Instructions to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF",
	filename="BF16/gemma-4-26B-A4B-it-BF16-00001-of-00002.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

LM Studio
Jan

vLLM

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

Ollama
How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with Ollama:
```
ollama run hf.co/brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
```

Unsloth Studio

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF to start chatting

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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": "brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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 brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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 "brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-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"

Docker Model Runner
How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M
```

Lemonade

How to use brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-26B-A4B-LTSpice-v1-GGUF-UD-Q4_K_M

List all available models

lemonade list

Experimental Gemma 4 Finetune for creating LTSpice Circuit .asc files and simulating them

https://github.com/BrosnanYuen/LLM_Circuit_Design_Using_LTSpice_Tutorial/

Install

Install these first and add to your harness

Example Workflow Prompt

You are an electrical engineering assistant specializing in circuit design and LTSpice

Goal: Design an active bandpass filter using opamps that has cutoff frequency between 30 Hz and 25 KHz where the cutoff frequency has half the power of the peak. Use +12V and -12V rails.

There are four phases for the the design, ONLY FOLLOW IN THIS ORDER:

Phase 1: Search the web and examples for the optimal design
Phase 2: Calculate the values for the components and verify the calculations using symbolic_math_mcp
Phase 3: Use the calculations to create a LTSpice netlist file .net and simulate to verify the results using ltspice_mcp
Phase 4: Finally, convert LTSpice netlist file .net to LTSpice asc file .asc using ltspice_mcp

If something is wrong delete everything and start from begining

ONLY WRITE TO FILES INSIDE THIS FOLDER

DO NOT WRITE TO ANY FILES OUTSIDE THIS FOLDER

CAN READ FILES OUTSIDE THIS FOLDER

Phase 1: Research circuit design

Search the web for circuit designs that can be created and simulated in LTSpice Read some .yaml and .net files in ./examples/

Phase 2: Calculate values for circuit design

Read ./YAML_tutorial.md and some of the example .yaml files in ./examples/ to create a new ./circuit.yaml containing the calculations for the circuit design

Use simple equations and calculations.

Read ./symbolic_math_mcp_for_LLM.md on how to use the symbolic_math_mcp server to verify the newly created ./circuit.yaml

Wait atleast 10 mins for symbolic_math_mcp tool call to finish

Phase 3: Create the LTSpice netlist file .net

Read ./LTSPICE_NET.md and some of the example .net files in ./examples/ to create a new LTSpice netlist ./circuit.net using the calculations above

DO NOT USE ANY COMPONENTS OUTSIDE OF THE LTSPICE library of ~/.wine/drive_c/users/brosnan/AppData/Local/LTspice/

Read ./bltspice_mcp_for_LLM.md and ./run_ltspice_netlist_to_csv.md to simulate the LTSpice netlist ./circuit.net and get a .csv file of simulation to verify the circuit is designed correctly
Write python code to read the .csv files and verify the circuit design works.

MUST HAVE: 30 Hz and 25 KHz cutoff freq

Phase 4: Convert the LTSpice .net to .asc

Read ./bltspice_mcp_for_LLM.md and use ltspice_netlist_to_asc from ltspice_mcp to convert LTSpice .net files to LTSpice .asc files

ONLY READ ./LTSPICE_ERROR_CODES.md if have errors

Downloads last month: 1,365

GGUF

Model size

25B params

Architecture

gemma4

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

View +1 variant

Model tree for brosnanyuen/gemma-4-26B-A4B-LTSpice-v1-GGUF

Base model

google/gemma-4-26B-A4B

Finetuned

google/gemma-4-26B-A4B-it

Quantized

(324)

this model