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"

Thanks + MTP head added

#13

by SuperLogic - opened 6 days ago

Discussion

SuperLogic

6 days ago

•

edited 6 days ago

Hugging Face CLI

Thanks for sharing this model — really nice work on the 3D side.

The only issue we hit is speed: the released weights dropped the MTP head (config declares mtp_num_hidden_layers: 1, but the 15 mtp.* tensors are not in the safetensors), so it runs at the plain baseline.

We grafted the MTP head back from the base Qwen3.5-4B and packed a ready-to-run GGUF:

https://huggingface.co/SuperLogic/Qwen3.5-4B-3D-Coder-MTP-GGUF

Same output quality, 47.9 -> 90.7 tok/s on a single RTX 4060 Laptop. In LM Studio just tick MTP on and set Prediction = 1.

Hope it's useful.

SuperLogic changed discussion title from MTP head added: 47.9 -> 90.7 tok/s (ready-to-run Q8_0 GGUF) to Thanks + MTP head added (47.9 -> 90.7 tok/s) 6 days ago

SuperLogic changed discussion title from Thanks + MTP head added (47.9 -> 90.7 tok/s) to Thanks + MTP head added 6 days ago

checksout

6 days ago

Ahhhh I didnt know there was an MTP version! Your model is CRAZY amounts of fun and now it goes BRRRRRR! Thanks for all the hard work you've put into this model!

maternion

6 days ago

Thanks for sharing this model — really nice work on the 3D side.

The only issue we hit is speed: the released weights dropped the MTP head (config declares mtp_num_hidden_layers: 1, but the 15 mtp.* tensors are not in the safetensors), so it runs at the plain baseline.

We grafted the MTP head back from the base Qwen3.5-4B and packed a ready-to-run GGUF:

https://huggingface.co/SuperLogic/Qwen3.5-4B-3D-Coder-MTP-GGUF

Same output quality, 47.9 -> 90.7 tok/s on a single RTX 4060 Laptop. In LM Studio just tick MTP on and set Prediction = 1.

Hope it's useful.

Please add your model under the 3d model as its base model. That way it will be easier to find.

ccore

Owner 6 days ago

Thanks for sharing this model — really nice work on the 3D side.

The only issue we hit is speed: the released weights dropped the MTP head (config declares mtp_num_hidden_layers: 1, but the 15 mtp.* tensors are not in the safetensors), so it runs at the plain baseline.

We grafted the MTP head back from the base Qwen3.5-4B and packed a ready-to-run GGUF:

https://huggingface.co/SuperLogic/Qwen3.5-4B-3D-Coder-MTP-GGUF

Same output quality, 47.9 -> 90.7 tok/s on a single RTX 4060 Laptop. In LM Studio just tick MTP on and set Prediction = 1.

Hope it's useful.

thanks a lot for doing this! really appreciate it!

i had previously fixed the mtp-related issue in my release, so it's really interesting to see you add the mtp head back from the base model and get almost twice the generation speed!

thanks for sharing your work with the community!

ccore changed discussion status to closed 6 days ago

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