Ollama v0.40.13 — Release Notes & Engineering Impact
Version 0.40.13 expands support for Liquid AI’s LFM3 models—including text‑to‑speech variants lfm3‑audio and lfm3‑omni—to Linux and Windows, enabling cross‑platform usage beyond Apple silicon.
ollama release archive — Page 1
93 tracked entries. Older history is imported progressively; see source coverage.
Ollama v0.40.12 — Release Notes & Engineering Impact
v0.40.12 adds the LFM3 family of small multimodal models and d1 2B decision models, expanding local AI capabilities on Apple silicon. It also delivers performance improvements and bug fixes without introducing breaking changes.
Ollama v0.40.11 — Release Notes & Engineering Impact
Ollama v0.40.11 adds speech generation on macOS via the `ollama run` command and an OpenAI-compatible `/v1/audio/speech` endpoint, plus introduces d3 decision models for classification, yes/no answers, and probabilistic scoring. These features expand Ollama's multimodal capabilities and structured reasoning without introducing breaking changes.
Ollama v0.40.10 — Release Notes & Engineering Impact
Ollama version v0.40.10 introduces support for NVIDIA's Nemotron 3.5 Bolt E4B vision-language model. Developers can now run this 128K-token context model locally with speculative decoding support.
Ollama v0.40.9 — Release Notes & Engineering Impact
Ollama v0.40.9 brings Flint support to Linux and Windows platforms while improving error handling for streaming OpenAI and Anthropic API endpoints. Additionally, it resolves context length propagation bugs in `ollama launch` and refines thinking configuration logic for web search follow-up requests.
Ollama v0.40.8 — Release Notes & Engineering Impact
Ollama v0.40.8. Source highlight: Flint brings Recursive's coding model to Ollama. It is designed for the work coding agents do across a repository: understanding unfamiliar code, tracing bugs, implementing features, and adding tests. Reasoning, multi-turn tool use, and a 262K-token context window support longer tasks across files a
Ollama v0.40.7 — Release Notes & Engineering Impact
Ollama v0.40.7. Source highlight: pplx-decider is a 27B decision model from Perplexity, fine-tuned from
Ollama v0.40.6 — Release Notes & Engineering Impact
Ollama v0.40.6. Source highlight: win: prevent orphaned runners
Ollama v0.40.5 — Release Notes & Engineering Impact
Ollama v0.40.5. Source highlight: NVIDIA Nemotron 3.5 Super
Ollama v0.40.4 — Release Notes & Engineering Impact
Ollama v0.40.4. Source highlight: Decision models in the CLI
Ollama v0.40.3 — Release Notes & Engineering Impact
Ollama v0.40.3. Source highlight: `ollama launch claude` no longer shows a warning about Claude connectors
Ollama v0.40.2 — Release Notes & Engineering Impact
Ollama v0.40.2. Source highlight: Models downloaded with earlier versions of Ollama are upgraded in the background the first time you run them, for better performance and compatibility when running on llama.cpp.
Ollama v0.40.1 — Release Notes & Engineering Impact
Ollama v0.40.1. Source highlight: server: proxy cloud usage and balance APIs
Ollama v0.35.1 — Release Notes & Engineering Impact
Ollama v0.35.1. Source highlight: Clef decision models
Ollama v0.35.0 — Release Notes & Engineering Impact
Ollama v0.35.0. Source highlight: Ollama now supports decision models through `/v1/systemone`, based on TypeSafe’s Jev API.
Ollama v0.40.0 — Release Notes & Engineering Impact
Ollama v0.40.0. Source highlight: **Models run on MLX on Apple Silicon by default**
Ollama v0.34.4 — Release Notes & Engineering Impact
Ollama v0.34.4. Source highlight: Structured outputs on thinking models now apply in a single pass, making them faster and more reliable.
Ollama v0.34.3 — Release Notes & Engineering Impact
Ollama v0.34.3. Source highlight: `GET /api/show` now advertises each model's thinking controls and default:
Ollama v0.34.2 — Release Notes & Engineering Impact
Ollama v0.34.2. Source highlight: Added first-run setup when running `ollama`, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows.
Ollama v0.34.1 — Release Notes & Engineering Impact
Ollama v0.34.1. Source highlight: MLX safetensors `ollama create` no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization.
Ollama v0.34.0 — Release Notes & Engineering Impact
Ollama v0.34.0. Source highlight: Use Ollama models in ChatGPT Desktop
Ollama v0.33.3 — Release Notes & Engineering Impact
Ollama v0.33.3. Source highlight: gemma4 now supports images and audio on MLX engine
Ollama v0.33.2 — Release Notes & Engineering Impact
Ollama v0.33.2. Source highlight: Ollama's app now follows the system appearance again, restoring dark mode support
Ollama v0.33.1 — Release Notes & Engineering Impact
Ollama v0.33.1. Source highlight: MLX: Qwen3.8 Flash Next support
Ollama v0.33.0 — Release Notes & Engineering Impact
Ollama v0.33.0. Source highlight: Developers can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.
Ollama v0.32.15 — Release Notes & Engineering Impact
Ollama v0.32.15. Source highlight: New desktop onboarding flow on first launch
Ollama v0.32.14 — Release Notes & Engineering Impact
Ollama v0.32.14. Source highlight: llm: transcode WebP images for llama-server
Ollama v0.32.13 — Release Notes & Engineering Impact
Ollama v0.32.13. Source highlight: qwen3.8: support developer instructions
Ollama v0.32.12 — Release Notes & Engineering Impact
Ollama v0.32.12. Source highlight: <img width="600" alt="ollama and qwen capybara" src="https://github.com/user-attachments/assets/5fa5e93b-d48b-4a6a-b72a-25379ab9429c" />
Ollama v0.32.11 — Release Notes & Engineering Impact
Ollama v0.32.11. Source highlight: `ollama launch dsh` now supports DeepSeek Harness, DeepSeek's open-source agent harness
Ollama v0.32.9 — Release Notes & Engineering Impact
Ollama v0.32.9. Source highlight: NVIDIA Nemotron 3.5 Lightning
Ollama v0.32.8 — Release Notes & Engineering Impact
Ollama v0.32.8. Source highlight: Muse Glimmer is now available on all platforms. Muse Glimmer can power coding agent applications such as Claude Code, Codex, Pi and more, as well as long-running personal assistants such as OpenClaw and Hermes.
Ollama v0.32.7 — Release Notes & Engineering Impact
Ollama v0.32.7. Source highlight: Note: Muse Glimmer is currently available via initial support via Ollama's MLX engine on Apple Silicon. Additional support and optimizations for Apple Silicon, NVIDIA, AMD, and other platforms will be available in the coming days.
Ollama v0.32.6 — Release Notes & Engineering Impact
Ollama v0.32.6. Source highlight: Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically
Ollama v0.32.5 — Release Notes & Engineering Impact
Ollama v0.32.5. Source highlight: Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.
Ollama v0.32.4 — Release Notes & Engineering Impact
Ollama v0.32.4. Source highlight: Support Laguna on Apple GPUs via the MLX engine
Ollama v0.32.3 — Release Notes & Engineering Impact
Ollama v0.32.3. Source highlight: Fixed model downloads that stall before sending data.
Ollama v0.32.1 — Release Notes & Engineering Impact
Ollama v0.32.1. Source highlight: Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations
Ollama v0.32.0 — Release Notes & Engineering Impact
Ollama v0.32.0. Source highlight: New interactive agent experience: running `ollama` now launches an agent to help you code and delegate work
Ollama v0.31.2 — Release Notes & Engineering Impact
Ollama v0.31.2. Source highlight: Enabled flash attention on older NVIDIA GPUs (compute capability 6.x)
Ollama v0.31.1 — Release Notes & Engineering Impact
Ollama v0.31.1. Source highlight: Faster Gemma 4 on Apple Silicon
Ollama v0.30.11 — Release Notes & Engineering Impact
Ollama v0.30.11. Source highlight: launch: add thinking capability detection to opencode
Ollama v0.30.10 — Release Notes & Engineering Impact
Ollama v0.30.10. Source highlight: Command A and North family models now run on Apple Silicon with the MLX engine
Ollama v0.30.9 — Release Notes & Engineering Impact
Ollama v0.30.9. Source highlight: Support for Cohere2Moe architecture
Ollama v0.30.8 — Release Notes & Engineering Impact
Ollama v0.30.8. Source highlight: Fixed `ollama launch` selecting the wrong provider in some cases
Ollama v0.30.7 — Release Notes & Engineering Impact
Ollama v0.30.7. Source highlight: Ollama Launch now supports Hermes Desktop, a native desktop interface for the Hermes agent. Run it alongside your Hermes agent to get a visual interface for managing conversations, integrations, and messaging apps.
Ollama v0.30.6 — Release Notes & Engineering Impact
Ollama v0.30.6. Source highlight: Gemma 4 QAT weights: the Gemma 4 family is now optimized with Quantization-Aware Training (QAT) to dramatically reduce memory requirements and maximize on-device performance. Look for the tags ending in `-qat`:
Ollama v0.30.5 — Release Notes & Engineering Impact
Ollama v0.30.5. Source highlight: Fixed the `gemma4:12b` floating point exception crash on x86, CUDA, Linux, and Windows systems.
Ollama v0.30.4 — Release Notes & Engineering Impact
Ollama v0.30.4. Source highlight: Nemotron-3-Ultra: NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.
Ollama v0.30.3 — Release Notes & Engineering Impact
Ollama v0.30.3. Source highlight: Gemma 4 12B: high-performance multimodal intelligence that runs directly on laptops, combining efficiency with advanced reasoning.