Instructions to use DKTechin/local-llm-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 DKTechin/local-llm-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 DKTechin/local-llm-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DKTechin/local-llm-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 DKTechin/local-llm-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf DKTechin/local-llm-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 DKTechin/local-llm-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf DKTechin/local-llm-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 DKTechin/local-llm-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf DKTechin/local-llm-gguf:Q4_K_M

Use Docker

docker model run hf.co/DKTechin/local-llm-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use DKTechin/local-llm-gguf with Ollama:
```
ollama run hf.co/DKTechin/local-llm-gguf:Q4_K_M
```

Unsloth Studio

How to use DKTechin/local-llm-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DKTechin/local-llm-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for DKTechin/local-llm-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DKTechin/local-llm-gguf to start chatting

How to use DKTechin/local-llm-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DKTechin/local-llm-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DKTechin/local-llm-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use DKTechin/local-llm-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf DKTechin/local-llm-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 "DKTechin/local-llm-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"

Docker Model Runner
How to use DKTechin/local-llm-gguf with Docker Model Runner:
```
docker model run hf.co/DKTechin/local-llm-gguf:Q4_K_M
```

Lemonade

How to use DKTechin/local-llm-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull DKTechin/local-llm-gguf:Q4_K_M

Run and chat with the model

lemonade run user.local-llm-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use DKTechin/local-llm-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 DKTechin/local-llm-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 DKTechin/local-llm-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

local-llm-gguf — weight mirror

Files loaded by the on-device assistant of the KakaoWork desktop app, re-uploaded byte-identical from their upstream repositories. The app needs a location whose bytes do not move under it; this repository is that location. Nothing here is our own work.

Every upstream repository below is Apache-2.0 and ungated. Please prefer the upstream repositories — they hold the other quantizations and the model cards.

Files

File	Size	Upstream
`gemma-4-E2B_q4_0-it.gguf`	3.35 GB	google/gemma-4-E2B-it-qat-q4_0-gguf
`gemma-4-E4B_q4_0-it.gguf`	5.15 GB	google/gemma-4-E4B-it-qat-q4_0-gguf
`Qwen3.5-2B-Q4_K_M.gguf`	1.28 GB	unsloth/Qwen3.5-2B-GGUF
`Qwen3.5-4B-Q4_K_M.gguf`	2.74 GB	unsloth/Qwen3.5-4B-GGUF

kanana-2-3b-instruct-Q4_K_M.gguf is not here — it is our own conversion and lives in DKTechin/kanana.

Credits

The models are by their creators — Google (Gemma 4) and Alibaba/Qwen (Qwen3.5) — and the GGUF builds are by the repositories listed above. Their licenses and terms of use apply to these copies unchanged.

If you maintain one of the upstream repositories and would rather this mirror not exist, open a discussion and we will remove it.

Downloads last month: 599

GGUF

Model size

5B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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