lean-coder-welter
Welterweight class · v1.0 · Qwen 3-Coder-Next base
Code generation - debugging, refactoring, code review
Verified vs llama.cppFree
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
Measured performance
Real numbers from our reference rig, not projections.
| Hardware | Prefill | Decode |
|---|---|---|
| 1x RTX 3090 (24 GB) | 12-23 tok/s | 14-20 tok/s |
| 2x RTX 3090 | 8-17 tok/s | 10-18 tok/s |
Download
Download 48.7 GB - single .lmpack, Q4_K_M
$ lean pull lean-coder-welterQuick start (coming soon)
$ curl -sSf https://leanmodels.ai/install.sh | sh
$ lean pull lean-coder-welter
$ lean run lean-coder-welterSingle binary, 15 MB. No Python, no Docker, no cloud dependency.
The installer is not live yet — binaries ship with our first release.