Instructions to use demirzeyn/gemma3-forensics-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf demirzeyn/gemma3-forensics-GGUF:Q4_K_M

Use Docker

docker model run hf.co/demirzeyn/gemma3-forensics-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use demirzeyn/gemma3-forensics-GGUF with Ollama:
```
ollama run hf.co/demirzeyn/gemma3-forensics-GGUF:Q4_K_M
```

Unsloth Studio

How to use demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-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 demirzeyn/gemma3-forensics-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for demirzeyn/gemma3-forensics-GGUF to start chatting

Docker Model Runner
How to use demirzeyn/gemma3-forensics-GGUF with Docker Model Runner:
```
docker model run hf.co/demirzeyn/gemma3-forensics-GGUF:Q4_K_M
```

Lemonade

How to use demirzeyn/gemma3-forensics-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull demirzeyn/gemma3-forensics-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma3-forensics-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

demirzeyn commited on Apr 3

Commit

5adae32

verified ·

1 Parent(s): 1c04745

Add README

Browse files

Files changed (1) hide show

README.md +27 -0

README.md ADDED Viewed

	@@ -0,0 +1,27 @@

+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+---
+# gemma3-forensics-GGUF : GGUF
+This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+**Example usage**:
+- For text only LLMs:    `llama-cli -hf demirzeyn/gemma3-forensics-GGUF --jinja`
+- For multimodal models: `llama-mtmd-cli -hf demirzeyn/gemma3-forensics-GGUF --jinja`
+## Available Model files:
+- `gemma-3-1b-it.Q8_0.gguf`
+- `gemma-3-1b-it.Q4_K_M.gguf`
+## Ollama
+An Ollama Modelfile is included for easy deployment.
+## Note
+The model's BOS token behavior was adjusted for GGUF compatibility.
+This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)