MI

Mistral Large 218B Instruct

MistralGGUF by leafsparkUpdated 2024-07-30
Download on Hugging Face
Parameters218B
Context32K
Layers157
Architecturellama
Smallest quant0.0 GB
Quick answer

Mistral Large 218B Instruct needs about 5.8 GB of memory at BF16 (a 0.0 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 0.0 GB (BF16) to 0.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 21.1 GB.

Mistral Large 218B Instruct is a 218B-parameter Mistral model in GGUF format, quantized by leafspark. Its trained context length is 32K tokens. The repository has 2 quant files, from 0.0 GB (BF16) to 0.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF160.0 GB 5.8 GB
Fits Get file →
Q8_00.0 GB 5.8 GB
Fits Get file →

What GPU do you need for Mistral Large 218B Instruct?

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: the best quant that fits is BF16 (0.0 GB file, about 5.8 GB in use).

Which Mistral Large 218B Instruct quant should you choose?

BF16 (0.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters218B
Layers157
Trained context32,768 tokens
KV cache (fp16)628 KB per token

Source

Quantized byleafspark
FamilyMistral
Licenseother
Downloads (HF)10
Last updated2024-07-30

Frequently asked questions about Mistral Large 218B Instruct

How much VRAM does Mistral Large 218B Instruct need?

About 5.8 GB at BF16 with an 8K context window. That is the 0.0 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 Mistral Large 218B Instruct on an 8 GB GPU?

Yes, with BF16: the 0.0 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Mistral Large 218B Instruct GGUF?

It depends on the quant: BF16 is 0.0 GB, Q8_0 is 0.0 GB.

What context length does Mistral Large 218B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 5.3 GB at 8K and 21.1 GB at 32K.

Where can I download Mistral Large 218B Instruct GGUF?

The files are on Hugging Face in the leafspark/Mistral-Large-218B-Instruct-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 Mistral Large 218B Instruct use?

Hugging Face lists the license as other. 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 leafspark

All by leafspark →

More Mistral models

All Mistral →

Other large models

All large models →