GGUF
English
chain-of-thought
cot-reasoning
step-by-step-reasoning
systematic-analysis
problem-decomposition
structured-output
structured-thinking
reasoning-model
gmsh-scripting
mesh-generation
computational-geometry
finite-element-analysis
engineering-simulation
cad-mesh-automation
geometric-modeling
numerical-methods
engineering-research
computational-engineering
mesh-optimization
geometry-processing
simulation-preprocessing
technical-code-generation
domain-specific-reasoning
engineering-assistant
8b-parameters
dense-decoder-model
open-source-model
GMeshNet-OSS-8B
GMeshNet-OSS
GMeshNet
GmshNet-OSS-8B
GmshNet-OSS
GmshNet
conversational
Instructions to use Callimesh/GMeshNet-OSS-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Callimesh/GMeshNet-OSS-8B-GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Callimesh/GMeshNet-OSS-8B-GGUF", filename="GMeshNet-OSS-8B-IQ3_XS.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Callimesh/GMeshNet-OSS-8B-GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Callimesh/GMeshNet-OSS-8B-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 Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Callimesh/GMeshNet-OSS-8B-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 Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Callimesh/GMeshNet-OSS-8B-GGUF with Ollama:
ollama run hf.co/Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
- Unsloth Studio new
How to use Callimesh/GMeshNet-OSS-8B-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 Callimesh/GMeshNet-OSS-8B-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 Callimesh/GMeshNet-OSS-8B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Callimesh/GMeshNet-OSS-8B-GGUF to start chatting
- Pi new
How to use Callimesh/GMeshNet-OSS-8B-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Callimesh/GMeshNet-OSS-8B-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": "Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use Callimesh/GMeshNet-OSS-8B-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf Callimesh/GMeshNet-OSS-8B-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 Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
Run Hermes
hermes
- Docker Model Runner
How to use Callimesh/GMeshNet-OSS-8B-GGUF with Docker Model Runner:
docker model run hf.co/Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
- Lemonade
How to use Callimesh/GMeshNet-OSS-8B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Callimesh/GMeshNet-OSS-8B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.GMeshNet-OSS-8B-GGUF-Q4_K_M
List all available models
lemonade list
llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)GMeshNet-OSS-8B
GMeshNet-OSS-8B is an open-source, dense, decoder-only 8B parameter large language model optimized for chain-of-thought reasoning, designed to produce structured analyses and generate robust Gmsh meshing scripts.
Quickstart
Install Dependencies
pip install llama-cpp-python
Run Inference
from llama_cpp import Llama
# Input your prompt here
USER_INPUT = """
Generate a GMSH script to create a 2D rectangular mesh with a circular hole at the center, applying finer mesh refinement near the hole and coarser mesh at the boundaries.
"""
def load_model(model_path):
llm = Llama(
model_path=model_path,
n_ctx=10000,
n_gpu_layers=27,
verbose=False
)
return llm
def generate_response(llm, user_input):
formatted_input = f"<gmsh_instruction>{user_input.strip()}</gmsh_instruction>"
messages = [{"role": "user", "content": formatted_input}]
response = llm.create_chat_completion(
messages=messages,
max_tokens=2000,
temperature=0.7,
stream=False
)
return response['choices'][0]['message']['content']
def run_inference():
model_path = "./" # Path to your model weights
llm = load_model(model_path)
result = generate_response(llm, USER_INPUT)
print(result)
if __name__ == "__main__":
run_inference()
Example Output
<think>
I need to analyze this meshing task step by step to create an effective GMSH script.
1. Geometry Requirements:
- Main domain: Rectangular plate (let's assume 10x10 units)
- Internal feature: Circular hole at center (radius 1 unit)
- Mesh requirements: Finer elements near hole, coarser elements at boundaries
2. Meshing Approach:
- Unstructured triangular mesh for flexibility around complex features
- Size field to control element gradation from fine near hole to coarse at boundaries
- Boundary layer not strictly necessary but could be added if flow simulation is intended
3. Construction Steps:
- Define rectangle points (4 corners)
- Define circle points (center + 4 quadrant points)
- Create line loops for both shapes
- Create surface with hole using Plane Surface command
- Set up size field for gradation control
- Generate mesh
</think>
<response>
1. High-level overview:
- Create 10x10 rectangular domain centered at origin
- Add circular hole of radius 1 at center
- Use distance-based size field to refine mesh near hole
- Generate unstructured triangular mesh with smooth gradation
2. Step-by-step instructions:
a) Create rectangle points (4 corners)
b) Create circle points (center + 4 quadrants)
c) Connect points with lines/arcs
d) Form line loops
e) Create surface with hole
f) Set up size field
g) Generate mesh
3. Complete GMSH script:
```
// Rectangle with circular hole - graded mesh example
// Geometry parameters
rect_size = 5; // Half-width/height of rectangle
hole_radius = 1; // Radius of central hole
// Points for rectangle
Point(1) = {-rect_size, -rect_size, 0};
Point(2) = {rect_size, -rect_size, 0};
Point(3) = {rect_size, rect_size, 0};
Point(4) = {-rect_size, rect_size, 0};
// Points for circle (center + 4 quadrants)
Point(5) = {0, 0, 0}; // Center
Point(6) = {hole_radius, 0, 0};
Point(7) = {0, hole_radius, 0};
Point(8) = {-hole_radius, 0, 0};
Point(9) = {0, -hole_radius, 0};
// Lines for rectangle
Line(1) = {1, 2};
Line(2) = {2, 3};
Line(3) = {3, 4};
Line(4) = {4, 1};
// Circle arcs
Circle(5) = {6, 5, 7};
Circle(6) = {7, 5, 8};
Circle(7) = {8, 5, 9};
Circle(8) = {9, 5, 6};
// Line loops
Line Loop(1) = {1, 2, 3, 4}; // Outer rectangle
Line Loop(2) = {5, 6, 7, 8}; // Inner circle
// Surface with hole
Plane Surface(1) = {1, 2};
// Mesh size control - fine near hole, coarse at boundaries
Field[1] = Distance;
Field[1].NodesList = {5}; // Measure distance from center point
Field[1].NNodesByEdge = 100;
Field[2] = Threshold;
Field[2].InField = 1;
Field[2].SizeMin = 0.05; // Fine mesh near hole
Field[2].SizeMax = 0.5; // Coarse mesh far away
Field[2].DistMin = hole_radius;
Field[2].DistMax = 2*hole_radius;
Background Field = 2;
// Physical groups for boundaries
Physical Curve("OuterBoundary", 1) = {1, 2, 3, 4};
Physical Curve("InnerBoundary", 2) = {5, 6, 7, 8};
Physical Surface("Domain", 1) = {1};
// Mesh settings
Mesh.Algorithm = 6; // Frontal-Delaunay
Mesh.Smoothing = 5;
Mesh.CharacteristicLengthExtendFromBoundary = 1;
// Generate 2D mesh
Mesh 2;
```
4. Implementation Notes:
- To run: Open in GMSH โ Mesh โ 2D
- Adjust parameters as needed:
* rect_size: Change rectangle dimensions
* hole_radius: Modify hole size
* SizeMin/SizeMax: Control mesh density
* DistMin/DistMax: Control refinement region extent
- For structured mesh option, add Transfinite lines/surface commands
- Visualize geometry first (Geometry tab) before meshing
- Common errors to avoid:
* Missing line loops
* Incorrect point references in curves
* Overlapping or intersecting geometries
</response>
- Downloads last month
- 75
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Callimesh/GMeshNet-OSS-8B-GGUF", filename="", )