Skip to content

tokimoa

Qwen3-Swallow-30B-A3B-RL-v0.2-MLX-6bit

tokimoa/Qwen3-Swallow-30B-A3B-RL-v0.2-MLX-6bit

Qwen3-Swallow-30B-A3B-RL-v0.2-MLX-6bit is a text generation model from tokimoa. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as apache-2.0.

東京科学大・産総研の Qwen3-Swallow-30B-A3B-RL-v0.2(日本語強化MoE、総パラメータ30B・アクティブ3B)を、公式BF16重みからMLX 6bitに変換したものです。Qwen3-Swallow-32B-RL-v0.2-MLX-4bit と同一レシピでの変換・検証です。

Downloads · 30 days

78

22% of all-time downloads

All-time downloads

362

Public

Parameters

30.5B

24.8 GB on disk

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors24.8 GB · 100%

Parameter types

How the weights are stored.

U3230.5B · 100%

Base models

Task
Text Generation
Library
mlx
Type
qwen3_moe
License
apache-2.0
Languages
ja, en
Created
Jul 26, 2026
Updated
Jul 26, 2026