Post-Cutoff

Thinking Machines LabInkling 2 familyCurrentReasoning modelReleased 20 Nov 2026

Inkling 2 Mini

Thinking Machines Lab’s laptop-sized Inkling 2 model (Nov 20, 2026). Sources: https://thinkingmachines.ai/news/inkling-2-mini and https://huggingface.co/thinkingmachines/Inkling-2-Mini

PricePrice not published

Checked21 November 2026

No published training cutoff

At least9events since its release on 20 November 2026

0 historic, 2 major. 2 days of news.

Thinking Machines Lab doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

How to call it

3 ways to use Inkling 2 Mini.

Providers, model ids, endpoints and docs for Inkling 2 Mini
ProviderModel idEndpointDocs
Hugging Face huggingface.co
Tinker (Thinking Machines) thinkingmachines.ai
Local (Ollama, llama.cpp GGUF, vLLM, SGLang) huggingface.co

Pricing

Price not published.

No price source linked. Checked 21 November 2026.

Specs

Input
Text
Output
Text
Context window
Not published
Max output
Not published
Open weights
Yes
Licence
Apache-2.0
Training cutoff
Not published
Released
20 November 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Looped transformer for local agentic work

    26.4B total / 3.4B active MoE; the two middle six-layer blocks run three times per token (48 layer applications); ~20 GB in NVFP4, runs on a laptop; DeepSWE v1.1 48.2%, AA Index v5.0 20.1.

    Source: thinkingmachines.ai

Notes

Benchmarks are the lab’s own. Context length, Tinker pricing and modality beyond text not stated on the launch page; HF licence field apache-2.0.