Instructions to use sticoapp/metel-gemma4-e4b-ko-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sticoapp/metel-gemma4-e4b-ko-v2 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("sticoapp/metel-gemma4-e4b-ko-v2")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use sticoapp/metel-gemma4-e4b-ko-v2 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sticoapp/metel-gemma4-e4b-ko-v2"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "sticoapp/metel-gemma4-e4b-ko-v2"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use sticoapp/metel-gemma4-e4b-ko-v2 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "sticoapp/metel-gemma4-e4b-ko-v2"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "sticoapp/metel-gemma4-e4b-ko-v2"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "sticoapp/metel-gemma4-e4b-ko-v2",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use sticoapp/metel-gemma4-e4b-ko-v2 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 "sticoapp/metel-gemma4-e4b-ko-v2"

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 sticoapp/metel-gemma4-e4b-ko-v2

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use sticoapp/metel-gemma4-e4b-ko-v2 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "sticoapp/metel-gemma4-e4b-ko-v2"

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 "sticoapp/metel-gemma4-e4b-ko-v2" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

metel-gemma4-e2b-ko-v1

Metel AI 서비스용 한국어 파인튜닝 모델. google/gemma-4-E2B-it 기반, MLX 4-bit 양자화.

학습 개요

항목	내용
베이스 모델	`google/gemma-4-E2B-it`
방법	LoRA (r=16, alpha=32)
학습률	2e-4
에폭	3
양자화	4-bit, group_size=64 (mlx_lm / mlx_vlm)
업로드 시각	2026-06-30T10:17:01Z

학습 데이터

출처	건수	라이선스
Anthropic Claude Haiku 합성 한국어 대화	~1,700	Metel 내부
KoAlpaca	~3,000	cc-by-sa-4.0
Metel 서비스 사용자 trajectory	~1,300	Metel 내부

주의: 학습 데이터 자체는 이 저장소에 포함되지 않습니다. 모델 가중치만 제공됩니다.

라이선스

이 모델은 다음 라이선스의 적용을 받습니다:

기본 가중치: Apache 2.0
KoAlpaca 파생 데이터: CC BY-SA 4.0

KoAlpaca 데이터를 사용하여 파생된 이 모델은 CC BY-SA 4.0 조건에 따라 동일 조건으로 공유되어야 합니다.

사용법 (mlx-vlm)

from mlx_vlm import load, generate

model, processor = load("mcred2030/metel-gemma4-e2b-ko-v1")
prompt = "안녕하세요! 오늘 날씨가 어때요?"
output = generate(model, processor, prompt=prompt, max_tokens=256)
print(output)

사용법 (mlx-lm, text-only 모드)

from mlx_lm import load, generate

model, tokenizer = load("mcred2030/metel-gemma4-e2b-ko-v1")
prompt = "안녕하세요! 오늘 날씨가 어때요?"
output = generate(model, tokenizer, prompt=prompt, max_tokens=256)
print(output)

iOS/macOS 앱 통합 (mlx-swift-lm)

Metel iOS/macOS 앱에서는 ModelVariant.e2bMetelV1 선택 시 이 모델을 사용합니다.

Model tree for sticoapp/metel-gemma4-e4b-ko-v2

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

(421)

this model

sticoapp
/

metel-gemma4-e4b-ko-v2

metel-gemma4-e2b-ko-v1

학습 개요

학습 데이터

라이선스

사용법 (mlx-vlm)

사용법 (mlx-lm, text-only 모드)

iOS/macOS 앱 통합 (mlx-swift-lm)

관련 링크

Model tree for sticoapp/metel-gemma4-e4b-ko-v2