Instructions to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-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 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-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 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-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 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-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 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-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 yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Ollama
How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with Ollama:
```
ollama run hf.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
```
Unsloth Desktop

How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M
```

Lemonade

How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

New discussion

Resources

View closed (4)

To fellow open-source creators: please don't bend the facts for clout — your work deserves respect, so let's earn it honestly

pinned

👍🔥 19

#49 opened 3 months ago by

yuxinlu1

Will you release a abliterated or uncensored variant also?

pinned

👀👍 5

#28 opened 3 months ago by

ridham034

C# & Java

pinned

#27 opened 3 months ago by

cnsiva

Installation Video and Testing - Step by Step

pinned

🔥 11

#16 opened 3 months ago by

fahdmirzac

MTP?!

pinned

👍❤️ 2

#5 opened 3 months ago by

victor11sk

Test - Dijkstra's shortest path algorithm - runtime 28ms Beats 99.46%

pinned

👍🔥 4

#4 opened 3 months ago by

jansensimanullang

Does the training data come from tau2-bench telecom ?

#58 opened 2 months ago by

swhua

mode as DNA ,可以考虑把整个蒸馏链条的能力知识训练回模型，这样模型就可以实现递归自我改进

#57 opened 2 months ago by

q021

Question: best quantization level for quality retention?

#56 opened 2 months ago by

3morixd

Question: best quantization level for quality retention?

#55 opened 2 months ago by

3morixd

Is this LoRA?

#54 opened 2 months ago by

NitrAI

🚩 Report: Spam

#53 opened 3 months ago by

urtuuuu

Finetune Diffusion gemma

#51 opened 3 months ago by

dfsafdsf

中文只能说粤语（

#50 opened 3 months ago by

linpinf

kkk

#48 opened 3 months ago by

xxdaffodilxx

can we get some benchmarks please

👀 1

#46 opened 3 months ago by

SolsticeAI

Request: QAT + MTP version of this model

🔥 2

#45 opened 3 months ago by

Jonybir

Are these small size finetunes even do the job?

➕ 2

#44 opened 3 months ago by

ninadob

256k context on rtx 3090 24gb (turboquant) used 18gb vram on Q8_0.gguf

🔥 1

#43 opened 3 months ago by

jarkevithwlad

top

#39 opened 3 months ago by

Trillvibess

Toolcall / C# / Svelte/React/etc stronger programming knowledge?

#38 opened 3 months ago by

Mk2Oracle

Error: "Model does not support chat" & RAM OOM on Custom GGUF import in Open WebUI

#37 opened 3 months ago by

user4302

why the old gemma license instead of Apache 2.0 like the pretrained gemma4?

🔥 3

#36 opened 3 months ago by

dummy9996

Unsloth Studio

#35 opened 3 months ago by

Nikolter

How to benchmark or compare 2 models?

#33 opened 3 months ago by

hirakai1411

tools

#31 opened 3 months ago by

biotest05

Has anyone compared this model against OmniCoder-9B on real life coding or things like Aider benchmarks ?

#30 opened 3 months ago by

bdutta

Delta between base and this finetuned model on coding benchmark

#26 opened 3 months ago by

arpanTarget

Fight for freedom, fight for open source !! Freedom

❤️🚀 1

#24 opened 3 months ago by

VaLtEc-BoY

QAT and/or Q3 version

#21 opened 3 months ago by

biologin

131k Context Limit?

#20 opened 3 months ago by

jessikat29

Model stops at first action

#19 opened 3 months ago by

analistaP

拒绝率有多低？

#18 opened 3 months ago by

XuehangCang

Will you release safetensors or an MLX version?

👍 1

#17 opened 3 months ago by

InderosDaniel

Sharing Fable5 data

❤️ 5

#15 opened 3 months ago by

lpalbou

BF16

#14 opened 3 months ago by

wepiqx

Multilingual

#13 opened 3 months ago by

GooGooMeow

Training methodology and dataset

❤️👍 4

#12 opened 3 months ago by

phiandersson

Error rendering prompt with jinja template

#11 opened 3 months ago by

binaryzer0

really good job keep it up

#10 opened 3 months ago by

akwin123

Quality eval on a single RTX 3090 — strong instruct/code-quality, soft tool-calling

🚀👍 9

#9 opened 3 months ago by

wasifb

Thank you and there is interest!

#8 opened 3 months ago by

NullSense

training data?

👀 1

#7 opened 3 months ago by

hololabs

Qwen3. 6

🔥 1

#6 opened 3 months ago by

GentooMonk

V2? 👀

😎 3

#2 opened 3 months ago by

singulariti

Not trolling

🚀 2

#1 opened 3 months ago by

johnlockejrr