MI

Mixtral Erotic 13Bx2 MOE 22B

MistralGGUF by JustDataUpdated 2024-03-07
Download on Hugging Face
Parameters21.5B
Context4K
Layers40
Architecturellama
Smallest quant17.6 GB
Quick answer

Mixtral Erotic 13Bx2 MOE 22B needs about 24.9 GB of memory at Q6_K (a 17.6 GB file) with an 8K context window, so it fits on a 32 GB GPU.

Mixtral Erotic 13Bx2 MOE 22B is a 21.5B-parameter Mistral model in GGUF format, quantized by JustData. Its trained context length is 4K tokens. The repository has 1 quant file, from 17.6 GB (Q6_K) to 17.6 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q6_K17.6 GB 21.5 GB
Too big Get file →

What GPU do you need for Mixtral Erotic 13Bx2 MOE 22B?

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 Q6_K (17.6 GB file, about 24.9 GB in use).

Which Mixtral Erotic 13Bx2 MOE 22B quant should you choose?

Q6_K (17.6 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters21.5B (approximate, mixture of experts)
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized byJustData
FamilyMistral
Downloads (HF)94
Last updated2024-03-07

Frequently asked questions about Mixtral Erotic 13Bx2 MOE 22B

How much VRAM does Mixtral Erotic 13Bx2 MOE 22B need?

About 24.9 GB at Q6_K with an 8K context window. That is the 17.6 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 Mixtral Erotic 13Bx2 MOE 22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 24.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mixtral Erotic 13Bx2 MOE 22B GGUF?

It depends on the quant: Q6_K is 17.6 GB.

What context length does Mixtral Erotic 13Bx2 MOE 22B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download Mixtral Erotic 13Bx2 MOE 22B GGUF?

The files are on Hugging Face in the JustData/Mixtral_Erotic-13Bx2-MOE-22B-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 Erotic 13Bx2 MOE 22B use?

Hugging Face lists the license as cc-by-nc-4.0. 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 JustData

All by JustData →

More Mistral models

All Mistral →

Other medium models

All medium models →