BA

Baichuan2 7B Base

BaichuanGGUF by jasonchen0112Updated 2024-03-26
Download on Hugging Face
Parameters7.51B
Context4K
Layers32
Architecturellama
Smallest quant15.0 GB
Quick answer

Baichuan2 7B Base needs about 19.8 GB of memory at its main file (a 15.0 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Baichuan2 7B Base is a 7.51B-parameter Baichuan model in GGUF format, quantized by jasonchen0112. Its trained context length is 4K tokens. The repository has 1 quant file, from 15.0 GB to 15.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—15.0 GB 17.7 GB
Too big Get file →

What GPU do you need for Baichuan2 7B Base?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (15.0 GB file, about 19.8 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.51B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized byjasonchen0112
FamilyBaichuan
Downloads (HF)3
Last updated2024-03-26

Frequently asked questions about Baichuan2 7B Base

How much VRAM does Baichuan2 7B Base need?

About 19.8 GB at its main file with an 8K context window. That is the 15.0 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 Baichuan2 7B Base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Baichuan2 7B Base GGUF?

It depends on the quant: file is 15.0 GB.

What context length does Baichuan2 7B Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download Baichuan2 7B Base GGUF?

The files are on Hugging Face in the jasonchen0112/Baichuan2-7B-Base.gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More Baichuan models

All Baichuan →

Other small models

All small models →