ModelListedExternal

Gemma 4 E4B It Heretic Mlx 4Bit

The Model McG-221/gemma-4-E4B-it-heretic-mlx-4Bit was converted to MLX format from coder3101/gemma-4-E4B-it-heretic using mlx-lm version 0.31.2.

Sourcehuggingface.co/McG-221/gemma-4-E4B-it-heretic-mlx-4Bit/tree/b0caa71ef36eabebafb01e23904195e751c5f8c4

KindText modelBase modelcoder3101/gemma-4-E4B-it-hereticVersionmodel

Model source

Kind: Text model
File size: 3.94 GB
Base model: coder3101/gemma-4-E4B-it-heretic
Version: vmodel
Updated: Sep 26, 2026
Downloads: 50
Source: Hugging Face

Source description

McG-221/gemma-4-E4B-it-heretic-mlx-4Bit

The Model McG-221/gemma-4-E4B-it-heretic-mlx-4Bit was converted to MLX format from coder3101/gemma-4-E4B-it-heretic using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("McG-221/gemma-4-E4B-it-heretic-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

Sources

1 source

Hugging FacePrimaryVersion b0caa71ef36eabebafb01e23904195e751c5f8c4

huggingface.co/McG-221/gemma-4-E4B-it-heretic-mlx-4Bit/tree/b0caa71ef36eabebafb01e23904195e751c5f8c4

Verified Sep 26

Model artifacts

1 artifact

model.safetensors

safetensors · 3.94 GB · SHA-256 2207975e2a45…3816 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeSep 26huggingface.co/McG-221/gemma-4-E4B-it-heretic-mlx-4Bit

--- library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: any-to-any tags: - heretic - uncensored - decensored - abliterated - ara - mlx - mlx-my-repo base_model: coder3101/gemma-4-E4B-it-heretic --- # McG-221/gemma-4-E4B-it-heretic-mlx-4Bit The Model [McG-221/gemma-4-E4B-it-heretic-mlx-4Bit](https://huggingface.co/McG-221/gemma-4-E4B-it-heretic-mlx-4Bit) was converted to MLX format from [coder3101/gemma-4-E4B-it-heretic](https://huggingface.co/coder3101/gemma-4-E4B-it-heretic) using mlx-lm version **0.31.2**. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("McG-221/gemma-4-E4B-it-heretic-mlx-4Bit") prompt="hello" if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```

NoteSep 26huggingface.co/McG-221/gemma-4-E4B-it-heretic-mlx-4Bit

Source context: 50 downloads · 0 likes · Pipeline any-to-any · Library transformers · Repo McG-221/gemma-4-E4B-it-heretic-mlx-4Bit