MI

mixtral quantized

MistralGGUF by alquimista888Updated 2024-04-14
Download on Hugging Face
Parameters7.24B
Context32K
Layers32
Architecturellama
Smallest quant4.4 GB
Quick answer

mixtral quantized needs about 5.9 GB of memory at its main file (a 4.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mixtral quantized is a 7.24B-parameter Mistral model in GGUF format, quantized by alquimista888. Its trained context length is 32K tokens. The repository has 1 quant file, from 4.4 GB to 4.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—4.4 GB 5.9 GB
Fits Get file →

What GPU do you need for mixtral quantized?

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 the main file (4.4 GB file, about 5.9 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters7.24B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized byalquimista888
FamilyMistral
Licenseapache-2.0
Downloads (HF)47
Last updated2024-04-14

Frequently asked questions about mixtral quantized

How much VRAM does mixtral quantized need?

About 5.9 GB at its main file 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 mixtral quantized on an 8 GB GPU?

Yes, with the smaller files: the 4.4 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mixtral quantized GGUF?

It depends on the quant: file is 4.4 GB.

What context length does mixtral quantized 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 mixtral quantized GGUF?

The files are on Hugging Face in the alquimista888/mixtral_quantized repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does mixtral quantized 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 Mistral models

All Mistral →

Other small models

All small models →