BA

Baichuan2-7B-Chat

BaichuanGGUF by apepkuss79Updated 2023-10-17
Download on Hugging Face
Parameters7.51B
Context4K
Layers32
Architecturebaichuan
Smallest quant4.4 GB
Quick answer

Baichuan2-7B-Chat needs about 9.2 GB of memory at Q4_0 (a 4.4 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 4.4 GB (Q4_0) to 15.0 GB (F16).

Baichuan2-7B-Chat is a 7.51B-parameter Baichuan model in GGUF format, quantized by apepkuss79. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.4 GB (Q4_0) to 15.0 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.4 GB 7.0 GB
Fits Get file →
F1615.0 GB 17.7 GB
Too big Get file →

What GPU do you need for Baichuan2-7B-Chat?

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: the best quant that fits is Q4_0 (4.4 GB file, about 9.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_0 (4.4 GB file, about 9.2 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (15.0 GB file, about 19.8 GB in use).

Which Baichuan2-7B-Chat quant should you choose?

Q4_0 (4.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byapepkuss79
FamilyBaichuan
Downloads (HF)55
Last updated2023-10-17

Frequently asked questions about Baichuan2-7B-Chat

How much VRAM does Baichuan2-7B-Chat need?

About 9.2 GB at Q4_0 with an 8K context window. That is the 4.4 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-Chat on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Baichuan2-7B-Chat GGUF?

It depends on the quant: Q4_0 is 4.4 GB, F16 is 15.0 GB.

What context length does Baichuan2-7B-Chat 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-Chat GGUF?

The files are on Hugging Face in the apepkuss79/Baichuan2-7B-Chat-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 from apepkuss79

All by apepkuss79 →

More Baichuan models

All Baichuan →

Other small models

All small models →