Instructions to use JP-D/BlenderLLM-7.6B_GGUF 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 JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
Use Docker
docker model run hf.co/JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use JP-D/BlenderLLM-7.6B_GGUF with Ollama:
ollama run hf.co/JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
- Unsloth Studio
How to use JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for JP-D/BlenderLLM-7.6B_GGUF to start chatting
- Pi
How to use JP-D/BlenderLLM-7.6B_GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf JP-D/BlenderLLM-7.6B_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": "JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use JP-D/BlenderLLM-7.6B_GGUF with Docker Model Runner:
docker model run hf.co/JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
- Lemonade
How to use JP-D/BlenderLLM-7.6B_GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
Run and chat with the model
lemonade run user.BlenderLLM-7.6B_GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_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 JP-D/BlenderLLM-7.6B_GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use JP-D/BlenderLLM-7.6B_GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf JP-D/BlenderLLM-7.6B_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 "JP-D/BlenderLLM-7.6B_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"
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
BlenderLLM GGUF files
BlenderLLM convert to GGUF https://huggingface.co/FreedomIntelligence/BlenderLLM 3 files: FP16, Q4_K_M, and Q8.
Example prompt: "Let’s create a birthday cake with three layers. The bottom layer should be chocolate, the middle layer vanilla, and the top layer red velvet. Each layer should be separated by a thick layer of buttercream frosting. Add a decorative border of frosting around the top edge, and place colorful sprinkles all over the surface. Finally, add a Happy Birthday message on top."
Result (code):
import bpy
#Step 1: Clear the Scene
bpy.ops.object.select_all(action='DESELECT')
bpy.ops.object.select_by_type(type='MESH')
bpy.ops.object.delete()
#Define the colors
chocolate = bpy.data.materials.new(name="Chocolate")
chocolate.diffuse_color = (0.24, 0.15, 0.10, 1) # Chocolate color
vanilla = bpy.data.materials.new(name="Vanilla")
vanilla.diffuse_color = (1.0, 0.98, 0.90, 1) # Vanilla color
red_velvet = bpy.data.materials.new(name="Red Velvet")
red_velvet.diffuse_color = (0.8, 0.1, 0.1, 1) # Red velvet color
buttercream = bpy.data.materials.new(name="Buttercream")
buttercream.diffuse_color = (1.0, 0.95, 0.87, 1) # Buttercream color
#Step 2: Create the Bottom Layer (Chocolate)
bpy.ops.mesh.primitive_cylinder_add(radius=1.5, depth=0.5, location=(0, 0, 0))
bottom_layer = bpy.context.object
bottom_layer.name = "Bottom Layer"
bottom_layer.data.materials.append(chocolate)
#Step 3: Create the Middle Layer (Vanilla)
bpy.ops.mesh.primitive_cylinder_add(radius=1.2, depth=0.4, location=(0, 0, 0.5))
middle_layer = bpy.context.object
middle_layer.name = "Middle Layer"
middle_layer.data.materials.append(vanilla)
#Step 4: Create the Top Layer (Red Velvet)
by.ops.mesh.primitive_cylinder_add(radius=0.9, depth=0.3, location=(0, 0, 0.9))
top_layer = bpy.context.object
top_layer.name = "Top Layer"
top_layer.data.materials.append(red_velvet)
#Step 5: Create the Buttercream Frosting Layers
for i in range(2):
bpy.ops.mesh.primitive_cylinder_add(radius=1.5 - 0.3 * i, depth=0.1, location=(0, 0, 0.3 + 0.4 * i))
frosting_layer = bpy.context.object
frosting_layer.name = f"Frosting Layer {i + 1}"
frosting_layer.data.materials.append(buttercream)
#Step 6: Create the Decorative Border on Top
bpy.ops.mesh.primitive_torus_add(major_radius=0.9, minor_radius=0.1, location=(0, 0, 1.2))
decorative_border = bpy.context.object
decorative_border.name = "Decorative Border"
decorative_border.data.materials.append(buttercream)
#Step 7: Add Sprinkles (Simplified as small spheres for demonstration)
import random
colors = [(1, 0, 0, 1), (0, 1, 0, 1), (0, 0, 1, 1), (1, 1, 0, 1)]
for _ in range(50):
x = random.uniform(-0.9, 0.9)
y = random.uniform(-0.9, 0.9)
z = 1.2
bpy.ops.mesh.primitive_uv_sphere_add(radius=0.03, location=(x, y, z))
sprinkle = bpy.context.object
sprinkle.name = "Sprinkle"
color = bpy.data.materials.new(name="Sprinkle Color")
color.diffuse_color = random.choice(colors)
sprinkle.data.materials.append(color)
#Step 8: Add Text (Happy Birthday)
bpy.ops.object.text_add(location=(0, 0, 1.5))
text = bpy.context.object
text.name = "Happy Birthday Text"
text.data.body = "Happy Birthday"
text.data.align_x = 'CENTER'
text.data.size = 0.2
text.rotation_euler = (0, 0, math.pi/2)
text.location = (0, -1.5, 1.5)
#Convert text to mesh and apply material
bpy.ops.object.convert(target='MESH')
text_material = bpy.data.materials.new(name="Text Material")
text_material.diffuse_color = (1, 1, 1, 1) # White color for text
text.data.materials.append(text_material)
license: apache-2.0
- Downloads last month
- 64
4-bit
8-bit
16-bit
