# lean-coder-welter - leanmodels.ai

*Welterweight class, v1.0, Qwen 3-Coder-Next base*

Code generation - debugging, refactoring, code review

80B total with 512 experts, only 3B active per token. A 48.7 GB model (Q4_K_M) that runs on 12 GB VRAM. Tuned for code generation, debugging, and software engineering.

## Specifications

- **Total params:** 80B
- **Active per token:** 3B
- **Base model:** Qwen3-Coder-Next
- **Architecture:** MoE (512 experts)
- **Experts:** 512 experts, 10 active
- **Min VRAM / RAM:** 12 GB / 32 GB
- **Tier:** Free

## Measured performance

Real numbers from our reference rig, not projections.

- **1x RTX 3090 (24 GB):** prefill 12-23 tok/s, decode 14-20 tok/s
- **2x RTX 3090:** prefill 8-17 tok/s, decode 10-18 tok/s

## Download

- **Download:** 48.7 GB (single .lmpack, Q4_K_M)

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

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