MI

Mixtral-8x7B-Instruct-v0.1

MistralGGUF by gobeanUpdated 2024-04-19
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant22.5 GB
Quick answer

Mixtral-8x7B-Instruct-v0.1 needs about 30.0 GB of memory at its main file (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 6 quants, from 22.5 GB to 38.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Mixtral-8x7B-Instruct-v0.1 is a 46.7B-parameter Mistral model in GGUF format, quantized by gobean. Its trained context length is 32K tokens. The repository has 6 quant files, from 22.5 GB to 38.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—22.5 GB 24.1 GB
Too big Get file →
—26.4 GB 28.0 GB
Too big Get file →
—28.4 GB 30.0 GB
Too big Get file →
—32.2 GB 33.8 GB
Too big Get file →
—33.2 GB 34.8 GB
Too big Get file →
—38.4 GB 40.0 GB
Too big Get file →

What GPU do you need for Mixtral-8x7B-Instruct-v0.1?

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: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (28.4 GB file, about 30.0 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (38.4 GB file, about 40.0 GB in use).

Which Mixtral-8x7B-Instruct-v0.1 quant should you choose?

If memory is tight, the smallest file is the first one in the table at 22.5 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

Architecturellama
Parameters46.7B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bygobean
FamilyMistral
Licenseapache-2.0
Downloads (HF)172
Last updated2024-04-19

Frequently asked questions about Mixtral-8x7B-Instruct-v0.1

How much VRAM does Mixtral-8x7B-Instruct-v0.1 need?

About 30.0 GB at its main file with an 8K context window. That is the 28.4 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-8x7B-Instruct-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mixtral-8x7B-Instruct-v0.1 GGUF?

It depends on the quant: file is 22.5 GB, file is 26.4 GB, file is 28.4 GB, file is 32.2 GB, file is 33.2 GB, file is 38.4 GB.

What context length does Mixtral-8x7B-Instruct-v0.1 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-8x7B-Instruct-v0.1 GGUF?

The files are on Hugging Face in the gobean/Mixtral-8x7B-Instruct-v0.1-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 Mixtral-8x7B-Instruct-v0.1 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 gobean

All by gobean →

More Mistral models

All Mistral →

Other large models

All large models →