Inkling 2 Mini on Ollama: MLX build, one-command hooks into Claude Code and OpenCode
ollama · x · 2026-11-21
The Ollama model page for Inkling 2 Mini details:
- Weights & formats: three tags — latest, 26b-a5b, and an MLX build 26b-a5b-nvfp4, each 20GB, with text+image input, tool calling, and thinking
- Requirements: a Mac with 32GB+ memory; one command (ollama run inkling-2-mini) to start
- Agent integration: official ollama launch one-liners to plug the model into Claude Code, OpenCode, Hermes Agent, and OpenClaw, plus CLI/cURL/Python/JavaScript examples
- Architecture: looped middle layers give each token more compute, targeting coding, computer use, design, and finance tasks
Related event: Inkling 2 Mini lands on Ollama, runs locally on Mac mini(2 posts)→
More from coding & agent
- Changing one MCP tool description sentence lifted correct tool selection from 19/55 to 45/55 — sparkignitefire · 2026-11-21
- Founder's rebuttal to McKinsey: enterprises need a first brain, not an AI second brain — vasuman · 2026-11-21
- Devs: LLMs absorb layered complexity until context explodes; tools and MCP are too heavy — dscape · 2026-11-21
- Unguided coding agents pass only 52% of web checks; Modern Web Guidance lifts it to 91% — rseroter · 2026-11-21
- n8n launches Agents: your existing workflows become an AI agent's toolkit — SucceededMind · 2026-11-21
- Nous Research picks winners of Hermes Agent plugin hackathon with ~1,000 entries — alexcovo_eth · 2026-11-21