Orion-zhen
/

Qwen3-30B-A3B-Thinking-2507-1M-GGUF

Model card Files Files and versions

Qwen3-30B-A3B-Thinking-2507-1M-GGUF

Scale context window up from 262144 to 1048576 (x4) using yarn.

Due to my poor limited network bandwidth, I have to pick out some quantization to upload, instead of all of them. BTW, Qwen is really good at scaling model name lol.

Downloads last month: 152

GGUF

Model size

31B params

Architecture

qwen3moe

Hardware compatibility

Log In to view the estimation

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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

Model tree for Orion-zhen/Qwen3-30B-A3B-Thinking-2507-1M-GGUF

Base model

Qwen/Qwen3-30B-A3B-Thinking-2507

Quantized

(72)

this model