gemma-4-26b-a4b-it-8bit(镜像)

这是 mlx-community/gemma-4-26b-a4b-it-8bit 的镜像,供螺壳(luoke)的本地应用在国内下载:螺壳主控按发布清单取这里的文件、逐文件核对哈希后用作 64 GB 以上内存档的底座模型。权重、config、tokenizer 等文件与 mlx-community 的原版逐字节相同(8 bit 仿射量化,group size 64),只补了这份说明和 LICENSE。上游模型 google/gemma-4-26b-a4b-it(Google)为 Apache License 2.0(见 Gemma 4 许可页);Google 另有禁止用途政策和使用条款,使用前请阅读。量化由 mlx-community 用 mlx-vlm 0.4.3 完成。


以下为 mlx-community 原模型卡:

mlx-community/gemma-4-26b-a4b-it-8bit

This model was converted to MLX format from google/gemma-4-26b-a4b-it using mlx-vlm version 0.4.3. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/gemma-4-26b-a4b-it-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
53
Safetensors
Model size
26B params
Tensor type
U32
·
BF16
·
MLX
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support