Instructions to use stamsam/MedusaGemma-E4B_MLX_4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stamsam/MedusaGemma-E4B_MLX_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("stamsam/MedusaGemma-E4B_MLX_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 stamsam/MedusaGemma-E4B_MLX_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 "stamsam/MedusaGemma-E4B_MLX_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": "stamsam/MedusaGemma-E4B_MLX_4Bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use stamsam/MedusaGemma-E4B_MLX_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 "stamsam/MedusaGemma-E4B_MLX_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 stamsam/MedusaGemma-E4B_MLX_4Bit

Run Hermes

hermes

MLX LM

How to use stamsam/MedusaGemma-E4B_MLX_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 "stamsam/MedusaGemma-E4B_MLX_4Bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "stamsam/MedusaGemma-E4B_MLX_4Bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "stamsam/MedusaGemma-E4B_MLX_4Bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

MedusaGemma-E4B-MLX-4Bit

Tagline: One spine. Many heads.

Started as a MacBook Pro experiment and grew into a full composite release.

Model Summary

MedusaGemma-E4B-MLX-4Bit is the compact Apple Silicon build of MedusaGemma-E4B: a fused local model for offline inference, reasoning, and practical work.

What Went Into It

This is the 4-bit MLX release for Apple Silicon local use. The donor lineage and adaptation work are baked in so this repo is a single downloadable model artifact.

Primary lineage:

google/gemma-4-E4B-it
DavidAU/gemma-4-E4B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking
Jiunsong/supergemma4-e4b-abliterated

Stamsam custom dojo / training

The adaptation stack was built on:

pocket-polymath-seam-adapter
pocket-polymath-legacy-adapter
pocket-polymath-legacy-4096-adapter
pocket-polymath-broad-growth-adapter
pocket-polymath-ultimate-dojo-adapter

Synthetic dojo data came from glm-5.1:cloud via Ollama, plus Gemini-generated material from the same workflow.

Quantization Notes

Format: MLX
Quantization: 4-bit
Target hardware: Apple Silicon

Best For

fast Apple Silicon local inference
offline assistant work
structured reasoning and business analysis
general writing and summarization
practical code generation
integration with the Pocket Polymath stack

Keep In Mind

The bare MLX build can still make arithmetic mistakes without the stack.
The bare MLX build can still miss exact refusal behavior without the stack.
The bare MLX build can still miss strict formatting constraints without validators.

Evaluation Snapshot

Fresh full holdout: 40/40
External-lite cleaned: 256/265, 96.6%
MBPP repair mode: 20/20 final on the cleaned slice and fresh holdout
Reasoning leaks: 0
Bad claims: 0

Safety and Reliability

The Pocket Polymath stack adds:

reasoning leak guard
missing-data refusal router
arithmetic router
structured-output validators
completion checks
optional sandboxed code verifier/repair mode

Release Names

Raw model: MedusaGemma-E4B
MLX 4-bit: MedusaGemma-E4B-MLX-Q4
Default stack: Pocket Polymath: MedusaGemma-E4B RC2
Optional code mode: Pocket Polymath: MedusaGemma-E4B RC2.1 Code Repair

Downloads last month: 24

Safetensors

Model size

1B params

Tensor type

F16

U32

MLX

Hardware compatibility

4-bit

Model tree for stamsam/MedusaGemma-E4B_MLX_4Bit

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Quantized

(202)

this model