MI

mistralai_mixtral-8x7b-instruct-v0.1

MistralGGUF by 404-OSUpdated 2024-05-01
Download on Hugging Face
Parameters46.7B
Context32K
Layers32
Architecturellama
Smallest quant15.6 GB
Quick answer

mistralai_mixtral-8x7b-instruct-v0.1 needs about 17.2 GB of memory at Q2_K (a 15.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

mistralai_mixtral-8x7b-instruct-v0.1 is a 46.7B-parameter Mistral model in GGUF format, quantized by 404-OS. Its trained context length is 32K tokens. The repository has 1 quant file, from 15.6 GB (Q2_K) to 15.6 GB (Q2_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K15.6 GB 17.2 GB
Too big Get file →

What GPU do you need for mistralai_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: the best quant that fits is Q2_K (15.6 GB file, about 17.2 GB in use).

Which mistralai_mixtral-8x7b-instruct-v0.1 quant should you choose?

Q2_K (15.6 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

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 by404-OS
FamilyMistral
Licenseapache-2.0
Downloads (HF)5
Last updated2024-05-01

Frequently asked questions about mistralai_mixtral-8x7b-instruct-v0.1

How much VRAM does mistralai_mixtral-8x7b-instruct-v0.1 need?

About 17.2 GB at Q2_K with an 8K context window. That is the 15.6 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 mistralai_mixtral-8x7b-instruct-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of mistralai_mixtral-8x7b-instruct-v0.1 GGUF?

It depends on the quant: Q2_K is 15.6 GB.

What context length does mistralai_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 mistralai_mixtral-8x7b-instruct-v0.1 GGUF?

The files are on Hugging Face in the 404-OS/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 mistralai_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 404-OS

All by 404-OS →

More Mistral models

All Mistral →

Other large models

All large models →