Ollama v0.12.1 — Release Notes & Engineering Impact
Ollama v0.12.1. Source highlight: Qwen3 Embedding: state of the art open embedding model by the Qwen team
1172 tracked entries. Older history is imported progressively; see source coverage.
Ollama v0.12.1. Source highlight: Qwen3 Embedding: state of the art open embedding model by the Qwen team
LocalAI v3.5.4. Source highlight: fix(python): make option check uniform across backends
LocalAI v3.5.3. Source highlight: fix(diffusers): fix float detection
Ollama v0.12.0. Source highlight: Cloud models are now available in preview, allowing you to run a group of larger models with fast, datacenter-grade hardware.
LocalAI v3.5.2. Source highlight: Revert "feat(nvidia-gpu): bump images to cuda 12.8"
Open WebUI v0.6.30. Source highlight: [0.6.30] - 2025-09-17
LocalAI v3.5.1. Source highlight: fix: make sure to turn down all processes on exit
Open WebUI v0.6.29. Source highlight: [0.6.29] - 2025-09-17
Hugging Face Transformers v4.56.2. Source highlight: Processor load with multi-processing (#40786)
vLLM v0.10.2. Source highlight: This release contains 740 commits from 266 contributors (97 new)!
Ollama v0.11.11. Source highlight: Improved memory usage when using gpt-oss in Ollama's app
Open WebUI v0.6.28. Source highlight: [0.6.28] - 2025-09-10
Open WebUI v0.6.27. Source highlight: [0.6.27] - 2025-09-09
Hugging Face Transformers v4.56.1. Source highlight: Patch release v4.56.1
Ollama v0.11.10. Source highlight: EmbeddingGemma a new open embedding model that delivers best-in-class performance for its size
LocalAI v3.5.0. Source highlight: Welcome to LocalAI 3.5.0! This release focuses on expanding backend support, improving usability, refining the overall experience, and keeping reducing footprint of LocalAI, to make it a truly portable, privacy-focused AI stack. We’ve added several new backends, enhanced the WebUI with new features,
Dify 1.8.1. Source highlight: 🌟 What's New in v1.8.1? 🌟
Ollama v0.11.9. Source highlight: Improved performance via overlapping GPU and CPU computations
Hugging Face Transformers v4.56.0. Source highlight: DINOv3 is a family of versatile vision foundation models that outperforms the specialized state of the art across a broad range of settings, without fine-tuning. DINOv3 produces high-quality dense features that achieve outstanding performance on various vision tasks, significantly surpassing previou
Open WebUI v0.6.26. Source highlight: [0.6.26] - 2025-08-28
Ollama v0.11.8. Source highlight: `gpt-oss` now has flash attention enabled by default for systems that support it
Dify 1.8.0. Source highlight: 🎉 Dify v1.8.0 Release Notes 🎉
Ollama v0.11.7. Source highlight: DeepSeek-V3.1 is now available to run via Ollama.
Hugging Face Transformers v4.55.4. Source highlight: There was a mick mack on our side when cherry-picking the commit #40197 which led to a wrong commit in the patch!
Open WebUI v0.6.25. Source highlight: [0.6.25] - 2025-08-22
Open WebUI v0.6.24. Source highlight: [0.6.24] - 2025-08-21
Open WebUI v0.6.23. Source highlight: [0.6.23] - 2025-08-21
Hugging Face Transformers v4.55.3. Source highlight: Patch release 4.55.3
vLLM v0.10.1.1. Source highlight: This is a critical bugfix and security release:
Ollama v0.11.6. Source highlight: Ollama's app will now switch between chats faster
vLLM v0.10.1. Source highlight: **NOTE: This release deprecates V0 FA3 support and as a result FP8 kv-cache in V0 may have issues**
Ollama v0.11.5. Source highlight: Performance improvements for the `gpt-oss` models
Hugging Face Transformers v4.55.2. Source highlight: Patch release 4.55.2!
Hugging Face Transformers v4.55.1. Source highlight: Patch release 4.55.1:
LocalAI v3.4.0. Source highlight: What’s New in LocalAI 3.4.0 🎉
Open WebUI v0.6.22. Source highlight: [0.6.22] - 2025-08-11
Dify 1.7.2. Source highlight: ✨ What’s New in v1.7.2? ✨
Open WebUI v0.6.21. Source highlight: [0.6.21] - 2025-08-10
Open WebUI v0.6.20. Source highlight: [0.6.20] - 2025-08-10
Open WebUI v0.6.19. Source highlight: [0.6.19] - 2025-08-09
Ollama v0.11.4. Source highlight: openai: allow for content _and_ tool calls in the same message
Ollama v0.11.3. Source highlight: Fixed issue where `gpt-oss` would consume too much VRAM when split across GPU & CPU or multiple GPUs
Ollama v0.11.2. Source highlight: Fix crash in gpt-oss when using kv cache quanitization
Ollama v0.11.0. Source highlight: Welcome OpenAI's gpt-oss models
Hugging Face Transformers v4.55.0. Source highlight: Welcome GPT OSS, the new open-source model family from OpenAI!
LocalAI v3.3.2. Source highlight: Exciting New Features 🎉
LocalAI v3.3.1. Source highlight: This is a minor release, however we have addressed some important bug regarding Intel-GPU Images, and we have changed naming of the container images.
Ollama v0.10.1. Source highlight: Fixed unicode character input for Japanese and other languages in Ollama's new app
Hugging Face Transformers 4.54.1. Source highlight: Patch release 4.54.1
LocalAI v3.3.0. Source highlight: What’s New in LocalAI 3.3.0 🎉