← November 21, 2026 briefing · added in the 12:00 KST update

Inkling 2 Mini follow-up: Ollama v0.40.17 runs it out of the box ('79.2% on SWE-Bench Verified'), adds concurrent requests on Apple silicon

Announced November 21, 2026

Verified (fact)

Ollama's v0.40.17 release (tagged rc4) supports Thinking Machines Lab's Inkling 2 Mini. It can be run with a single command, `ollama run inkling-2-mini`. The release notes say the model supports text and image input, tool calling, and thinking, and scored 79.2% on SWE-Bench Verified. In this version, Ollama also handles multiple requests concurrently on Apple silicon devices. `ollama launch claude` supports Claude Code's deferred tool loading, so MCP tools are loaded only when needed rather than all at once.

Needs fact-check (claim)

Ollama release notes: Inkling 2 Mini scores 79.2% on SWE-Bench Verified

Why it matters (interpretation)

The new open-weight model can now run directly on a personal Mac. This lowers the barrier to trying it in a local coding agent setup.

Sources

Story thread

  1. 2026-11-21 Thinking Machines Lab releases looped open-weight model Inkling 2 Mini: 26B total, 5.4B active, runs on a Mac in ~20GB
  2. 2026-11-21 Inkling 2 Mini follow-up: Ollama v0.40.17 runs it out of the box ('79.2% on SWE-Bench Verified'), adds concurrent requests on Apple silicon

More about Ollama