§ local-llm · storyline
Ollama v0.20.5
Ollama releases v0.20.5 with OpenClaw messaging channel support, flash attention for Gemma 4, improved OpenCode detection, and a fix for the /save command on safetensor-imported models.
OpenClaw channel setup with `ollama launch` What's Changed OpenClaw channel setup: connect WhatsApp, Telegram, Discord, and other messaging channels through `ollama launch openclaw` Enable flash attention for Gemma 4 on compatible GPUs `ollama launch opencode` now detects curl-based OpenCode installs at `~/.opencode/bin` Fix `/save` command for models imported from safetensors New Contributors @sjhddh made their first contribution in https://github.com/ollama/ollama/pull/15424 Full Changelog: https://github.com/ollama/ollama/compare/v0.20.4...v0.20.5
§ sources1 publication · timeline below
- github.comollama v0.20.5primary