MI

Franken Mistral Merlinite Maid 10B

MistralGGUF by ND911Updated 2024-03-13
Download on Hugging Face
Parameters10.5B
Context8K
Layers47
Architecturellama
Smallest quant11.2 GB
Quick answer

Franken Mistral Merlinite Maid 10B needs about 13.2 GB of memory at its main file (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Franken Mistral Merlinite Maid 10B is a 10.5B-parameter Mistral model in GGUF format, quantized by ND911. Its trained context length is 8K tokens. The repository has 1 quant file, from 11.2 GB to 11.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—11.2 GB 13.2 GB
Too big Get file →

What GPU do you need for Franken Mistral Merlinite Maid 10B?

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: the best quant that fits is the main file (11.2 GB file, about 13.2 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.5B
Layers47
Trained context8,192 tokens
KV cache (fp16)188 KB per token

Source

Quantized byND911
FamilyMistral
Downloads (HF)10
Last updated2024-03-13

Frequently asked questions about Franken Mistral Merlinite Maid 10B

How much VRAM does Franken Mistral Merlinite Maid 10B need?

About 13.2 GB at its main file with an 8K context window. That is the 11.2 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 Franken Mistral Merlinite Maid 10B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Franken Mistral Merlinite Maid 10B GGUF?

It depends on the quant: file is 11.2 GB.

What context length does Franken Mistral Merlinite Maid 10B support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.6 GB at 8K and 1.6 GB at 8K.

Where can I download Franken Mistral Merlinite Maid 10B GGUF?

The files are on Hugging Face in the ND911/Franken-Mistral-Merlinite-Maid-10B-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Franken-Merlinite-Maid

Similar models

Browse all →

More from ND911

All by ND911 →

More Mistral models

All Mistral →

Other medium models

All medium models →