Inkling 2 Small
No published training cutoff
Price not published
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
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.
3 ways to use Inkling 2 Mini.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | huggingface.co | ||
| Tinker (Thinking Machines) | thinkingmachines.ai | ||
| Local (Ollama, llama.cpp GGUF, vLLM, SGLang) | huggingface.co |
Price not published.
No price source linked. Checked 21 November 2026.
What its maker marketed at launch, and what people found later, each with its source.
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.
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.
Paste this into a new chat. It points your AI to a dated list of AI news since October 2026, with a source for every item.
Using Gemini, Grok or another assistant? Copy the prompt and paste it into a new chat. Only Claude and ChatGPT have a link that opens with a prompt filled in.
Files for every cutoff, with their sizes: Briefings.
For developers: an MCP server is planned. For AI agents