Gemma 4 E2B It Uncensored Heretic Ara MLX 6bit Int6 Affine

--- base_model: p-e-w/gemma-4-E2B-it-heretic-ara language: en library_name: mlx license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license pipeline_tag: any-to-any tags: - mlx - heretic - uncensored - decensored - abliterated - ara --- # 🦆 zecanard/gemma-4-E2B-it-uncensored-heretic-ara-MLX-6bit-int6-affine [This model](https://huggingface.co/zecanard/gemma-4-E2B-it-uncensored-heretic-ara-MLX-6bit-int6-affine) was converted to MLX from [`p-e-w/gemma-4-E2B-it-heretic-ara`](https://huggingface.co/p-e-w/gemma-4-E2B-it-heretic-ara) using `mlx-vlm` version **0.6.3**. Please refer to the [original model card](https://huggingface.co/p-e-w/gemma-4-E2B-it-heretic-ara) for more details. ## 🌟 Quality Quantized vision language model with an effective **7.877 bits per weight**. `mlx_vlm.convert --quantize --q-group-size 32 --q-bits 6 --q-mode affine` ## 🛠️ Customizations This quant includes a bugfix for tools calling. It is aware of the current date, and also enables thinking (if available). You may disable this behavior by deleting the following line from the chat template, or changing `true` to `false`: `{%- set enable_thinking = true %}` You may need to adjust your environment’s **Reasoning Section Parsing** to recognize `<|channel>thought` as the **Start String**, and `<channel|>` as the **End String**. ## 🖥️ Use with `mlx` ```bash pip install -U mlx-vlm ``` ```bash mlx_vlm.generate --model zecanard/gemma-4-E2B-it-uncensored-heretic-ara-MLX-6bit-int6-affine --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image> ```

Source context: 37 downloads · 1 likes · Pipeline any-to-any · Library mlx · Repo zecanard/gemma-4-E2B-it-uncensored-heretic-ara-MLX-6bit-int6-affine