VI

Vistral 7B Chat

VistralGGUF by uonlpUpdated 2024-02-02
Download on Hugging Face
Parameters7.29B
Context32K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

Vistral 7B Chat needs about 6.6 GB of memory at Q5_0 (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.1 GB (Q4_0) to 14.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Vistral 7B Chat is a 7.29B-parameter Vistral model in GGUF format, quantized by uonlp. Its trained context length is 32K tokens. The repository has 6 quant files, from 4.1 GB (Q4_0) to 14.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_04.1 GB 5.7 GB
Fits Get file →
Q4_14.6 GB 6.2 GB
Fits Get file →
Q5_05.0 GB 6.6 GB
Fits Get file →
Q5_15.5 GB 7.1 GB
Fits Get file →
—7.8 GB 9.3 GB
Too big Get file →
F1614.6 GB 16.2 GB
Too big Get file →

What GPU do you need for Vistral 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: the best quant that fits is Q4_0 (4.1 GB file, about 5.7 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (5.5 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (7.8 GB file, about 9.3 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (7.8 GB file, about 9.3 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.6 GB file, about 16.2 GB in use).

Which Vistral 7B Chat quant should you choose?

Q5_0 (5.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 4.1 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters7.29B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byuonlp
FamilyVistral
Licenseafl-3.0
Downloads (HF)381
Last updated2024-02-02

Frequently asked questions about Vistral 7B Chat

How much VRAM does Vistral 7B Chat need?

About 6.6 GB at Q5_0 with an 8K context window. That is the 5.0 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 Vistral 7B Chat on an 8 GB GPU?

Yes, with Q5_1: the 5.5 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Vistral 7B Chat GGUF?

It depends on the quant: Q4_0 is 4.1 GB, Q4_1 is 4.6 GB, Q5_0 is 5.0 GB, Q5_1 is 5.5 GB, file is 7.8 GB, F16 is 14.6 GB.

What context length does Vistral 7B Chat support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Vistral 7B Chat GGUF?

The files are on Hugging Face in the uonlp/Vistral-7B-Chat-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 Vistral 7B Chat use?

Hugging Face lists the license as afl-3.0. 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 Vistral models

All Vistral →

Other small models

All small models →