Instructions to use ccore/Qwen3.5-4B-3D-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ccore/Qwen3.5-4B-3D-Coder 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 ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Use Docker

docker model run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use ccore/Qwen3.5-4B-3D-Coder with Ollama:
```
ollama run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
```
Unsloth Desktop

How to use ccore/Qwen3.5-4B-3D-Coder with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder: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": "ccore/Qwen3.5-4B-3D-Coder:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ccore/Qwen3.5-4B-3D-Coder with Docker Model Runner:
```
docker model run hf.co/ccore/Qwen3.5-4B-3D-Coder:Q4_K_M
```

Lemonade

How to use ccore/Qwen3.5-4B-3D-Coder with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-3D-Coder-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ccore/Qwen3.5-4B-3D-Coder with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder: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 ccore/Qwen3.5-4B-3D-Coder:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ccore/Qwen3.5-4B-3D-Coder with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ccore/Qwen3.5-4B-3D-Coder: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 "ccore/Qwen3.5-4B-3D-Coder: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"

Image analisys support

by TOPG-V - opened 1 day ago

Discussion

TOPG-V

1 day ago

It would be cool to add vision capabilities to the model so that it can analyze voxel images

Like this one. Also I really like your work ! Keep going!

ccore

Owner 1 day ago

it actually already supports vision! i only uploaded the language weights because i assumed people who wanted vision would just add the original vision projector themselves. this also keeps the download smaller for those who only need text and code generation.

that's how i use it locally, and the vision components are loaded automatically, so i didn't really think about it haha

but no problem, i can also upload a version with the vision components included to make things easier for everyone!

TOPG-V

1 day ago

Thanks cuz most apps like unsloth and PocketPal(for phones) only see it as a vision model if it's set to be so and have no option to add vision compatibility layer ! Please include the both non vision and vision tho* 🙏

TOPG-V

1 day ago

•

edited 1 day ago

Also thanks for running the image voxel for me also (it wasn't my ambition tho cuz I just found a random one to explain what I meant XD)😅 Thanks anyway!

ccore

Owner 1 day ago

Thanks cuz most apps like unsloth and PocketPal(for phones) only see it as a vision model if it's set to be so and have no option to add vision compatibility layer ! Please include the both non vision and vision tho* 🙏

thanks, that makes sense!

i'm actually updating that right now and also generating a few example files so people can see how both versions work in practice.

i'll try to include both the non vision and vision versions to make things easier depending on the app people want to use. thanks for the suggestion!

ccore

Owner 1 day ago

btw, i've got a little surprise for you guys coming this weekend haha. i think you're going to like it!

TOPG-V

1 day ago

Thanks for your time! I really appreciate your work for the community with your amazing , mind-blowing good fine-tune 🥰 If I have any more suggestions in the future, I'll tell you!

TOPG-V

1 day ago

•

edited 1 day ago

Also,there was no need to write me up as the image contributor, but I'm happy to help improve your work any way I can 🧡

TOPG-V

about 9 hours ago

•

edited about 9 hours ago

Hey id. also have some issues id like to tell about: Even on Fp16KV and the Q8 models after i asked it to generate a entire city of a voxel it did it , but fell into java animation loops and main core loops, which i think is worth investigating , because from what i have tested so far its good on small voxels but when it comes to big ones it starts to fail or loop :)Im sure the prompt was very detailed though*

I will continue running tests on different enviorments, though i cant promise what time it will take because im running ram inference , because i forgot to buy a egpu and well now my 3070 is on my shelve and im waiting to get myself a egpu :)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment