Instructions to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M",
	filename="gemma-4-12B-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M 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 majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M: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 majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M: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 majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M

Ollama
How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with Ollama:
```
ollama run hf.co/majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
```

Unsloth Studio

How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M 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 majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M 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 majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M to start chatting

Atomic Chat new
Docker Model Runner
How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M
```

Lemonade

How to use majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-TurboQuant-GGUF-Q4_K_M-Q4_K_M

List all available models

lemonade list

majentik commited on 2 days ago

Commit

f8180c6

verified ·

1 Parent(s): 945cf0e

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

Browse files

Files changed (1) hide show

README.md +8 -1

README.md CHANGED Viewed

@@ -13,6 +13,14 @@ tags:
   - turboquant
 ---
 # gemma-4-12B — TurboQuant GGUF Q4_K_M
 [`google/gemma-4-12B`](https://huggingface.co/google/gemma-4-12B) @ `023679ed352de9bb66cc873c9009ce3482585c08` quantized pack, published as `majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M`.
@@ -32,4 +40,3 @@ Released under the **TurboQuant** line. RotorQuant and TurboQuant are this proje
 ## License
 Governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). See the upstream repo for the full license text.

   - turboquant
 ---
+> [!TIP]
+> **KV-cache quantization (upstream, no fork needed):** llama.cpp/Ollama cover
+> this natively — `-ctk q8_0 -ctv q8_0` (~half KV memory, negligible quality
+> loss) or `-ctk q4_0 -ctv q4_0` (~quarter memory, small quality cost). In
+> Ollama: `OLLAMA_KV_CACHE_TYPE=q8_0` with `OLLAMA_FLASH_ATTENTION=1`.
 # gemma-4-12B — TurboQuant GGUF Q4_K_M
 [`google/gemma-4-12B`](https://huggingface.co/google/gemma-4-12B) @ `023679ed352de9bb66cc873c9009ce3482585c08` quantized pack, published as `majentik/gemma-4-12B-TurboQuant-GGUF-Q4_K_M`.
 ## License
 Governed by the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). See the upstream repo for the full license text.