November 20 agent guide: Inkling 2 Mini open weights
November 20, 2026 extended Thinking Machines’ Inkling 2 line downward. Inkling 2 Mini ships Apache 2.0 open weights as a 26.4B MoE looped transformer aimed at laptop-scale agentic coding with strong DeepSWE and Vals scores among sub-100B open models.

In this post (6 sections)
November 20, 2026 is an open-weight local-agent day. Thinking Machines Lab released Inkling 2 Mini eight days after Inkling 2 Small’s Apache 2.0 drop, targeting laptops and small GPUs without giving up agentic coding strength.
Architecture
Inkling 2 Mini stores 24 layers and runs the two middle blocks three times per token, so 24 stored layers behave like 48 depth for reasoning. Specs: 26.4B total MoE parameters, 3.4B active, 5.4B weight activations per token with looping, multimodal image-text-to-text tagging on Hugging Face, and native NVFP4 training/inference. Quantized GGUF paths support Ollama and llama.cpp.
Monitorability angle
The lab stresses that looping can improve answers without writing long chain-of-thought, which changes how teams oversee agents. Factual benchmarks do not improve with more loops the way long-context graph tasks can. Mini leans on search and tools (BrowseComp, DeepSearchQA, MCP Atlas) to cover knowledge gaps.
Who should adopt it
- Teams that need offline or air-gapped coding agents after November 12’s Small weights proved the Inkling 2 recipe.
- Platforms standardizing on Apache 2.0 MoE workers beside Qwen3.8-27B and Gemma 4 mid-size opens.
- Eval groups measuring tokens per resolved DeepSWE or Terminal-Bench task on a single workstation.
Builder checklist
- 01Pull thinkingmachines/Inkling-2-MiniConfirm Apache 2.0 terms and NVFP4 vs GGUF path for your hardware.
- 02Benchmark against Qwen3.8-27B on the same harnessUse DeepSWE and a private merge suite; do not trust only published scatter plots.
- 03Wire MCP tools earlyMini’s knowledge gap is intentional; tool use is part of the product story.
- 04Keep Small for heavier hostsMini does not replace Inkling 2 Small’s larger deployment profile.
Conclusion
November 20 gives builders a laptop-scale Inkling 2 worker with Apache 2.0 weights and a looping design aimed at agentic coding efficiency. Bacancy Technology’s rule: treat Mini as a local open lane beside Qwen4-Max API and GPT-6.2 Sol cloud defaults.
Related reading
- November 19 Genie 4 API: /blog/november-19-genie-4-api-claude-code-328-2026
- November 16 Qwen4-Max: /blog/november-16-qwen4-max-claude-code-326-2026
- November 12 Inkling 2 Small: /blog/november-12-gemini-4-hydrogen-inkling-sglang-2026
- November 4 Kimi weights: /blog/november-04-kimi-k31-pro-weights-hy4-2026
- Agentic AI topic map: /topics/agentic-ai
Need local open-weight agent hosting?
Bacancy Technology designs open-weight serving, NVFP4 capacity plans, and MCP tool allowlists. Consulting: /consulting/ . Contact: /contact/ .
Sources: thinkingmachines.ai — inkling 2 mini ; Hugging Face .
Agentic AI patterns, delivered Thursdays
What I am shipping, watching, and pruning out of client stacks each week. One email. No fluff.