Instructions to use daolsoft/geulbom-qwen3.5-4b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use daolsoft/geulbom-qwen3.5-4b-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Use Docker

docker model run hf.co/daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use daolsoft/geulbom-qwen3.5-4b-gguf with Ollama:
```
ollama run hf.co/daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
```
Unsloth Desktop

How to use daolsoft/geulbom-qwen3.5-4b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use daolsoft/geulbom-qwen3.5-4b-gguf with Docker Model Runner:
```
docker model run hf.co/daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M
```

Lemonade

How to use daolsoft/geulbom-qwen3.5-4b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Run and chat with the model

lemonade run user.geulbom-qwen3.5-4b-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use daolsoft/geulbom-qwen3.5-4b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use daolsoft/geulbom-qwen3.5-4b-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "daolsoft/geulbom-qwen3.5-4b-gguf:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Geulbom Qwen3.5 4B Q4_K_M

This is Daolsoft's reproducible GGUF conversion of the official Qwen/Qwen3.5-4B weights for the local, text-only AI features planned for Geulbom. It is not an official Qwen release and does not include a multimodal projector.

Reproducibility

Item	Value
Source revision	`851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`
llama.cpp release	`b10276`
llama.cpp revision	`6ea215d171fd31df943bf1ac8227129f2b963160`
Quantization	`Q4_K_M`
File	`qwen3.5-4b-q4_k_m.gguf`
Size	`2,783,446,688` bytes
SHA-256	`1e7a30ab183568d76c114323b8ae082f153a8913e391ed801f429b3bb4222339`

The conversion runs in the pinned Docker environment in the Geulbom repository:

docker compose build ai-model-build
docker compose run --rm ai-model-build
docker compose run --rm --entrypoint bash ai-model-build /workspace/build/ai/smoke-test-model.sh

The smoke test loads the generated file with the same pinned llama.cpp release on CPU and verifies a Korean chat completion. Product release still requires Geulbom's full Korean document quality, Windows runtime, memory, cancellation, and repeated-stability test gates.

License

The source model is provided under Apache License 2.0. Review the official source repository's license and model card before redistribution or use.

Downloads last month: 8

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for daolsoft/geulbom-qwen3.5-4b-gguf

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Quantized

(409)

this model