---
license: gpl-3.0
language:
- en
- zh
base_model:
- Qwen/Qwen3-30B-A3B-Instruct-2507
---

# Qwen3-30B-A3B-Instruct-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.