Instructions to use jorch/gemma-4-e4b-it-lm-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jorch/gemma-4-e4b-it-lm-4bit 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("jorch/gemma-4-e4b-it-lm-4bit")

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 jorch/gemma-4-e4b-it-lm-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jorch/gemma-4-e4b-it-lm-4bit"

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": "jorch/gemma-4-e4b-it-lm-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use jorch/gemma-4-e4b-it-lm-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "jorch/gemma-4-e4b-it-lm-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "jorch/gemma-4-e4b-it-lm-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "jorch/gemma-4-e4b-it-lm-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use jorch/gemma-4-e4b-it-lm-4bit 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 "jorch/gemma-4-e4b-it-lm-4bit"

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 jorch/gemma-4-e4b-it-lm-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jorch/gemma-4-e4b-it-lm-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "jorch/gemma-4-e4b-it-lm-4bit"

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 "jorch/gemma-4-e4b-it-lm-4bit" \
  --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"

Gemma 4 E4B — Text-Only MLX 4-bit

Text-only extraction of Google's Gemma 4 E4B instruction-tuned model, converted to MLX format with 4-bit quantization.

This is the language model component only (no vision/audio towers), suitable for text chat on Apple Silicon devices including iPhones (8 GB RAM) and Macs.

Model Details

Spec	Value
Base model	`google/gemma-4-e4b-it`
Architecture	Gemma 4 with Per-Layer Embeddings (PLE)
Parameters	8B total, 4.5B active
Hidden size	2560
Layers	42
Attention heads	8 (2 KV heads)
Vocab size	262,144
Context window	128K tokens
Quantization	4-bit affine (group size 64)
Download size	3.9 GB
License	Apache 2.0

Conversion

Converted from google/gemma-4-e4b-it using mlx-lm with Gemma 4 support from ml-explore/mlx-lm PR #1095:

python -m mlx_lm convert --hf-path google/gemma-4-e4b-it -q --q-bits 4 --mlx-path ./gemma-4-e4b-it-lm-4bit

Usage with mlx-lm (Python)

from mlx_lm import load, generate

model, tokenizer = load("jorch/gemma-4-e4b-it-lm-4bit")
response = generate(model, tokenizer, prompt="What is machine learning?", verbose=True, max_tokens=512)

Usage with mlx-swift-lm (iOS/macOS)

Requires Gemma 4 text model support in mlx-swift-lm:

import MLXLLM
import MLXLMCommon

let configuration = ModelConfiguration(id: "jorch/gemma-4-e4b-it-lm-4bit")
let container = try await LLMModelFactory.shared.loadContainer(configuration: configuration)

Why text-only?

The mlx-community/gemma-4-e4b-it-4bit model was converted with mlx-vlm and includes vision/audio towers. That conversion is missing critical text model weights (norm, per_layer_projection_norm, per_layer_model_projection), making it incompatible with text-only LLM loaders.

This conversion uses mlx-lm which properly extracts and preserves all text model weight keys.

E4B vs E2B

	E2B	E4B
Active params	2.3B	4.5B
Download	2.5 GB	3.9 GB
Quality	Good for everyday chat	Noticeably better reasoning
Speed	Faster	Slightly slower
iPhone 8 GB	Comfortable	Fits with headroom

Built for SoloAI

This model powers SoloAI — a privacy-first iOS chat app that runs Gemma 4 entirely on-device.

Downloads last month: 35

Safetensors

Model size

8B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit