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

Libraries

How to use nikimori/gemma-4-e4b-it-4bit-slim 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("nikimori/gemma-4-e4b-it-4bit-slim")

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 nikimori/gemma-4-e4b-it-4bit-slim with Pi:

Start the MLX server

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

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": "nikimori/gemma-4-e4b-it-4bit-slim"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nikimori/gemma-4-e4b-it-4bit-slim with MLX LM:

Generate or start a chat session

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

Run an OpenAI-compatible server

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

Hermes Agent

How to use nikimori/gemma-4-e4b-it-4bit-slim 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 "nikimori/gemma-4-e4b-it-4bit-slim"

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 nikimori/gemma-4-e4b-it-4bit-slim

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nikimori/gemma-4-e4b-it-4bit-slim with OpenClaw:

Start the MLX server

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

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 "nikimori/gemma-4-e4b-it-4bit-slim" \
  --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-it, 4-bit MLX (slim)

A slimmer re-pack of mlx-community/gemma-4-e4b-it-4bit, a conversion of google/gemma-4-E4B-it:

The audio tower is removed. The vision tower stays, because Pretype's speculative-decoding load (with Google's MTP drafter) needs it.
All other weights are unchanged.

The weights are 4.53 GB instead of 5.15 GB (−12%). In Pretype's evals the outputs match the original (details). The license is the upstream one (Apache-2.0).

Made for Pretype, on-device autocomplete for macOS. It is the model that fixes a selection (⌥Tab) and drafts replies on Pretype's Gemma E2B 8-bit tier, and on the E4B tiers in Base style.

On Pretype's held-out sets (2026-10-11, 17–19 languages), it restores 65% [61–69] of single-typo sentences exactly, proposes a change on 21% of clean lines, and drafts a usable reply for 95% [92–97] of on-screen conversations.

from mlx_lm import load, generate
model, tokenizer = load("nikimori/gemma-4-e4b-it-4bit-slim")
messages = [{"role": "user", "content": "Fix the typo: I recieved your letter."}]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
print(generate(model, tokenizer, prompt=prompt, max_tokens=40))

Downloads last month: 41

Safetensors

Model size

8B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for nikimori/gemma-4-e4b-it-4bit-slim

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(391)

this model