ME

MermaidMixtral-3x7b

MermaidmixtralGGUF by danielusUpdated 2024-04-02
Download on Hugging Face
Parameters18.5B
Context32K
Layers32
Architecturellama
Smallest quant19.7 GB
Quick answer

MermaidMixtral-3x7b needs about 21.2 GB of memory at Q8_0 (a 19.7 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.

MermaidMixtral-3x7b is a 18.5B-parameter Mermaidmixtral model in GGUF format, quantized by danielus. Its trained context length is 32K tokens. The repository has 1 quant file, from 19.7 GB (Q8_0) to 19.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_019.7 GB 21.2 GB
Too big Get file →

What GPU do you need for MermaidMixtral-3x7b?

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 Q8_0 (19.7 GB file, about 21.2 GB in use).

Which MermaidMixtral-3x7b quant should you choose?

Q8_0 (19.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.5B (approximate, mixture of experts)
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bydanielus
Licensecc-by-4.0
Downloads (HF)23
Last updated2024-04-02

Frequently asked questions about MermaidMixtral-3x7b

How much VRAM does MermaidMixtral-3x7b need?

About 21.2 GB at Q8_0 with an 8K context window. That is the 19.7 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 MermaidMixtral-3x7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 21.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of MermaidMixtral-3x7b GGUF?

It depends on the quant: Q8_0 is 19.7 GB.

What context length does MermaidMixtral-3x7b 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 MermaidMixtral-3x7b GGUF?

The files are on Hugging Face in the danielus/MermaidMixtral-3x7b-Q8_0-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 MermaidMixtral-3x7b use?

Hugging Face lists the license as cc-by-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 danielus

All by danielus →

More Mermaidmixtral models

All Mermaidmixtral →

Other medium models

All medium models →