Watching local inference live in LM Studio on an M2 MacBook
vboykis · x · 2026-11-23
vboykis shares the simple joy of running Thinking Machines' inkling 2 mini locally via LM Studio on an M2 MacBook, where you can watch inference happen live: streamed chunks, token counts (6719 prompt / 473 completion incl. 100 reasoning tokens in her example) all visible in the logs.
More from Models
- Bittensor's Subnet 92 claims a 'frontier JEV model' 200x faster than LLMs — markjeffrey · 2026-11-23
- Physicist claims Claude independently reproduced his private Riemann hypothesis conclusion — bdsqlsz · 2026-11-23
- Qwen 3.8 27B pi adapter tested: 4x fewer tool calls, 54% faster, but no harder-task gains — Fabulous_Pollution10 · 2026-11-23
- Pedro Domingos: OpenAI admits pretraining has barely improved since 2022 — pmddomingos · 2026-11-23
- Inkling-2-Mini hits 10.04x on KernelBench-Mega locally, beating Grok 4.7 and GPT-6.1 — ziqiao_ma · 2026-11-23
- Baidu open-sources Unlimited-OCR: 3B model reads 100-page PDFs in one shot — udmrzn · 2026-11-23