Thinking Machines open-sources Inkling 2 Mini: 26B looped transformer with 5.4B active params
SonglinYang4 · x · 2026-11-21
Thinking Machines released open weights for Inkling 2 Mini, a looped transformer with 24 layers (middle 12 looped 3x), pruned to 26B total / 5.4B active parameters, natively in NVFP4, logit-distilled from a larger model. It scores 20.1 on AA Index and is positioned as small enough to run on a laptop yet strong enough for agentic work—a smaller rung on the scaling ladder after feedback that Inkling 2 Small's 594B was too big.
More from Models
- Tesla FSD 15's real-time view isn't 3D rendering — it's the AI model's own synthetic perception — mark_k · 2026-11-22
- Gemini Black Friday half-price: JP-region trick gets Pro annual plan for $91.54 — huangyun_122 · 2026-11-22
- Microsoft's USB4 RDMA lets mini PCs pool memory to run Qwen3-235B — JFPuget · 2026-11-22
- Google AI Mode now enforces usage limits, users surprised by rate-limit popup — elvano124 · 2026-11-22
- Sol 6.2 now refuses reverse engineering that Sol 6.1 happily did for a month — cardak98 · 2026-11-22
- Anthropic's record ~$81B IPO, GPT-6.2 pricing, Qwen4-Max and Copilot Autopilot: week in review — ksraj1001 · 2026-11-22