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

Libraries

How to use mlx-community/gemma-4-e4b-it-OptiQ-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("mlx-community/gemma-4-e4b-it-OptiQ-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
LM Studio

Pi new

How to use mlx-community/gemma-4-e4b-it-OptiQ-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 "mlx-community/gemma-4-e4b-it-OptiQ-4bit"

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": "mlx-community/gemma-4-e4b-it-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gemma-4-e4b-it-OptiQ-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 "mlx-community/gemma-4-e4b-it-OptiQ-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 mlx-community/gemma-4-e4b-it-OptiQ-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/gemma-4-e4b-it-OptiQ-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 "mlx-community/gemma-4-e4b-it-OptiQ-4bit"

Run an OpenAI-compatible server

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

mlx-community/gemma-4-e4b-it-OptiQ-4bit

A 4-bit mixed-precision MLX quant produced by mlx-optiq — the sensitivity-aware quantization toolkit for Apple Silicon. Beats stock uniform 4-bit on every benchmark in the six-metric Capability Score.

A 4-bit mixed-precision MLX quant of google/gemma-4-e4b-it. Per-layer bit-widths come from a KL-divergence sensitivity pass on a six-domain calibration mix (prose · reasoning · code · agent · tool-call · constraint-bearing instructions). Sensitive layers go to 8-bit; robust ones stay at 4-bit. The on-disk size is within ~5 % of a stock uniform 4-bit MLX quant.

Quantization details

Property	Value
Predominant precision	4-bit
Layers at 8-bit (sensitive)	155
Layers at 4-bit (robust)	224
Total quantized layers	379
Group size	64
Calibration mix	six-domain mix (40 samples × 6 domains)
Reference for sensitivity	bf16 (auto-resolved; falls back to uniform-4-bit if bf16 doesn't fit)
Speculative drafter	served with `mlx-community/gemma-4-e4b-it-assistant-bf16` via `optiq serve --drafter`

We follow the same naming convention llama.cpp uses for Q4_K_M and similar mixed-precision quants: the "4-bit" label is for the predominant precision, not the weighted average. The mixed allocation is what lets this build beat stock uniform-4-bit on every benchmark below at the same disk size.

Usage

Load it with mlx-lm and use it as usual:

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gemma-4-e4b-it-OptiQ-4bit")
response = generate(
    model, tokenizer,
    prompt="Explain quantum computing in simple terms.",
    max_tokens=200,
)

For more (mixed-precision KV-cache serving, sensitivity-aware LoRA fine-tuning, OpenAI + Anthropic-compatible inference server, hot-swap mounted adapters, sandboxed Python execution for agent workflows), install mlx-optiq:

pip install mlx-optiq

Speculative decoding (assistant drafter)

Gemma-4 ships a separate small drafter for speculative decoding. Pair this quant with mlx-community/gemma-4-e4b-it-assistant-bf16 for faster decode:

optiq serve --model mlx-community/gemma-4-e4b-it-OptiQ-4bit \
            --drafter mlx-community/gemma-4-e4b-it-assistant-bf16

See the Gemma-4 family guide on mlx-optiq.com for sampling defaults, training recipes, and family-specific caveats.

Benchmarks

Six-metric Capability Score (mean of MMLU + GSM8K + IFEval + BFCL + HumanEval + HashHop). Apples-to-apples comparison against stock uniform 4-bit:

Metric	OptIQ	Uniform 4-bit	Δ
MMLU (5-shot, 1000 samples)	58.8%	52.9%	+5.9
GSM8K (1000 samples, 3-shot CoT)	77.8%	46.1%	+31.7
IFEval (full set, strict)	70.6%	68.6%	+2.0
BFCL-V3 simple (200 calls)	69.0%	67.5%	+1.5
HumanEval (164 problems, pass@1)	76.8%	58.5%	+18.3
HashHop (long-context retrieval)	42.0%	20.0%	+22.0
Capability Score (mean of 6)	65.84	52.28	+13.57
KL vs bf16 reference (mean / p95)	0.2755 / 1.3460	—	—
On-disk size	6.1 GB	4.9 GB	+1.2

Every metric gets one equal vote. Disk size is reported next to the score as an honest second axis instead of being folded into the score. See the eval-framework writeup for the full methodology.

License

Gemma license (inherits from base model). See https://ai.google.dev/gemma/terms for the terms of use.

Downloads last month: 11,793

Safetensors

Model size

7B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit