---
title: Gemma-SEA-LION-v4-27B-IT-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16.md"
repository: mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16
last_updated: 2026-02-22
license: gemma
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gemma3
architectures:
  - Gemma3ForConditionalGeneration
base_model:
  - aisingapore/Gemma-SEA-LION-v4-27B-IT
base_model_relation: finetune
parameters: 21.8B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
  - vi
  - id
  - th
  - fil
  - ta
  - ms
  - km
  - lo
  - my
  - jv
  - su
inference_backends:
  - "deploy_task text/emb/vlm"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 44
stars: 0
tags:
  - transformers
  - mlx
  - translation
---

# Gemma-SEA-LION-v4-27B-IT-bf16

> Gemma-SEA-LION-v4-27B-IT-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16

mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16 是 ModelScope 魔搭社区上的 21.8B 参数text-generation模型，采用 gemma 许可，基于 aisingapore/Gemma-SEA-LION-v4-27B-IT 构建，可用 deploy_task text/emb/vlm、sglang 0.5.2、vllm 0.9.2 部署。

- **Repository**: mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16
- **License**: gemma
- **Tasks**: text-generation
- **Parameters**: 21.8B
- **Base model**: aisingapore/Gemma-SEA-LION-v4-27B-IT
- **Inference backends**: deploy_task text/emb/vlm, sglang 0.5.2, vllm 0.9.2
- **Tags**: transformers, mlx, translation
- **Downloads**: 44
- **Stars**: 0
- **Last updated**: 2026-02-22

Source: https://www.modelscope.cn/models/mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16

---

# mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16

The Model [mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16](https://huggingface.co/mlx-community/Gemma-SEA-LION-v4-27B-IT-bf16) was converted to MLX format from [aisingapore/Gemma-SEA-LION-v4-27B-IT](https://huggingface.co/aisingapore/Gemma-SEA-LION-v4-27B-IT) using mlx-lm version **0.30.7**.

You can find other similar translation-related MLX model quants for an Apple Mac at https://huggingface.co/bibproj

* 11 Languages: Burmese, English, Indonesian, Khmer, Lao, Malay, Mandarin, Tagalog, Tamil, Thai, Vietnamese, Javanese, and Sundanese
* Last updated: 2025-08-25