Ollama

Ollama v0.32.1 improves Gemma 4's tool calling and multi-turn reasoning, fixes MLX model cache leaks, and enhances Agent search and authentication flows.

Ollama v0.32.1 improves Gemma 4 tool calling and multi-turn reasoning, fixes an MLX cache leak, and optimizes cache snapshot performance.

Pal MCP Server gained 11,676 stars on GitHub this week, integrating Claude Code, GeminiCLI, and other CLIs while supporting multiple backends like Gemini and OpenAI.

Ollama v0.32.0 introduces an interactive Agent experience and renames Codex App to ChatGPT.

Ollama v0.32.0 adds parser/renderer selection for Qwen3.5, warns on old Agent models at launch, and introduces an agent UI command.

Ollama v0.31.2 includes Agent core integration, CUDA fallback, Flash Attention enablement, MLX rewrite, and various fixes.

Ollama v0.31.2 enhances CUDA and ROCm GPU support, enables Flash Attention for CUDA CC 6.x, and removes legacy code and experimental features.

Ollama v0.31.2 introduces an Agent core framework and enables Flash Attention for CUDA CC 6.x GPUs, along with various fixes.

Ollama v0.31.1 uses multi-token prediction to significantly accelerate Gemma 4 inference on Apple Silicon.