https://freedom.tech/project/ollama/ Every Ollama release and update tracked by Freedom.Tech. en Freedom.Tech is a Foundation project. https://foundation.xyz Freedom.Tech, a Foundation project (https://foundation.xyz) https://freedom.tech/posts/2026-08-26-ollama-0-33-1/ https://freedom.tech/posts/2026-08-26-ollama-0-33-1/ Wed, 26 Aug 2026 18:09:57 GMT Ollama 0.33.1 adds Qwen3.8 Flash support, structured output for MLX models, and fixes Metal GPU timeouts during model loading https://freedom.tech/posts/2026-08-21-ollama-0-33-0/ https://freedom.tech/posts/2026-08-21-ollama-0-33-0/ Fri, 21 Aug 2026 22:52:46 GMT Claude Desktop integration: toggle individual Ollama models on and off from the menu bar, choose models directly within Claude https://freedom.tech/posts/2026-08-19-ollama-0-32-15/ https://freedom.tech/posts/2026-08-19-ollama-0-32-15/ Wed, 19 Aug 2026 17:25:16 GMT Model metadata caching halves time-to-first-token, parser error handling fixed, Qwen system messages normalized https://freedom.tech/posts/2026-08-14-ollama-0-32-11/ https://freedom.tech/posts/2026-08-14-ollama-0-32-11/ Fri, 14 Aug 2026 01:22:12 GMT Ollama added DeepSeek Harness and Meta Muse Code agent support, plus web search in OpenAI-compatible Responses API https://freedom.tech/posts/2026-08-12-ollama-0-32-10/ https://freedom.tech/posts/2026-08-12-ollama-0-32-10/ Wed, 12 Aug 2026 22:36:49 GMT Ollama 0.32.10 changes default repeat penalty to 1.0 for faster speculative decoding, speeds NVFP4 prefill%, and fixes blob verification on shared digests https://freedom.tech/posts/2026-08-11-ollama-0-32-9/ https://freedom.tech/posts/2026-08-11-ollama-0-32-9/ Tue, 11 Aug 2026 13:23:33 GMT Ollama adds NVIDIA's Nemotron 3.5 Lightning, a 30B mixture-of-experts model optimized for always-on agent deployment https://freedom.tech/posts/2026-08-10-ollama-0-32-8/ https://freedom.tech/posts/2026-08-10-ollama-0-32-8/ Mon, 10 Aug 2026 23:49:29 GMT Muse Glimmer model now available across all platforms, optimized for coding agents and personal assistants with MLX performance on Apple Silicon https://freedom.tech/posts/2026-08-10-ollama-0-32-7/ https://freedom.tech/posts/2026-08-10-ollama-0-32-7/ Mon, 10 Aug 2026 10:49:15 GMT Muse Glimmer, Meta's 30B multimodal agent model, now runs locally on Ollama with Apple Silicon optimization and image input support https://freedom.tech/posts/2026-08-04-ollama-0-32-6/ https://freedom.tech/posts/2026-08-04-ollama-0-32-6/ Tue, 04 Aug 2026 18:49:20 GMT Ollama 0.32.6 speeds up Qwen3.5 on Apple GPUs via speculative decoding, fixes OpenAI API streaming format compliance, and improves TUI usability https://freedom.tech/posts/2026-07-25-ollama-0-32-4/ https://freedom.tech/posts/2026-07-25-ollama-0-32-4/ Sat, 25 Jul 2026 02:22:12 GMT Ollama 0.32.4 adds Laguna support for Apple GPUs, fixes Qwen3 MoE expert quantization, and improves speculative decoding performance https://freedom.tech/posts/2026-07-23-ollama-0-32-3/ https://freedom.tech/posts/2026-07-23-ollama-0-32-3/ Thu, 23 Jul 2026 00:44:28 GMT Ollama 0.32.3 fixes stalled downloads, expands GPU support to Windows ARM64 and B200, and adds chat/tool-calling for Laguna 2.1 models https://freedom.tech/posts/2026-07-20-ollama-0-32-2/ https://freedom.tech/posts/2026-07-20-ollama-0-32-2/ Mon, 20 Jul 2026 21:00:30 GMT Ollama 0.32.2 adds agent skills system, fixes Anthropic thinking-block handling, updates llama.cpp and MLX backends, and enables unlimited tool rounds for cloud models https://freedom.tech/posts/2026-07-16-ollama-0-32-1/ https://freedom.tech/posts/2026-07-16-ollama-0-32-1/ Thu, 16 Jul 2026 03:27:23 GMT Ollama 0.32.1 fixes MLX model cache leaks, improves Gemma 4 tool calling, and adds working directory context to agents https://freedom.tech/posts/2026-07-11-ollama-0-32-0/ https://freedom.tech/posts/2026-07-11-ollama-0-32-0/ Sat, 11 Jul 2026 01:03:46 GMT Adds Qwen3.5 parser and renderer selection; Agent UI warns before loading old agent models https://freedom.tech/posts/2026-07-06-ollama-0-31-2/ https://freedom.tech/posts/2026-07-06-ollama-0-31-2/ Mon, 06 Jul 2026 22:28:22 GMT Flash attention now works on older NVIDIA GPUs, vision model offloading improved, and non-UTF-8 model paths fixed https://freedom.tech/posts/2026-06-30-ollama-0-31-1/ https://freedom.tech/posts/2026-06-30-ollama-0-31-1/ Tue, 30 Jun 2026 22:10:17 GMT Gemma 4 nearly 90 percent faster on Apple Silicon via multi-token prediction https://freedom.tech/posts/2026-06-29-ollama-0-30-12/ https://freedom.tech/posts/2026-06-29-ollama-0-30-12/ Mon, 29 Jun 2026 17:45:08 GMT Fixed tool call parsing to handle JSON strings with braces correctly, and updated llama.cpp and MLX dependencies https://freedom.tech/posts/2026-06-25-ollama-0-30-11/ https://freedom.tech/posts/2026-06-25-ollama-0-30-11/ Thu, 25 Jun 2026 01:52:05 GMT Ollama 0.30.11 fixes GPU detection on hybrid Windows systems, improves speculative decoding, and corrects memory reporting for partially offloaded models https://freedom.tech/posts/2026-06-17-ollama-0-30-10/ https://freedom.tech/posts/2026-06-17-ollama-0-30-10/ Wed, 17 Jun 2026 16:22:02 GMT Command and Northfamily models now run on Apple Silicon via MLX engine, llama.cpp updated to build 9672 https://freedom.tech/posts/2026-06-15-ollama-0-30-9/ https://freedom.tech/posts/2026-06-15-ollama-0-30-9/ Mon, 15 Jun 2026 19:55:07 GMT Ollama 0.30.9 adds Cohere2Moe support, fixes token output limits in coding agents, and validates message sizes against context windows https://freedom.tech/posts/2026-06-12-ollama-0-30-8/ https://freedom.tech/posts/2026-06-12-ollama-0-30-8/ Fri, 12 Jun 2026 17:04:52 GMT Ollama 0.30.8 improves prompt caching efficiency, fixes provider selection bugs, and hardens MLX inference stability with snapshot creation https://freedom.tech/posts/2026-06-07-ollama-0-30-7/ https://freedom.tech/posts/2026-06-07-ollama-0-30-7/ Sun, 07 Jun 2026 21:51:48 GMT Ollama adds Hermes Desktop, a native UI for managing Hermes agent conversations and integrations via ollama launch https://freedom.tech/posts/2026-06-05-ollama-0-30-6/ https://freedom.tech/posts/2026-06-05-ollama-0-30-6/ Fri, 05 Jun 2026 20:00:18 GMT Ollama adds Gemma 4 QAT models for lower memory use, integrates Oh My Pi coding agent, improves Apple Silicon quantization https://freedom.tech/posts/2026-06-03-ollama-0-30-3/ https://freedom.tech/posts/2026-06-03-ollama-0-30-3/ Wed, 03 Jun 2026 16:35:43 GMT Ollama added Gemma 4 12B model support, expanding locally-runnable open-weight options for builders https://freedom.tech/posts/2026-06-03-ollama-0-30-2/ https://freedom.tech/posts/2026-06-03-ollama-0-30-2/ Wed, 03 Jun 2026 00:37:18 GMT Auto-install Cline CLI; Qwen code integration added; Template logging improved for troubleshooting https://freedom.tech/posts/2026-05-13-ollama-0-23-4/ https://freedom.tech/posts/2026-05-13-ollama-0-23-4/ Wed, 13 May 2026 20:40:22 GMT Ollama launch now handles vision models with image inputs. Local image paths work in Claude tool results https://freedom.tech/posts/2026-05-13-ollama-0-30-0/ https://freedom.tech/posts/2026-05-13-ollama-0-30-0/ Wed, 13 May 2026 14:32:54 GMT Ollama now builds directly on llama.cpp with GGUF format support and MLX acceleration for Apple Silicon inference