{"schema":"postcutoff/model@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/m/inkling-2-mini/","md":"https://postcutoff.com/m/inkling-2-mini/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"inkling-2-mini","name":"Inkling 2 Mini","org":"Thinking Machines Lab","family":"Inkling 2","released":"2026-11-20","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"apache-2.0","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","url":"https://huggingface.co/thinkingmachines/Inkling-2-Mini"},{"provider":"Tinker (Thinking Machines)","url":"https://thinkingmachines.ai/news/inkling-2-mini"},{"provider":"Local (Ollama, llama.cpp GGUF, vLLM, SGLang)","url":"https://huggingface.co/blog/inkling2mini"}],"capabilities":[{"name":"Looped transformer for local agentic work","detail":"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.","first":false,"discovered":"launch","source":"https://thinkingmachines.ai/news/inkling-2-mini"}],"entry":"2026-11-20-thinking-machines-inkling-2-mini-looped","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.","verified":"2026-11-21","body_md":"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","page_url":"https://postcutoff.com/m/inkling-2-mini/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":9,"you_url":"https://postcutoff.com/you/inkling-2-mini/","briefings":null}