Downloads · 30 days
129
11% of all-time downloads
Qwen3-30B-A3B-Mixture-2507
YOYO-AI/Qwen3-30B-A3B-Mixture-2507
Qwen3-30B-A3B-Mixture-2507 is a text generation model from YOYO-AI. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
All-time downloads
1.2K
Public
Parameters
30.5B
61.1 GB on disk
Likes
12
Public
Repo makeup
Click a slice to open those files.
.safetensors61.1 GB · 100%
At a glance
- Task
- Text Generation
- License
- apache-2.0
- Model type
- qwen3_moe
- Access
- Public
- Created
- Jul 30, 2025
- Updated
- Sep 19, 2025
- SHA
- b46c958b
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Highlights:
-
merge method:
nuslerp -
Highest precision:
dtype: float32+out_dtype: bfloat16 -
Context length:
262,144
Parameter Settings:
[!NOTE]
Temperature=0.7,TopP=0.8,TopK=20,MinP=0.
Configuration:
The following YAML configuration was used to produce this model:
models:
- model: Qwen/Qwen3-30B-A3B-Thinking-2507
parameters:
weight: 1
- model: Qwen/Qwen3-30B-A3B-Instruct-2507
parameters:
weight: 1
merge_method: nuslerp
tokenizer_source: Qwen/Qwen3-30B-A3B-Thinking-2507
parameters:
normalize: true
int8_mask: false
dtype: float32
out_dtype: bfloat16
- Task
- Text Generation
- Type
- qwen3_moe
- License
- apache-2.0
- Languages
- en, zh
- Created
- Jul 30, 2025
- Updated
- Sep 19, 2025