---
license: other
language:
- en
- ko
tags:
- local-inference
- gguf
- moe
- qwen
- windows
- consumer-gpu
- openai-compatible
- llama-cpp
pipeline_tag: text-generation
library_name: gguf
---

# Pungyo (풍요) — Run Qwen3.6-35B-A3B on an 8GB laptop

> **램을 풍요롭게 — Run big. Keep your memory abundant.**

OpenAI-compatible local server. Pick the files you need, drop them in a folder,
run one of the two `.exe` files. The model loads on an 8GB laptop GPU; the
operating point is chosen automatically in memory.

This repository is **not a model release**.
The internal mechanism is **not disclosed**.

## Speed (measured, RTX 4060 Laptop 8GB, 245-token steady-state)

| profile | speed | VRAM | when to pick |
|---|---|---|---|
| **single** (octagon) | ~34.5 tok/s | ~7 GB (tight) | maximum speed |
| **twin** (wireframe) | ~28.5 tok/s | ~3.7 GB (headroom) | stability under load |

Twin nearly halves VRAM pressure for ~17% less speed — far less likely to OOM
during longer or heavier runs. Same model, different operating point.

## How does it work?

Not explained here. The mechanism is covered by patent-filed technology
(application filed, KR). This release only demonstrates **that it works and
stays stable** — it does not disclose **how**.

## Download — pick 4 files (5 if you want both profiles)

| file | required? | size |
|---|---|---|
| `Qwen3.6-35B-A3B-Q4_K_M.gguf` | yes (the model) | ~20 GB |
| `cublas64_13.dll` | yes (GPU runtime) | 49 MB |
| `cublasLt64_13.dll` | yes (GPU runtime) | 435 MB |
| `pungyo-server-single.exe` | pick at least one | 246 MB |
| `pungyo-server-twin.exe` | pick at least one | 246 MB |

Put them all in the **same folder**. That's the install.

## Run (3 steps)

1. **Open PowerShell in the folder** where you put the files.
2. **Start the server** — single (fast) or twin (stable):

```powershell
# single profile (max speed)
.\pungyo-server-single.exe -m .\Qwen3.6-35B-A3B-Q4_K_M.gguf --port 8080 --host 127.0.0.1 -c 4096

# OR twin profile (stable)
.\pungyo-server-twin.exe   -m .\Qwen3.6-35B-A3B-Q4_K_M.gguf --port 8080 --host 127.0.0.1 -c 4096
```

3. **Use it.** Wait ~30-60 seconds for the model to load, then:
   - **Browser**: open `http://localhost:8080` — built-in chat UI is ready
   - **OpenAI-compatible clients** (Cursor, Continue, ChatBox, Open WebUI, Jan, LangChain, etc.): set base URL to `http://localhost:8080/v1`
   - **API**: `POST http://localhost:8080/v1/chat/completions` (OpenAI schema)

Stop with `Ctrl+C` in the server window.

## Requirements

- Windows 10/11
- NVIDIA RTX-class 8GB VRAM GPU (or larger), recent NVIDIA driver
- 32 GB system memory recommended
- ~21 GB free disk for the files

## Security

The example uses `--host 127.0.0.1` — the server is **reachable only from your
own PC**. To allow other machines on your LAN to use it, change to
`--host 0.0.0.0` and add `--api-key YOUR_KEY` (and ideally place a TLS reverse
proxy like Caddy in front). Never expose to the public internet without auth +
TLS.

## Not Included

- Qwen training data
- internal mechanism / operating-point logic (source)
- private validation traces

## License

- Pungyo execution binaries: see `LICENSE-PUNGYO`.
- Built on llama.cpp / ik_llama.cpp (MIT): see `LICENSE-LLAMACPP`.
- Qwen base model (`Qwen3.6-35B-A3B-Q4_K_M.gguf`) is redistributed under
  Apache-2.0: see `LICENSE-QWEN`.
- License scope separation: see `NOTICE.md`.

## Patent Notice

Pungyo relates to patent-filed technology by Myeong Jun Jo
(application filed, KR). This release is an observable public verification
artifact, **not** an internal implementation disclosure. Commercial or patent
licensing inquiries: koing754@gmail.com