Instructions to use mlx-community/gemma-4-e2b-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-e2b-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-e2b-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 Settings
LM Studio

How to use mlx-community/gemma-4-e2b-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-e2b-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-e2b-it-OptiQ-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/gemma-4-e2b-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-e2b-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-e2b-it-OptiQ-4bit

Run Hermes

hermes

MLX LM

How to use mlx-community/gemma-4-e2b-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-e2b-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-e2b-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-e2b-it-OptiQ-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

codelion commited on about 20 hours ago

Commit

783acd4

verified ·

1 Parent(s): bf59eb5

card: remove em-dashes, ensure funnel

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ tags:
 # mlx-community/gemma-4-e2b-it-OptiQ-4bit
-> **Built with [mlx-optiq](https://mlx-optiq.com)** — the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. [Try the Lab](https://mlx-optiq.com/docs/lab/) · [All OptIQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)
-A 4-bit mixed-precision MLX quant produced by [mlx-optiq](https://mlx-optiq.com/) — 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-e2b-it](https://huggingface.co/google/gemma-4-e2b-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.
@@ -88,7 +88,7 @@ Six-metric Capability Score (mean of MMLU + GSM8K + IFEval + BFCL + HumanEval +
 | HumanEval (164 problems, pass@1) | **64.6%** | 57.9% | +6.7 |
 | HashHop (long-context retrieval) | **14.0%** | 22.0% | -8.0 |
 | **Capability Score** (mean of 6) | **53.21** | 51.09 | **+2.12** |
-| KL vs bf16 reference (mean / p95) | 0.7103 / 3.7552 | — | — |
 | On-disk size | 4.0 GB | 3.3 GB | +0.7 |
 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](https://mlx-optiq.com/blog/eval-framework) for the full methodology.

 # mlx-community/gemma-4-e2b-it-OptiQ-4bit
+> **Built with [mlx-optiq](https://mlx-optiq.com)**, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon, no PyTorch and no cloud. [Try the Lab](https://mlx-optiq.com/docs/lab/) · [All OptIQ quants](https://mlx-optiq.com/models) · [Docs](https://mlx-optiq.com/docs/)
+A 4-bit mixed-precision MLX quant produced by [mlx-optiq](https://mlx-optiq.com/), 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-e2b-it](https://huggingface.co/google/gemma-4-e2b-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.
 | HumanEval (164 problems, pass@1) | **64.6%** | 57.9% | +6.7 |
 | HashHop (long-context retrieval) | **14.0%** | 22.0% | -8.0 |
 | **Capability Score** (mean of 6) | **53.21** | 51.09 | **+2.12** |
+| KL vs bf16 reference (mean / p95) | 0.7103 / 3.7552 |, |, |
 | On-disk size | 4.0 GB | 3.3 GB | +0.7 |
 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](https://mlx-optiq.com/blog/eval-framework) for the full methodology.