# lean-think-heavy - leanmodels.ai

*Heavyweight class, v1.0, Arcee Trinity Large-Thinking base*

Extended reasoning - chain-of-thought, agentic tasks, deep analysis

398B total, ~13B active per token. Interleaved sliding-window + global attention with chain-of-thought and agentic RL post-training. The largest model in the catalog.

## Specifications

- **Total params:** 398B
- **Active per token:** ~13B
- **Base model:** Arcee Trinity-Large-Thinking
- **Architecture:** afmoe (SWA + global)
- **Experts:** 256 experts, 4 active + 1 shared
- **Target VRAM / RAM:** 48 GB / 64 GB
- **Tier:** Paid
- **License:** Apache 2.0

## Not yet verified

This model hasn't been benchmarked or verified on our hardware yet. Sizes and specs are targets, not measured results. No download or purchase until it clears the same verification the available models passed.

## Get the model

- **Download (target):** ~241.9 GB (single .lmpack, Q4_K_M)