Downloads · 30 days
79
3% of all-time downloads
zecanard/gemma-4-31B-it-Claude-Opus-Distilled-MLX-6bit-int6-affine
gemma-4-31B-it-Claude-Opus-Distilled-MLX-6bit-int6-affine is a image-text-to-text model from zecanard. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
This model was converted to MLX from TeichAI/gemma-4-31B-it-Claude-Opus-Distill using mlx-vlm version 0.6.3. Please refer to the original model card for more details.
Downloads · 30 days
79
3% of all-time downloads
All-time downloads
2.6K
Public
Parameters
31.3B
60.1 GB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors28 GB · 100%
How the weights are stored.
U3230.7B · 98%
From the Hugging Face model README
This model was converted to MLX from TeichAI/gemma-4-31B-it-Claude-Opus-Distill using mlx-vlm version 0.6.3.
Please refer to the original model card for more details.
Quantized vision language model with an effective 7.170 bits per weight.
mlx_vlm.convert --quantize --q-group-size 32 --q-bits 6 --q-mode affine
This quant includes a bugfix related to 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.
mlxpip install -U mlx-vlm
mlx_vlm.generate --model zecanard/gemma-4-31B-it-Claude-Opus-Distilled-MLX-6bit-int6-affine --max-tokens 100 --temperature 0 --prompt "Describe this image." --image <path_to_image>