Instructions to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M

Ollama
How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF with Ollama:
```
ollama run hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
```
Unsloth Desktop

How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF with Docker Model Runner:
```
docker model run hf.co/yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M
```

Lemonade

How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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-agentic-fable5-composer2.5-v2-3.5x-tau2-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)

Garbled / repeating <unused49> in LM Studio? Known Gemma 4 client bug — not the weights (fixes inside)

pinned

🔥👍 8

#15 opened 3 months ago by

yuxinlu1

Ollama Port

pinned

#13 opened 3 months ago by

xentriom

Great agentic jump, but very slow for conversational/chat use — latency data inside

pinned

🔥 7

#11 opened 3 months ago by

TILK

MTP draft model fails to load in llama.cpp — "invalid vector subscript" (gemma4-assistant arch)

pinned

#9 opened 3 months ago by

Metod90

Tool Calling is not working in VScode[Cline]

pinned

#7 opened 3 months ago by

bhagathgoud

Gave it a simple coding task, it began looping and hallucinating hard

pinned

👍 6

#5 opened 3 months ago by

Indexnusrefather

wacky output with Q2_K

pinned

#4 opened 3 months ago by

ehurrn

He got bought out

pinned

🔥 9

#2 opened 3 months ago by deleted

The first ever model that ignored all instructions and started to do complete mess.

#69 opened 7 days ago by

rumatoest

Can I get the distilled dataset?

#68 opened about 2 months ago by

minjaezzzang

Update README.md

#67 opened 2 months ago by

zelk12

Does not work with the new LM Studio Bionic...

#66 opened 2 months ago by

cosmingurau

Hey,i have a question

#65 opened 2 months ago by

AsThirtyThree

Progress update on v3?

#64 opened 2 months ago by

Lihanvdwes

Dynamic Reasoning Collapse & Token Degradation on Gemma4 11.9B (Q6_K)

#63 opened 2 months ago by

CarlosJavi

For me this model is being extremely bad, what am I doing wrong?

#61 opened 3 months ago by

Xhatz

Request: NVFP4 Version

#60 opened 3 months ago by

Zesales

Where does the training data come from ？

#59 opened 3 months ago by

swhua

real benchmarks

🤝 2

#58 opened 3 months ago by

anonymousmaharaj

总是不能正确显示简体中文

🤝 3

#57 opened 3 months ago by

rickieyang

Multilingual powerhouse — testing for mobile deployment

#54 opened 3 months ago by

3morixd

Is it good for flutter programming?

#53 opened 3 months ago by

sdds01

any updates on its 27b qwen 3.6 cousin

#51 opened 3 months ago by

SolsticeAI

v3 when?

#50 opened 3 months ago by

yyouretoast

llama.cpp `preset.ini` to specify `gemma4-v2-Q8_0.gguf` over `MTP/gemma-4-12B-it-MTP-Q8_0.gguf`

#49 opened 3 months ago by

brian-learns

Run on 16gb ram ?

#48 opened 3 months ago by

Yoyo406

Getting MTP drafter download error when loading model

#47 opened 3 months ago by

mazdadoost

Ollama x Claude Code

#46 opened 3 months ago by

josefacero01

safety precaution

#45 opened 3 months ago by

Visaal07

My model is acting crazy in llama.cpp

#44 opened 3 months ago by

Milor123

model w/o quantized?

#43 opened 3 months ago by

junujunu

Recommendations

#42 opened 3 months ago by

SmbodyGaming

The model dosn't support tooling or agents

#41 opened 3 months ago by

limbo0x01

A way to correctly reproduce a benchmark?

#40 opened 3 months ago by

anonymousmaharaj

Safetensors version?

#39 opened 3 months ago by

Ryex

how big is your data set in size

👀 1

#38 opened 3 months ago by

akwin123

Anyway to fix this?

#36 opened 3 months ago by

octracus

Doesn"t work with LM Studio

#35 opened 3 months ago by

Romataurus

Claude Fable 5 system prompts

❤️ 1

#34 opened 3 months ago by

KElzarw

Thanks for this great model! GGUF to safetensors main and MTP

🔥 1

#33 opened 3 months ago by

tepirale

hermes agent cannot run why

#32 opened 3 months ago by

zhenyiek

Unstablity when using in OpenCode

#31 opened 3 months ago by

http403

I'm trying to download the 12gb version....

#30 opened 3 months ago by

crhylove

How to contribute data

🔥 3

#29 opened 3 months ago by

dann69

Qat Version?

#28 opened 3 months ago by

HaukoSigis

Thank you for reading :V

#26 opened 3 months ago by

Hunter878o

Thank you to a fellow open-source dev for the rigorous testing — corrected sampler guidance (long-form generation)

#25 opened 3 months ago by

yuxinlu1

Qwen 3.6 35B A3B please 🙏

#24 opened 3 months ago by

KElzarw

thank you for the model

#22 opened 3 months ago by

jarkevithwlad

model failing in claude code \ lm studio

#21 opened 3 months ago by

agent20stv