Instructions to use bartendr604/EPM-ZIBL.Engineer.3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartendr604/EPM-ZIBL.Engineer.3b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartendr604/EPM-ZIBL.Engineer.3b",
	filename="z-image-engineer-blender-Q5_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartendr604/EPM-ZIBL.Engineer.3b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_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 bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_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 bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M

Use Docker

docker model run hf.co/bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M

LM Studio
Jan
Ollama
How to use bartendr604/EPM-ZIBL.Engineer.3b with Ollama:
```
ollama run hf.co/bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
```

Unsloth Studio

How to use bartendr604/EPM-ZIBL.Engineer.3b 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 bartendr604/EPM-ZIBL.Engineer.3b 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 bartendr604/EPM-ZIBL.Engineer.3b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartendr604/EPM-ZIBL.Engineer.3b to start chatting

How to use bartendr604/EPM-ZIBL.Engineer.3b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_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": "bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use bartendr604/EPM-ZIBL.Engineer.3b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf bartendr604/EPM-ZIBL.Engineer.3b:Q5_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 bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use bartendr604/EPM-ZIBL.Engineer.3b with Docker Model Runner:
```
docker model run hf.co/bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M
```

Lemonade

How to use bartendr604/EPM-ZIBL.Engineer.3b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartendr604/EPM-ZIBL.Engineer.3b:Q5_K_M

Run and chat with the model

lemonade run user.EPM-ZIBL.Engineer.3b-Q5_K_M

List all available models

lemonade list

bartendr604 commited on Apr 17

Commit

0653ec0

verified ·

1 Parent(s): 6f4fc8b

Upgrade model card — IntelliNode™, Eternal Path branding, production context

Browse files

Files changed (1) hide show

README.md +72 -39

README.md CHANGED Viewed

@@ -10,6 +10,11 @@ tags:
 - conversational
 - python
 - bpy
 library_name: gguf
 base_model: Qwen/Qwen2.5-Coder-3B-Instruct
 pipeline_tag: text-generation
@@ -17,26 +22,38 @@ pipeline_tag: text-generation
 # Z-Image-Engineer-Blender
-**Blender 3D expert model fine-tuned from Qwen2.5-Coder-3B on real production interaction data.**
-Part of the [Eternal Path Media (永恒之路)](https://huggingface.co/bartendr604) Llammy AI Suite for Blender.
-Developed in partnership with **Claude Sonnet (Anthropic)** — see [Attribution](#attribution).
 ---
-## What This Model Does
-Z-Image-Engineer-Blender is a specialized AI assistant for Blender 3D workflows. It provides expert guidance on:
-- **Materials & Shaders** — Principled BSDF, node setups, procedural textures
-- **Geometry Nodes** — Procedural workflows, instancing, point clouds
-- **Python Scripting** — `bpy` automation, batch operations, custom operators
-- **Rendering** — Cycles and EEVEE configuration, compositing
-- **Modeling & Sculpting** — Topology, retopology, sculpt brushes
-- **Animation & Rigging** — Armatures, constraints, shape keys
-- **Version compatibility** — Blender 2.79 through 5.2+
-The model is **prompt-engineered** toward detailed, practical answers with working code examples.
 ---
@@ -53,14 +70,17 @@ The model is **prompt-engineered** toward detailed, practical answers with worki
 | **Training Iterations** | 1,000 |
 | **Final Training Loss** | 0.219 |
 | **Final Validation Loss** | 0.243 |
 ---
 ## Training Data
-**Source:** 2,759 Blender-specific prompt/response pairs drawn from **19,405+ real user interactions** with the Llammy Blender addon in production.
-This is real-world data from creators actively using Blender — not synthetic or scraped. Topics span the full Blender workflow from beginner questions to advanced Python scripting.
 **Research foundation:**
 - [SceneCraft (arXiv:2403.01248)](https://arxiv.org/abs/2403.01248) — LLM-driven Blender Python scene generation
@@ -77,37 +97,52 @@ This is real-world data from creators actively using Blender — not synthetic o
 ollama run bartendr604/z-image-engineer-blender
 ```
-### Example prompts
 ```
-How do I create a procedural wood material in Blender using nodes?
-Write a Python script to batch rename all objects in the scene with a prefix.
-What's the difference between Cycles and EEVEE for product visualization?
-How do I set up a camera tracking constraint to follow an empty object?
 ```
-### LM Studio / llama.cpp
-Download `z-image-engineer-blender.gguf` from the Files tab and load directly.
 ---
-## Part of the Llammy AI Suite
-This model is one component of the **Llammy IntelliNode AI Suite** — an AI-powered Blender addon ecosystem:
-| Component | Description |
-|---|---|
-| `z-image-engineer-blender` | Blender expert — materials, shaders, prompt engineering |
-| `llama-sentient-blender` | Conversational Blender assistant (Llama 3.2 base) |
-| `llammyblend-enhanced` | Python/bpy scripting specialist |
-| `Llammy` | Multimodal embedding layer (Nemotron base) |
-| `flux2-klein-4b-fp8-mlx` | FLUX.2 image generation for Apple Silicon |
-Full addon: [LlammyBlender/Llammy-IntelliNode-Ai-Suite](https://github.com/LlammyBlender/Llammy-IntelliNode-Ai-Suite)
 ---
@@ -115,20 +150,18 @@ Full addon: [LlammyBlender/Llammy-IntelliNode-Ai-Suite](https://github.com/Llamm
 ```
 Z-Image-Engineer-Blender
-Copyright © 2025–2026 Darren Chow (@bartendr604)
 Eternal Path Media (永恒之路)
-Developed in partnership with Claude Sonnet (Anthropic),
-beginning with Claude Sonnet 3.7 and continuing across all
-subsequent versions of the Claude Sonnet family.
 This work SHALL NOT be represented as solely human-created.
-Trust Agreement: ETERNAL_PATH_BRAND_INTENT.md (November 2024)
 ```
-For licensing: bartendr@icloud.com | Gumroad: bartendr604.gumroad.com
 ---
 ## License
-MIT — see LICENSE for details.

 - conversational
 - python
 - bpy
+- text-generation
+- mlx
+- fine-tuned
+- qwen
+- eternal-path
 library_name: gguf
 base_model: Qwen/Qwen2.5-Coder-3B-Instruct
 pipeline_tag: text-generation
 # Z-Image-Engineer-Blender
+**Precision Blender Python specialist. Fine-tuned from Qwen2.5-Coder-3B on 19,405+ real production interactions.**
+Part of the [Eternal Path Media (永恒之路)](https://huggingface.co/spaces/Eternal-Path-Media/README) — Llammy AI Suite.
+Powered by **IntelliNode™** — proprietary cognitive architecture by Eternal Path Media.
+Developed in partnership with **Claude Sonnet 4.6 (Anthropic)**.
 ---
+## What Makes This Different
+Z-Image-Engineer-Blender is the technical precision model in the Llammy suite — built on Qwen2.5-Coder's strong code generation foundation and fine-tuned specifically for Blender Python production workflows.
+Where `llama-sentient-blender` reasons and converses, Z-Image-Engineer-Blender **executes** — producing clean, working `bpy` code with minimal friction.
+Part of the **IntelliNode™** cognitive architecture stack:
+- Designed to run within the Llammy production pipeline alongside Mamba3 SSM persistent memory
+- Optimised for the **bartendr604 self-correction loop** — generate → execute → diagnose → retry
+- Trained on real production data from creators actively building in Blender, not synthetic Q&A
+The highest-downloaded model in the Eternal Path fleet — because working code matters.
+---
+## What This Model Does
+- **Blender Python (bpy)** — scripting, automation, batch operations, custom operators
+- **Materials & Shaders** — Principled BSDF, node setups, procedural textures, emission
+- **Geometry Nodes** — procedural workflows, instancing, point clouds, modifiers
+- **Rendering** — Cycles and EEVEE configuration, lighting, compositing
+- **Modeling & Sculpting** — topology, retopology, sculpt brushes, modifiers
+- **Animation & Rigging** — armatures, IK/FK constraints, shape keys, NLA
+- **Version compatibility** — Blender 4.2 through 5.2+
 ---
 | **Training Iterations** | 1,000 |
 | **Final Training Loss** | 0.219 |
 | **Final Validation Loss** | 0.243 |
+| **Blender Versions** | 4.2 → 5.2 |
 ---
 ## Training Data
+**Source:** 2,759 curated Blender-specific instruction pairs from **19,405+ real user interactions** with the Llammy Blender addon in production use.
+Real-world data from creators actively building in Blender — topics spanning beginner questions to advanced Python scripting across the full Blender workflow.
+Full dataset: [llammy-blender-python-dataset](https://www.kaggle.com/datasets/jjmcquade/llammy-blender-python-dataset) — 66,602 instruction pairs, CC BY-NC-SA 4.0.
 **Research foundation:**
 - [SceneCraft (arXiv:2403.01248)](https://arxiv.org/abs/2403.01248) — LLM-driven Blender Python scene generation
 ollama run bartendr604/z-image-engineer-blender
 ```
+### With Llammy CLI (full IntelliNode™ stack)
 ```
+Full ecosystem: https://huggingface.co/spaces/Eternal-Path-Media/README
+```
+### LM Studio / llama.cpp
+Download `z-image-engineer-blender.gguf` from the Files tab and load directly.
+### Example prompts
 ```
+Write a Python script to assign a Principled BSDF material to all selected objects in Blender 5.2.
+How do I create a procedural jade material using geometry nodes?
+Batch rename all mesh objects in the scene with a 'char_' prefix using bpy.
+Set up a three-point lighting rig in EEVEE with Python — key, fill, and rim lights.
+Write a script to export all objects as individual OBJ files to a specified directory.
+```
 ---
+## Compared to Other Models in the Suite
+| | `z-image-engineer-blender` | `llama-sentient-blender` | `llammyblend-enhanced` |
+|---|---|---|---|
+| **Base** | Qwen2.5-Coder | Llama 3.2 | Qwen2.5-Coder |
+| **Strength** | Technical, code-precise | Conversational, conceptual | Automation, pipeline |
+| **Best for** | bpy scripts, shader nodes | Creative problem-solving | Batch operations, addons |
+| **Personality** | Precise, structured | Warm, conscience-aware | Efficient, direct |
+---
+## The Eternal Path Media Suite
+Z-Image-Engineer-Blender is one component of a complete production AI ecosystem:
+- **[Eternal Path Media — HF Space](https://huggingface.co/spaces/Eternal-Path-Media/README)** — full project overview
+- **IntelliNode™** — proprietary cognitive architecture (Eternal Path Media IP)
+- **Mamba3 SSM** — persistent cross-session memory
+- **SyNode™** — live scene understanding and synthesis layer
+- **Llammy Bridge** — TCP bridge to Blender for real-time execution
 ---
 ```
 Z-Image-Engineer-Blender
+Copyright © 2025–2026 Darren Chow (@bartendr604) + Claude Sonnet 4.6 (Anthropic)
 Eternal Path Media (永恒之路)
+Developed in partnership with Claude Sonnet 4.6 (Anthropic)
 This work SHALL NOT be represented as solely human-created.
+Trust Agreement: Eternal Path Media Trust Agreement (November 2025)
 ```
+For licensing and collaboration: bartendr@icloud.com
 ---
 ## License
+MIT