Back to list

MINIMAX-H3 33

MiniMax
MiniMax-H3_33b__b1_2core_1chip
MINIMAX-H3 MiniMax-H3 33 gguf w8a8 M50 Testing 2.2.0-Preview
Download Model
https://dr.bee-link.cn/vfm-admin/vfm-downloader.php?q=dXBsb2Fkcy9MTE0vTW9kZWxzL01JTklNQVgtSDMvaG1tX3hoMl9taW5pbWF4LWgzLTMzYl93OGE4X2IxXzFjaGlwXzJjb3Jlc18zNTJ4NjA4X3YxLjUuMC56aXA%3D&h=4a7ff04a4b6df27e7d687d9791fce29d
Download Now
SHA-256 Checksum 56.71 GB
3b94e9f2b85ed8d0e36d0f6a1e0ab9bec7f13e02ced291c52edf3c01ad1179d1
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.
Note: Models built on v1.3 require NPU driver 1.3 or above to work properly.
Note: Models for inference framework 2.2.0-Preview require inference framework 2.2.0-Preview or above to work properly.
33
Parameters
—
Tokens
gguf
Format
—
Target
1
Batch
2
CPU Cores

Basic Info

Model ID MiniMax-H3_33b__b1_2core_1chip
Vendor MINIMAX-H3
Name (CN) MINIMAX-H3 33
Name (EN) MINIMAX-H3 33
Series MINIMAX-H3
Type MiniMax-H3

Tech Specs

Format gguf
Parameters 33
Quantization w8a8
Context Length ✗ false
Batch ✓ true
CPU Cores 2
Chip Count ✓ true
Chip Type M50

Deployment

Available ✓ true
Status Testing
Software Stack 2.2.0-Preview

Capabilities

Input Text
Output Text
Features gguf w8a8 vl:352*608
Inference Engines HLIEPython
Frameworks HLIEPython

Description

Description (CN) Type: MiniMax-H3 | Size: 33 | Quant: w8a8 | Chip: M50 | Status: Testing

Timestamps

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