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"}
     ]
   }'

codelion commited on 12 days ago

Commit

cfac466

verified ·

1 Parent(s): 6d66b75

card: link blog post for calibration mix instead of bare optiq.jsonl reference

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ tags:
 A 4-bit mixed-precision MLX quant produced by [mlx-optiq](https://mlx-optiq.com/), the sensitivity-aware quantization toolkit for Apple Silicon.
-A 4-bit mixed-precision MLX quant of [google/gemma-4-e4b-it](https://huggingface.co/google/gemma-4-e4b-it). Per-layer bit-widths come from a KL-divergence sensitivity pass on the bundled [`optiq.jsonl`](https://mlx-optiq.com/blog/calibration-mix) 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
@@ -30,7 +30,7 @@ A 4-bit mixed-precision MLX quant of [google/gemma-4-e4b-it](https://huggingface
 | Layers at 4-bit (robust) | 224 |
 | Total quantized layers | 379 |
 | Group size | 64 |
-| Calibration mix | `optiq.jsonl` (40 samples × 6 domains) |
 | Reference for sensitivity | bf16 (auto-resolved; falls back to uniform-4-bit if bf16 doesn't fit) |
 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 at the same disk size. Benchmark deltas are below.

 A 4-bit mixed-precision MLX quant produced by [mlx-optiq](https://mlx-optiq.com/), the sensitivity-aware quantization toolkit for Apple Silicon.
+A 4-bit mixed-precision MLX quant of [google/gemma-4-e4b-it](https://huggingface.co/google/gemma-4-e4b-it). Per-layer bit-widths come from a KL-divergence sensitivity pass on a [six-domain calibration mix](https://mlx-optiq.com/blog/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
 | Layers at 4-bit (robust) | 224 |
 | Total quantized layers | 379 |
 | Group size | 64 |
+| Calibration mix | [six-domain mix](https://mlx-optiq.com/blog/calibration-mix) (40 samples × 6 domains) |
 | Reference for sensitivity | bf16 (auto-resolved; falls back to uniform-4-bit if bf16 doesn't fit) |
 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 at the same disk size. Benchmark deltas are below.