# lean-agent-light - leanmodels.ai

*Lightweight class, v1.0, Qwen 3.5 base*

General-purpose agent - tool calling, structured output, multi-step reasoning

The entry point. A 21 GB model (Q4_K_M) that runs on 12 GB VRAM - expert offloading handles the rest. Qwen3.5 GDN hybrid architecture surpasses last-gen models many times its size.

## Specifications

- **Total params:** 35B
- **Active per token:** 3B
- **Base model:** Qwen3.5-35B-A3B
- **Architecture:** GDN hybrid MoE
- **Experts:** 256 experts, 8 active
- **Min VRAM / RAM:** 12 GB / 16 GB
- **Tier:** Free

## Measured performance

Real numbers from our reference rig, not projections.

- **1x RTX 3090 (24 GB):** prefill 14-31 tok/s, decode 19-31 tok/s
- **2x RTX 3090:** prefill 10-23 tok/s, decode 15-27 tok/s

## Download

- **Download:** 21.4 GB (single .lmpack, Q4_K_M)

```bash
curl -sSf https://leanmodels.ai/install.sh | sh
lean pull lean-agent-light
lean run lean-agent-light
```

Single binary, 15 MB. No Python, no Docker, no cloud dependency.
The installer is not live yet - binaries ship with our first release.