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
- llama.cpp
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
- Pi
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:9931/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://127.0.0.1:9931/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://127.0.0.1:9931/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"
Update October 27 Q4 and Q8 checkpoints and Rome comparison
Browse filesRefresh both GGUF downloads, describe improved one-shot scene generation with unchanged parameters, and announce the October 28 FP16, dataset, and technical report release.
- .gitattributes +1 -0
- Qwen3.5-4B-3D-Coder-Q4_K_M.gguf +1 -1
- Qwen3.5-4B-3D-Coder-Q8_0.gguf +1 -1
- README.md +10 -14
- images/{dif.png → roma3.png} +2 -2
.gitattributes
CHANGED
|
@@ -46,3 +46,4 @@ images/dragonrider-aerie.png filter=lfs diff=lfs merge=lfs -text
|
|
| 46 |
Qwen3.5-4B-3D-Coder-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
Qwen3.5-4B-3D-Coder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
images/dif.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 46 |
Qwen3.5-4B-3D-Coder-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
Qwen3.5-4B-3D-Coder-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
images/dif.png filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
images/roma3.png filter=lfs diff=lfs merge=lfs -text
|
Qwen3.5-4B-3D-Coder-Q4_K_M.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2708804096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32c37c83d3ca055d30aefa679f1a1670d3e2eb889ee7cc805792d53f219cfae8
|
| 3 |
size 2708804096
|
Qwen3.5-4B-3D-Coder-Q8_0.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4482402816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c30b02629456aa2bc32e522de0f58eb1aafd8518a7634128fed67d1486fc2a9a
|
| 3 |
size 4482402816
|
README.md
CHANGED
|
@@ -20,29 +20,25 @@ This is an early preview of a 4B model I am still training, with a particular fo
|
|
| 20 |
|
| 21 |
This is an **independent fine-tune** by [CCORE](https://huggingface.co/ccore), based on [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B). **It is not an official Qwen release.**
|
| 22 |
|
| 23 |
-
##
|
| 24 |
|
| 25 |
-
Both **Q4_K_M** and **Q8_0**
|
| 26 |
|
| 27 |
-
|
| 28 |
-
- In my latest tests, this update appears to produce more successful **one-shot scene generations**.
|
| 29 |
|
| 30 |
-
|
| 31 |
|
| 32 |
-
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
-
|
| 39 |
|
| 40 |
-
|
| 41 |
|
| 42 |
-
|
| 43 |
-
- The **full set of quantized versions**.
|
| 44 |
-
- The **training dataset**, so others can use it to train or fine-tune other models.
|
| 45 |
-
- An **evaluation report with a variety of prompts**, showing how the model performed on them throughout training.
|
| 46 |
|
| 47 |
## Early examples
|
| 48 |
|
|
|
|
| 20 |
|
| 21 |
This is an **independent fine-tune** by [CCORE](https://huggingface.co/ccore), based on [Qwen/Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B). **It is not an official Qwen release.**
|
| 22 |
|
| 23 |
+
## October 27 checkpoint update
|
| 24 |
|
| 25 |
+
Both **Q4_K_M** and **Q8_0** now contain the updated October 27 checkpoint. If you downloaded an earlier version, please download the files again to get this update.
|
| 26 |
|
| 27 |
+
In my latest tests, **one-shot success has improved substantially**, along with **overall scene quality**. Some scenes can still require another attempt or a correction.
|
|
|
|
| 28 |
|
| 29 |
+
**Generation parameters remain unchanged** for both quantizations. Use the settings listed below. The earlier fix for the layer-related issue reported by some users is also included.
|
| 30 |
|
| 31 |
+
The comparison below shows the Rome scene across the **October 25, 26, and 27** previews.
|
| 32 |
|
| 33 |
+
[](https://huggingface.co/ccore/Qwen3.5-4B-3D-Coder/blob/main/images/roma3.png)
|
| 34 |
|
| 35 |
+
## Release plans — October 28, 2026
|
| 36 |
|
| 37 |
+
**Today, October 28, 2026**, I will release the **full FP16 model weights**, the **training dataset**, and a **technical report**.
|
| 38 |
|
| 39 |
+
The report will include a variety of prompts and their results across training checkpoints, showing how the model's behavior and scene quality evolved throughout training.
|
| 40 |
|
| 41 |
+
The **full set of quantized versions** is also planned.
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
## Early examples
|
| 44 |
|
images/{dif.png → roma3.png}
RENAMED
|
File without changes
|