Ollama - Package Updates

[Package Updates]

[1.5.3]

• Update ollama to 0.17.6
• Full Changelog
• Fixed issue where GLM-OCR would not work due to incorrect prompt rendering
• Fixed tool calling parsing and rendering for Qwen 3.5 models

[Package Updates]

[1.5.4]

• Update ollama to 0.17.7
• Full Changelog
• Allow thinking levels such as "medium" to correctly interpreted in Ollama's API for all thinking models
• Add context length to support compaction when using ollama launch

[Package Updates]

[1.6.1]

• Update ollama to 0.18.1
• Full Changelog
• Web Search and Fetch in OpenClaw
• Ollama now ships with web search and web fetch plugin for OpenClaw. This allows Ollama's models (local or cloud) to search the web for the latest content and news. This also allows OpenClaw with Ollama to be able to fetch the web and extract readable content for processing. This feature does not execute JavaScript.
• When using local models with web search in OpenClaw, ensure you are signed into Ollama with ollama signin
• You can install web search directly into OpenClaw as a plugin if you already have OpenClaw configured and working:

[Package Updates]

[1.6.2]

• Update ollama to 0.18.2
• Full Changelog
• Add extra check to ensure npm and git are installed before installing OpenClaw
• Claude Code will now be faster when run locally, due to preventing cache breakages
• Fix to correctly support ollama launch openclaw --model <model>
• Register Ollama's websearch package correctly for OpenClaw

[Package Updates]

[1.8.0]

• Update ollama to 0.20.0
• Full Changelog
• docs: update pi docs by @​ParthSareen in #​15152
• mlx: respect tokenizer add_bos_token setting in pipeline by @​dhiltgen in #​15185
• tokenizer: add SentencePiece-style BPE support by @​dhiltgen in #​15162

[Package Updates]

[1.8.1]

• Update ollama to 0.20.2
• Full Changelog
• app: default app home view to new chat instead of launch by @​jmorganca in #​15312
• bench: add prompt calibration, context size flag, and NumCtx reporting by @​dhiltgen in #​15158
• model/parsers: fix gemma4 arg parsing when quoted strings contain " by @​drifkin in #​15254
• ggml: skip cublasGemmBatchedEx during graph reservation by @​jessegross in #​15301
• gemma4: enable flash attention by @​dhiltgen in #​15296
• ggml: fix ROCm build for cublasGemmBatchedEx reserve wrapper by @​jessegross in #​15305
• model/parsers: rework gemma4 tool call handling by @​drifkin in #​15306

[Package Updates]

[1.8.2]

• Update ollama to 0.20.3
• Full Changelog
• Gemma 4 Tool Calling improvements
• Added latest models to Ollama App
• OpenClaw fixes for launching TUI

[Package Updates]

[1.8.3]

• Update ollama to 0.20.4
• Full Changelog
• mlx: Improve M5 performance with NAX
• gemma4: enable flash attention

[Package Updates]

[1.8.5]

• Update ollama to 0.20.6
• Full Changelog
• Gemma 4 Tool Calling Improvements
• App bug fixes and improvements
• Parallel tool calling improvements
• Docs for Hermes Agent

[Package Updates]

[1.8.6]

• Update ollama to 0.20.7
• Full Changelog
• Fix quality of gemma:e2b and gemma:e4b when thinking is disabled
• ROCm: Update to ROCm 7.2.1 on Linux by @​saman-amd in #​15483

[Package Updates]

[1.9.0]

• Update ollama to 0.21.0
• Full Changelog
• Gemma 4 on MLX. Added support for running Gemma 4 via MLX on Apple Silicon, including a text-only MLX runtime for the model. The MLX backend also picked up mixed-precision quantization, better capability detection, and a batch of new op wrappers (Conv2d, Pad, activations, trig, masked SDPA, and RoPE-with-freqs).
• Hermes and GitHub Copilot CLI in ollama launch. Added both integrations, which can now be configured in one command alongside the rest of the supported coding agents.
• OpenCode moved to inline config. ollama launch opencode now writes its config inline rather than to a separate file, matching how other integrations are handled.
• ollama launch no longer rewrites config when nothing changed. Pressing on a configured multi-model integration, or passing --model with the current primary, used to trigger a confirmation prompt and rewrite both the editor's config file and config.json. Now it's a no-op when the resolved model list matches what's already saved.
• Fixed ollama launch openclaw --yes so it correctly skips the channels configuration step, so non-interactive setups complete cleanly.
• Restored the Gemma 4 nothink renderer with the e2b-style prompt.
• Fixed the Gemma 4 compiler error that was breaking Metal builds.
• Fixed macOS cross-compiles so they no longer trigger generate, which was breaking cmake builds on some Xcode versions.
• Quieted cgo builds by suppressing deprecated warnings during go build.
• Full Changelog: https://github.com/ollama/ollama/compare/v0.20.7...v0.21.0

[Package Updates]

[1.9.1]

• Update ollama to 0.21.1
• Full Changelog
• MLX runner adds logprobs support for compatible models
• Faster MLX sampling with fused top-P and top-K in a single sort pass, plus repeat penalties applied in the sampler
• Improved MLX prompt tokenization by moving tokenization into request handler goroutines
• Better MLX thread safety for array management
• GLM4 MoE Lite performance improvement with a fused sigmoid router head
• Fixed model picker showing stale model after switching chats in the macOS app
• Fixed structured outputs for Gemma 4 when think=false
• Full Changelog: https://github.com/ollama/ollama/compare/v0.21.0...v0.21.1

[Package Updates]

[1.9.2]

• Update ollama to 0.21.2
• Full Changelog
• Improved reliability of the OpenClaw onboarding flow in ollama launch
• Recommended models in ollama launch now appear in a fixed, canonical order
• OpenClaw integration now bundles Ollama's web search plugin in OpenClaw

[Package Updates]

[1.10.0]

• Update ollama to 0.22.0
• Full Changelog
• NVIDIA's Nemotron 3 Omni
• Poolside's first open-weight coding model - Laguna XS.2
• Full Changelog: https://github.com/ollama/ollama/compare/v0.21.2...v0.22.0

[Package Updates]

[1.10.1]

• Update ollama to 0.22.1
• Full Changelog
• Updated the Gemma 4 renderer for thinking and tool calling improvements
• Model recommendations are now updated without updating Ollama
• Aligned the desktop app's launch page with ollama launch integrations
• Fixed the Poolside integration title in ollama launch
• Full Changelog: https://github.com/ollama/ollama/compare/v0.22.0...v0.22.1

[Package Updates]

[1.11.0]

• Update ollama to 0.23.0
• Full Changelog
• Launch Claude Desktop with ollama launch claude-desktop
• The Ollama app now surfaces featured models from server-driven recommendations
• Fixed OpenClaw gateway timeout on Windows by enforcing IPv4 loopback (thanks @UniquePratham)
• Hardened Metal initialization to gracefully handle ggml kernel compilation failures

[Package Updates]

[1.11.1]

• Update ollama to 0.23.1
• Full Changelog
• Update MLX and MLX-C with threading fixes by @dhiltgen in #15845
• go: bump to 1.26 by @ParthSareen in #15904
• Add Gemma 4 MTP speculative decoding by @pdevine in #15980

[Package Updates]

[1.11.2]

• Update ollama to 0.23.2
• Full Changelog
• ollama launch no longer includes Claude Desktop due to the third-party integration being limited to Anthropic models.
• Use ollama launch claude-desktop --restore to restore Claude Desktop to its normal state.
• /api/show responses are now cached, improving median latency by ~6.7x which will increase load speed for integrations like VS Code.
• Improved backup workflow when managing launch integrations
• Cleaner image generation layout in the MLX runner
• Full Changelog: https://github.com/ollama/ollama/compare/v0.23.1...v0.23.2

[Package Updates]

[1.11.3]

• Update ollama to 0.23.3
• Full Changelog
• mlx: refined model push behavior by @dhiltgen in #15431
• app: harden update flows by @dhiltgen in #16100
• mlx: update the imagegen runner for mlx thread affinity by @pdevine in #16096
• mlx: avoid status timeout during inference by @dhiltgen in #16086
• mlx: fix macOS 26 target leakage in v3 metallib by @dhiltgen in #16053

[Package Updates]

[1.11.4]

• Update ollama to 0.23.4
• Full Changelog
• ollama launch opencode now supports vision models with image inputs
• Fixed formatting of Claude tool results when using local image paths