native macOS and Windows applications featuring network exposure and custom model directories.

Ollama v0.9.0 introduces 'thinking' support, allowing models like DeepSeek R1 and Qwen 3 to separate reasoning from output via a new API field and CLI toggles.

Ollama v0.8.0 introduces streaming support for tool calls and improves engine logging with more detailed memory estimation data.

This release introduces support for Qwen 3 and Qwen 2 architectures while providing critical stability fixes for multimodal models and memory management.

Ollama v0.7.0 introduces a new multimodal engine supporting vision models like Llama 4 and Gemma 3, along with WebP support and various performance improvements and bug fixes.

This release focuses on performance optimizations for Qwen 3 MoE models and critical stability fixes, including memory leak resolutions and improved OOM handling.

Ollama v0.6.7 introduces support for Llama 4, Qwen 3, and Phi 4 reasoning models while increasing the default context window and fixing several inference and path-handling bugs.

This release adds support for IBM Granite 3.3 and DeepCoder models, introduces an experimental high-performance downloader, and fixes critical memory leaks for Gemma 3 and Mistral Small 3.1.

This release introduces support for the Mistral Small 3.1 vision model and optimizes loading performance for Gemma 3 on network-backed filesystems.

Ollama v0.6.4 focuses on stability improvements for Gemma 3 and DeepSeek models, adds vision capability metadata to the API, and introduces AMD RDNA4 support for Linux users.

This release introduces performance optimizations and improved loading for Gemma 3, alongside critical bug fixes for model execution errors and enhancements to the CLI tools.

This release introduces multi-image support and memory optimizations for Gemma 3, adds support for AMD Strix Halo GPUs, and fixes issues with model quantization and saving.

This release introduces support for the Command A 111B model, improves memory management for gemma3, and adds new CLI features including verbose model information and navigation hotkeys.

This release introduces support for Google's Gemma 3 model family across various sizes and resolves execution errors for Snowflake Arctic embedding models.