Instructions to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 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 tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3: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 tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3: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 tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

Use Docker

docker model run hf.co/tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

LM Studio
Jan

vLLM

How to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

Ollama
How to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 with Ollama:
```
ollama run hf.co/tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 with Docker Model Runner:
```
docker model run hf.co/tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M
```

Lemonade

How to use tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3-Q4_K_M

List all available models

lemonade list

Atomic Chat

Gemma-4 12B Coder — SFT v3 (deprecated)

⚠️ Deprecated — do not use for new work. intermediate SFT iteration superseded by v5.

Replaced by tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-GGUF.

gemma-4 12B coder for local, agentic tool use — GGUF quantizations for llama.cpp / Ollama.

Run it: llama-server -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M --jinja (full commands below).

At a glance


Type	GGUF quantizations · llama.cpp / Ollama
Techniques	—
Tool-calling	native `--jinja`
Status	⚠️ Deprecated → `tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v5-GGUF`
Use	`llama-server -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M --jinja`

Use it

# llama.cpp (server) — tool-calling needs the recovery shim, see below
llama-server -hf tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M --jinja --ctx-size 16384

# Ollama
ollama run hf.co/tpls/gemma-4-12B-coder-fable5-composer2.5-v1-sft-v3:Q4_K_M

Files

Sizes and a one-click loader are in the file browser / Quantizations widget above; the note says which quant to reach for.

Quant	Notes
`Q4_K_M`	good default — fits 12 GB VRAM, best size/quality balance

Intended use & limitations

Built for code generation and agentic tool use; serve locally via llama.cpp / Ollama, or use as a base to fine-tune / merge / quantize. Outputs can be wrong or fabricated — validate tool arguments before executing, and keep a human in the loop for anything consequential.