Qwopus3.6 35B A3B v1 MLX 5bit Int5 Affine

--- base_model: Jackrong/Qwopus3.6-35B-A3B-v1 library_name: mlx tags: - mlx - text-generation-inference - transformers - unsloth - qwen3_6 - moe - reasoning - chain-of-thought - lora - sft - multimodal - vision - tool-use - function-calling - long-context license: apache-2.0 language: - en - zh - es - ru - ja pipeline_tag: image-text-to-text --- # 🦆 zecanard/Qwopus3.6-35B-A3B-v1-MLX-5bit-int5-affine [This model](https://huggingface.co/zecanard/Qwopus3.6-35B-A3B-v1-MLX-5bit-int5-affine) was converted to MLX from [`Jackrong/Qwopus3.6-35B-A3B-v1`](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-v1) using `mlx-vlm` version **0.6.3**. Please refer to the [original model card](https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-v1) for more details. ## 🌟 Quality Quantized vision language model with an effective **6.129 bits per weight**. `mlx_vlm.convert --quantize --q-group-size 32 --q-bits 5 --q-mode affine` ## 🛠️ Customizations This quant 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 %}` A fix is also included for a thinking-related performance issue in Qwen 3.6. ## 🖥️ Use with `mlx` ```bash pip install -U mlx-vlm ``` ```bash mlx_vlm.generate --model zecanard/Qwopus3.6-35B-A3B-v1-MLX-5bit-int5-affine --max-tokens 100 --temperature 0 --prompt "Describe this image." --image ```