Instructions to use sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF",
	filename="gemma-4-12B-coder-fable5-composer2.5-IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sakamakismile/gemma-4-12B-coder-fable5-composer2.5-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": "sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

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

Unsloth Studio

How to use sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF 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 sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF 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 sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF to start chatting

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

Start the llama.cpp server

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

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sakamakismile/gemma-4-12B-coder-fable5-composer2.5-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 sakamakismile/gemma-4-12B-coder-fable5-composer2.5-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 sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF:Q4_K_M

Run Hermes

hermes

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

💻 Gemma-4-12B-Coder (fable5 × composer2.5) — imatrix GGUF ✨

Runs anywhere llama.cpp runs — AMD/Vulkan, CPU, Apple, NVIDIA. No Blackwell, no MTP, just GGUF. 🐧🍎🪟

Importance-matrix (imatrix) quants of yuxinlu1's coding model, calibrated on real Python coding data so the low-bit builds keep their coding smarts. Text-only (a coding model — no vision baggage). 💚

🙏 Credit

Quants of yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1 — all thanks to @yuxinlu1 for the model. ⭐ the original and watch it for a v2! The author's recipe: a fine-tune of google/gemma-4-12B-it on execution-verified Python coding chains-of-thought (Composer 2.5 real CoT + a Fable 5 "second-attempt" set for the hard cases). It thinks in Gemma's native channel, then writes clean, runnable code. De-refused; Python/algorithmic focus; English-centric.

Why this repo: the originals are static GGUF. These add an importance matrix (code-calibrated) so IQ4_XS / Q4_K keep more quality at low VRAM — the builds that fly for AMD/Vulkan and CPU folks.

📦 Pick your quant (all imatrix)

Quant	Size	Vibe
🟢 Q3_K_S	5.53 GB	smallest that works — for 8 GB / 6 GB cards (leaves room for context). ~91.7% HumanEval[:12]
🟢 Q3_K_M	6.09 GB	tiny and sharp — 100% HumanEval[:15]
🔵 IQ4_XS	6.64 GB	the imatrix 4-bit sweet spot — 100% HumanEval[:15]
🔵 Q4_K_M	7.38 GB	balanced (embeddings/output at Q6_K)
⚪ Q5_K_M	8.55 GB	quality-first if you have the RAM/VRAM

💡 8 GB VRAM (or 6 GB): grab Q3_K_S (5.5 GB) — it leaves headroom for context and still codes well. On the Vulkan backend (AMD) all of these fly. ⚠️ Avoid IQ3 (i-quant 3-bit) for this model — IQ3_XXS/IQ3_S collapse to gibberish here (gemma-4's special attention layers don't survive 3-bit i-quants). The Q3_K_* K-quants stay coherent at the same size — that's why the small tiers are Q3_K, not IQ3.

🚀 Run it (llama.cpp — any backend)

# build llama.cpp with your backend (Vulkan for AMD):  cmake -B build -DGGML_VULKAN=ON && cmake --build build
# grab one quant:
hf download sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF gemma-4-12B-coder-fable5-composer2.5-IQ4_XS.gguf --local-dir .

# chat server (OpenAI-compatible at http://localhost:8080)
./llama-server -m gemma-4-12B-coder-fable5-composer2.5-IQ4_XS.gguf \
  -ngl 99 --ctx-size 16384 -fa on --jinja \
  --temp 1.0 --top-p 0.95 --top-k 64 --host 0.0.0.0 --port 8080

⚠️ Needs a recent llama.cpp — this is the gemma4 architecture (older builds won't load it). 🧠 Thinking is on by default via the chat template (--jinja). The model reasons through edge cases, then writes the code. For deterministic coding use --temp 0.

🦙 Ollama (one line, straight from this repo)

ollama run hf.co/sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF:Q4_K_M

Pick any tag: Q3_K_S Q3_K_M IQ4_XS Q4_K_M Q5_K_M.

❗ "manifest not found"? You must include both the hf.co/ prefix and an explicit quant tag. Without a tag, Ollama looks for :latest (which doesn't exist here); without hf.co/, it searches Ollama's own registry instead of this repo. The fix is just …-GGUF:Q4_K_M.

Also works in LM Studio / Jan / KoboldCpp — import the GGUF, pick a quant, go. 🐾

📊 How good is it? (greedy pass@1)

Benchmark	Score
HumanEval	90.2% (148/164)
MBPP	85.7% (366/427)

Strong at hard algorithms, bug-fixing & refactoring, and faithful open reasoning. Japanese prompts cause no measurable Python-quality drop.

⚠️ One honest caveat: on time-series / quant-finance code it can introduce a look-ahead bias (and its reasoning may state the right rule while the code does the opposite). Great algorithm/debug helper — but review its pandas/numpy back-test code before trusting it.

🔧 Quant details

imatrix computed on a code-heavy calibration set (HumanEval + MBPP problems & solutions) so the importance matrix reflects real coding activations.
Source: the author's Q8_0 GGUF (≈lossless). Text-only gemma4 (no vision/audio).
Higher tiers keep token-embeddings & output tensors at Q6_K (K-quant default) for fidelity where it matters most; the Q3_K tiers trade a little there for size.
K-quants over i-quants here: gemma-4's heterogeneous attention (head_dim 256 / 512 layers) survives Q3_K_* but collapses under IQ3_* — verified, so the small tiers ship as Q3_K.

📚 License & use

Gemma Terms of Use (derivatives must comply). De-refused / not safety-aligned — add your own guardrails. Best on Python/algorithmic tasks; double-check general facts and time-series code. Shared as-is. Quants & eval by Lna-Lab; thanks to @yuxinlu1. 🐾✨

Downloads last month: 3,561

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

Model tree for sakamakismile/gemma-4-12B-coder-fable5-composer2.5-GGUF

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF