YU

Yuan2 M32

YuanGGUF by IEITYuanUpdated 2024-06-03
Download on Hugging Face
Parameters40.2B
Context4K
Layers—
Architectureyuan2_moe
Smallest quant5.3 GB
Quick answer

Yuan2 M32 needs about 12.5 GB of memory at its main file (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 8 quants, from 5.3 GB to 10.7 GB.

Yuan2 M32 is a 40.2B-parameter Yuan model in GGUF format, quantized by IEITYuan. Its trained context length is 4K tokens. The repository has 8 quant files, from 5.3 GB to 10.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.3 GB 6.1 GB
Fits Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →
—10.7 GB 11.9 GB
Too big Get file →

What GPU do you need for Yuan2 M32?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is the main file (5.3 GB file, about 6.4 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (5.3 GB file, about 6.4 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (10.7 GB file, about 12.5 GB in use).

Which Yuan2 M32 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 5.3 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureyuan2_moe
Parameters40.2B
Trained context4,096 tokens

Source

Quantized byIEITYuan
FamilyYuan
Licenseapache-2.0
Downloads (HF)118
Last updated2024-06-03

Frequently asked questions about Yuan2 M32

How much VRAM does Yuan2 M32 need?

About 12.5 GB at its main file with an 8K context window. That is the 10.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Yuan2 M32 on an 8 GB GPU?

Yes, with the smaller files: the 5.3 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Yuan2 M32 GGUF?

It depends on the quant: file is 5.3 GB, file is 10.7 GB, file is 10.7 GB, file is 10.7 GB, file is 10.7 GB, file is 10.7 GB and 2 more.

What context length does Yuan2 M32 support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download Yuan2 M32 GGUF?

The files are on Hugging Face in the IEITYuan/Yuan2-M32-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Yuan2 M32 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from IEITYuan

All by IEITYuan →

More Yuan models

All Yuan →

Other large models

All large models →