Instructions to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("meshllm/gemma-4-e4b-it-parity-q8_0-gguf", dtype="auto")

llama-cpp-python

How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="meshllm/gemma-4-e4b-it-parity-q8_0-gguf",
	filename="gemma-4-e4b-it-q8_0.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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
llama-cli -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

Use Docker

docker model run hf.co/meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

LM Studio
Jan
Ollama
How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with Ollama:
```
ollama run hf.co/meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
```

Unsloth Studio

How to use meshllm/gemma-4-e4b-it-parity-q8_0-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 meshllm/gemma-4-e4b-it-parity-q8_0-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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for meshllm/gemma-4-e4b-it-parity-q8_0-gguf to start chatting

How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

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": "meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use meshllm/gemma-4-e4b-it-parity-q8_0-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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

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 meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with Docker Model Runner:
```
docker model run hf.co/meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0
```

Lemonade

How to use meshllm/gemma-4-e4b-it-parity-q8_0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull meshllm/gemma-4-e4b-it-parity-q8_0-gguf:Q8_0

Run and chat with the model

lemonade run user.gemma-4-e4b-it-parity-q8_0-gguf-Q8_0

List all available models

lemonade list

Gemma 4 E4B Instruct Parity GGUF (Q8_0)

This repository contains the canonical GGUF side of the meshllm Gemma 4 parity pair.

Source checkpoint: google/gemma-4-E4B-it
Conversion path: original checkpoint -> GGUF -> Q8_0
Intended use: backend parity testing against the matching MLX artifact

This artifact is not meant to be a general "best available" Gemma 4 release. It exists so that GGUF and MLX can be compared from the same original model lineage with minimal third-party conversion noise.

Canonical pair:

GGUF: meshllm/gemma-4-e4b-it-parity-q8_0-gguf
MLX: meshllm/gemma-4-e4b-it-parity-8bit-mlx

Latest trusted exact result:

Backend	Model	Exact
GGUF	`gemma-4-e4b-it-q8_0.gguf`	`PASS`
MLX	`meshllm/gemma-4-e4b-it-parity-8bit-mlx`	`PASS`

Prompt comparison from local same-origin validation:

Prompt	GGUF Q8_0	MLX 8bit
`primary`	`blue`	`blue`
`alt-green`	`green`	`green`
`alt-red`	`red`	`red`
`capital-france`	`Paris`	`Paris`
`primary-colors`	`red, green, blue`	`red, green, blue`
`two-plus-two`	`4`	`4`
`largest-planet`	`Jupiter`	`Jupiter`
`breathing-gas`	`Oxygen`	`Oxygen`
`opposite-hot`	`Cold`	`Cold`
`banana-color`	`Yellow`	`Yellow`
`after-monday`	`Tuesday`	`Tuesday`

Downloads last month: 114

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for meshllm/gemma-4-e4b-it-parity-q8_0-gguf

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(231)

this model