Instructions to use Akira-Papa/akira-papa-1.0-e4b-jp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akira-Papa/akira-papa-1.0-e4b-jp with MLX:

# Download the model from the Hub
pip install huggingface_hub[hf_xet]

huggingface-cli download --local-dir akira-papa-1.0-e4b-jp Akira-Papa/akira-papa-1.0-e4b-jp

llama-cpp-python

How to use Akira-Papa/akira-papa-1.0-e4b-jp with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Akira-Papa/akira-papa-1.0-e4b-jp",
	filename="akira-papa-1.0-E4B-jp-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Akira-Papa/akira-papa-1.0-e4b-jp with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Akira-Papa/akira-papa-1.0-e4b-jp: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 Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Akira-Papa/akira-papa-1.0-e4b-jp: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 Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M

Use Docker

docker model run hf.co/Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M

LM Studio
Jan
Ollama
How to use Akira-Papa/akira-papa-1.0-e4b-jp with Ollama:
```
ollama run hf.co/Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
```

Unsloth Studio

How to use Akira-Papa/akira-papa-1.0-e4b-jp 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 Akira-Papa/akira-papa-1.0-e4b-jp 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 Akira-Papa/akira-papa-1.0-e4b-jp to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Akira-Papa/akira-papa-1.0-e4b-jp to start chatting

How to use Akira-Papa/akira-papa-1.0-e4b-jp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Akira-Papa/akira-papa-1.0-e4b-jp"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Akira-Papa/akira-papa-1.0-e4b-jp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Akira-Papa/akira-papa-1.0-e4b-jp with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Akira-Papa/akira-papa-1.0-e4b-jp"

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 Akira-Papa/akira-papa-1.0-e4b-jp

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Akira-Papa/akira-papa-1.0-e4b-jp with Docker Model Runner:
```
docker model run hf.co/Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M
```

Lemonade

How to use Akira-Papa/akira-papa-1.0-e4b-jp with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Akira-Papa/akira-papa-1.0-e4b-jp:Q4_K_M

Run and chat with the model

lemonade run user.akira-papa-1.0-e4b-jp-Q4_K_M

List all available models

lemonade list

akira-papa-1.0-e4b-jp

akira-papa-1.0-e4b-jp は、Gemma 4 E4B-it を土台に、Akira-Papa が作成・整理した日本語データ、teacher-guided rewrite、route-aware tuning を重ねた E4B mainline です。
短いブログ本文や、温度感のある日本語 writer 補助を主目的に整えています。

位置づけ

現在の系統: E4B mainline
Hugging Face repo: https://huggingface.co/Akira-Papa/akira-papa-1.0-e4b-jp
Gemma 4 E4B-it ベースの日本語 writer 寄りライン

主な用途

短いブログ本文
short_blog_section
具体と生活感を優先した writer 補助
writer route を優先したい場合

強み

温度感のある短文
ブログ本文の書き出し
自然な日本語の tone 調整

同梱される主なファイル

mainline merged model 一式
akira-papa-1.0-E4B-jp-Q8_0.gguf
akira-papa-1.0-E4B-jp-Q4_K_M.gguf
NOTICE
GEMMA_TERMS.md
MODIFICATIONS.md

使い分け

Q8_0: mainline 品質優先の本命
Q4_K_M: 容量優先の補助 variant
merged model: MLX 系ワークフロー向け

注意

Q4_K_M は writer route で崩れやすく、experimental 扱いです。まずは Q8_0 を推奨します
長文 reasoning や heavy coding 専用 best ではありません

ベースモデルと利用条件

このモデルのベースは google/gemma-4-E4B-it です。

利用前に次を確認してください。

NOTICE
GEMMA_TERMS.md
MODIFICATIONS.md

Downloads last month: 182

Safetensors

Model size

8B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Inference Providers NEW

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

Model tree for Akira-Papa/akira-papa-1.0-e4b-jp

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(241)

this model

Akira-Papa
/

akira-papa-1.0-e4b-jp