MMODELYST
Models/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit
MDL

Qwen3-30B-A3B-Thinking-2507-AWQ-4bit

cyankiwi

Hugging Face ↗
Parameters
30B
Downloads
134.2K
on HF
Likes
15
Avg score
—
Weights
Open
Released
Jul 30, 2025
About

Qwen3-30B-A3B-Thinking-2507-AWQ-4bit is a 30B-parameter open-weights model in the Qwen3 family from cyankiwi.

apache-2.0text-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →
Training-Free Long-Context Scaling of Large Language ModelsMInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse AttentionQwen2.5-1M Technical ReportRULER: What's the Real Context Size of Your Long-Context Language Models?Qwen3 Technical Report
Details
Publishercyankiwi
FamilyQwen3
Parameters30B
Licenseapache-2.0
WeightsOpen
ReleasedJul 30, 2025