Instructions to use finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M",
	filename="gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf finis-est/gemma-4-31b-larkspur-v0.5-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-server -hf finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf finis-est/gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf finis-est/gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M

Use Docker

docker model run hf.co/finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M

LM Studio
Jan
Ollama
How to use finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with Ollama:
```
ollama run hf.co/finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
```

Unsloth Studio

How to use finis-est/gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-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 finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M to start chatting

Atomic Chat new
Docker Model Runner
How to use finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with Docker Model Runner:
```
docker model run hf.co/finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M
```

Lemonade

How to use finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-31b-larkspur-v0.5-Q4_K_M-Q4_K_M

List all available models

lemonade list

Gemma 4 31B Larkspur v0.5 — Q4_K_M GGUF

Q4_K_M quantization of trashpanda-org/gemma-4-31b-larkspur-v0.5.

Quant Details

Property	Value
Source	`trashpanda-org/gemma-4-31b-larkspur-v0.5`
Quant	Q4_K_M (4.83 BPW)
Size	~18 GB
Format	GGUF (llama.cpp)
Original Precision	bf16

Usage

Load with any llama.cpp-compatible runtime (llama.cpp, KoboldCpp, ollama, LM Studio, etc.):

llama-cli -m gemma-4-31b-larkspur-v0.5-Q4_K_M.gguf -p "Your prompt here"

Notes

Quantized from the bf16 source weights using llama.cpp's convert_hf_to_gguf.py → llama-quantize
Q4_K_M offers a good balance of quality and size, fitting comfortably on 2×T4 (32 GB) with room for KV cache

Downloads last month: 55

GGUF

Model size

31B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for finis-est/gemma-4-31b-larkspur-v0.5-Q4_K_M

Base model

trashpanda-org/gemma-4-31b-larkspur-v0.5

Quantized

(2)

this model