Instructions to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use majentik/gemma-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/gemma-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf majentik/gemma-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

LM Studio
Jan

vLLM

How to use majentik/gemma-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-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-4-31B-it-RotorQuant-GGUF-Q4_K_M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Ollama
How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Ollama:
```
ollama run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M
```

Lemonade

How to use majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M-Q4_K_M

List all available models

lemonade list

Atomic Chat

majentik commited on Jul 9

Commit

50287a7

verified ·

1 Parent(s): cf39760

docs: warn that the turboquant fork predates gemma4 support (reported in gemma-4-26B-A4B-RotorQuant#1)

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -14,6 +14,10 @@ library_name: gguf
 pipeline_tag: image-text-to-text
 ---
 # gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M
 GGUF Q4_K_M weight-quantized variant of [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it) optimised for use with **RotorQuant** KV cache compression via a dedicated llama.cpp fork.

 pipeline_tag: image-text-to-text
 ---
+> [!WARNING]
+> **Fork compatibility (2026-07-07):** the `llama-cpp-turboquant` fork is currently based on a llama.cpp revision that **predates `gemma4` architecture support** — it fails with `unknown model architecture: 'gemma4'` and cannot run this model at all. Until the fork rebases, use **mainline llama.cpp** (which loads this GGUF fine with standard KV-cache types); the RotorQuant/TurboQuant KV-cache options are not usable with gemma-4 yet.
+<!-- gemma4-fork-note -->
 # gemma-4-31B-it-RotorQuant-GGUF-Q4_K_M
 GGUF Q4_K_M weight-quantized variant of [google/gemma-4-31B-it](https://huggingface.co/google/gemma-4-31B-it) optimised for use with **RotorQuant** KV cache compression via a dedicated llama.cpp fork.