Back to list

QWEN3 30

Alibaba Cloud
Qwen3_30b-a3b_16k_b4_2core_1chip
QWEN3 Qwen3 30 gguf w4a8 16,384 tokens M50 Stable 1.5.0
Download Model
https://dr.bee-link.cn/vfm-admin/vfm-downloader.php?q=dXBsb2Fkcy9MTE0vTW9kZWxzL1FXRU4zL1F3ZW4zL0hpTW9kZWwtUXdlbjNfMjUwNy0zMGJfYTNiLXAyNTYtMTZLLWI0LTJjb3JlLTFkLXhoMi12MS40LjAtMjAyNjA1MjcxODQ3MjAuZ2d1Zg%3D%3D&h=038d39d5b34c383c5f1e8fa2f9465de7
Download Now
SHA-256 Checksum 16.25 GB
f92b0c10cb3bba70cf788afb32d751e9e8317094d43ca34a868009343aec96cc
Verify the download: on Windows run certutil -hashfile FILENAME SHA256; on macOS / Linux run shasum -a 256 FILENAME or sha256sum FILENAME. A matching value means the file is intact.
Build: 1.4.0
Note: Models built on v1.3 require NPU driver 1.3 or above to work properly.
Note: Models for inference framework 1.5.0 require inference framework 1.5.0 or above to work properly.
30
Parameters
16,384
Tokens
gguf
Format
—
Target
4
Batch
2
CPU Cores

Basic Info

Model ID Qwen3_30b-a3b_16k_b4_2core_1chip
Vendor 阿里云
Name (CN) QWEN3 30
Name (EN) QWEN3 30
Series QWEN3
Type Qwen3

Tech Specs

Format gguf
Parameters 30
Quantization w4a8
Context Length 16384
Batch 4
CPU Cores 2
Chip Count ✓ true
Chip Type M50

Deployment

Available ✓ true
Status Stable
Software Stack 1.5.0

Capabilities

Input Text
Output Text
Features gguf w4a8
Inference Engines HLIECpp HLIEPython HLIELLama HLIEvLLM
Frameworks HLIECpp HLIEPython HLIELLama HLIEvLLM

Description

Description (CN) Type: Qwen3 | Size: 30 | Quant: w4a8 | Context: 16384 | Chip: M50 | Build: 1.4.0 | Status: Stable

Build Info

Build Version 1.4.0

Timestamps

Created 2026-11-07 06:00:02
Updated 2026-11-07 06:00:02