Ollama 發布 v0.40.17-rc3,改善多個 AI 工具的使用方式
v0.40.17-rc3
Ollama v0.40.17-rc3 加入多項更新:Claude Code 需要工具時才載入 MCP 工具;Apple silicon 上的 Ollama 現在能同時處理多個請求。
- 更新也修正了部分顯示卡載入模型或配置記憶體失敗的問題,並讓 API 傳遞工具設定時保留原有的 JSON 格式規則。
- 這次更新還調整了多行輸入、模型推理設定和 ChatGPT 設定檔切換等操作,讓使用過程少一些卡關。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
Inkling 2 Mini
Inkling 2 Mini from Thinking Machines is a 26B parameter model with 5.4B active.
Its looped layers give it more computation per token than its size suggests, and it still fits on a Mac at about 20GB. It handles text and images, tool calls, and thinking, and scores 79.2% on SWE-Bench Verified).
ollama run inkling-2-mini
What's Changed
-
ollama launch claudesupports Claude Code's deferred tool loading, so MCP tools are loaded when needed instead of all at
once -
Ollama on Apple silicon now serves multiple requests at once.
-
ollama launch opencodesets thinking options from the model's metadata -
ollama launch pirefreshes Pi's model list after sign-in and passes along prompt arguments -
ollama launch chatgpt --restoreasks before switching an active profile and preserves existing settings and chat history;
quitting ChatGPT yourself now lets it exit through its own quit prompt -
Running
ollamawith no arguments in a non-interactive shell prints help instead of erroring -
Ctrl+C or Ctrl+G while in a multiline
"""block leaves multiline mode instead of swallowing the next line -
Changing the context shift setting no longer reloads the model
-
Vulkan now uses mmap for integrated GPUs, fixing
Failed to allocate pinned memoryload failures on shared-memory GPUs -
On Windows iGPUs, partially offloaded models no longer fail to allocate the KV cache
-
Tool definitions passed through the API keep JSON schema keywords Ollama doesn't model instead of dropping them
-
Disabling thinking now maps to the model's lowest supported reasoning level rather than being ignored
-
Source builds can use prebuilt MLX-C and XGrammar binaries
Full Changelog: v0.40.16...v0.40.17-rc3