Back to list

QWEN3.5 2

Alibaba Cloud
Qwen3.5_2b_64k_b1_2core_1chip
QWEN3 Qwen3.5 2 gguf w8a8 65,536 tokens M50 Temporary 2.0.0
Download Model
https://dr.bee-link.cn/vfm-admin/vfm-downloader.php?q=dXBsb2Fkcy9MTE0vTW9kZWxzL1FXRU4zL1F3ZW4zLjUvSGlNb2RlbC1Rd2VuMy41LTJiLXc4YTgtcDI1Ni0yNTZLLWIxLTJjb3JlLTFkLXhoMi12MS4zLjAtMjAyNjA2MTExMDEyNDEuZ2d1Zg%3D%3D&h=5ede253ab9b3d7574c9abbae838a7a44
Download Now
SHA-256 Checksum 3.15 GB
0b6c30cd1a7ef3eea486c44406f675f69c5acde3dc1c8f520af29ccb48fe5a3b
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: 1.3.0
Note: Models built on v1.3 require NPU driver 1.3 or above to work properly.
Note: Models for inference framework 2.0.0 require inference framework 2.0.0 or above to work properly.
2
Parameters
65,536
Tokens
gguf
Format
—
Target
1
Batch
2
CPU Cores

Basic Info

Model ID Qwen3.5_2b_64k_b1_2core_1chip
Vendor 阿里云
Name (CN) QWEN3.5 2
Name (EN) QWEN3.5 2
Series QWEN3
Type Qwen3.5

Tech Specs

Format gguf
Parameters 2
Quantization w8a8
Context Length 65536
Batch ✓ true
CPU Cores 2
Chip Count ✓ true
Chip Type M50

Deployment

Available ✓ true
Status Temporary
Software Stack 2.0.0

Capabilities

Input Text
Output Text
Features gguf w8a8
Inference Engines HLIECpp HLIEPython HLIELLama HLIEvLLM
Frameworks HLIECpp HLIEPython HLIELLama HLIEvLLM

Description

Description (CN) Type: Qwen3.5 | Size: 2 | Quant: w8a8 | Context: 65536 | Chip: M50 | Build: 1.3.0 | Status: Temporary

Build Info

Build Version 1.3.0

Timestamps

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