Tech Meridian ← LIVE FEED
PROMY MERIDIAN RU

RELEASE · MODELS · #4010

Thinking Machines Lab releases Inkling 2 Mini — looped MoE model for local use

Inkling 2 Mini is a new multimodal looped transformer Mixture-of-Experts from Thinking Machines Lab (~26B physical params, ~3B active per token) that reuses 24 physical layers with a triple-pass loop to behave like a deeper model, supports 1M-token context, image+text inputs, mixed-precision NVFP4/MXFP8 expert weights, and a DSpark drafter; a variable-loop research checkpoint (TML-d24-varloop-research) is also provided. The model is packaged for local and datacenter inference with transformers, llama.cpp, MLX and SGLang support and is reported to lead many benchmarks in its class.

KEY POINTS

  1. Inkling 2 Mini is a new multimodal looped transformer Mixture-of-Experts from Thinking Machines Lab (~26B physical params, ~3B active per token) that reuses 24 physical layers with a triple-pass loop to behave like a deeper model, supports 1M-token context, image+text inputs, mixed-precision NVFP4/MXFP8 expert weights, and a DSpark drafter; a variable-loop research checkpoint (TML-d24-varloop-research) is also provided.
  2. The model is packaged for local and datacenter inference with transformers, llama.cpp, MLX and SGLang support and is reported to lead many benchmarks in its class.
  3. This release demonstrates a practical looped-MoE design that increases logical depth and capacity while keeping checkpoints small, aimed at making high-capacity multimodal models viable for local and on‑premise deployments.

WHY IT MATTERS

This release demonstrates a practical looped-MoE design that increases logical depth and capacity while keeping checkpoints small, aimed at making high-capacity multimodal models viable for local and on‑premise deployments.

SOURCES & TIMELINE

2