MI

Mistral 22B v0.2 Q4 K S

MistralGGUF by Cran-MayUpdated 2024-04-13
Download on Hugging Face
Parameters22.2B
Context64K
Layers56
Architecturellama
Smallest quant12.7 GB
Quick answer

Mistral 22B v0.2 Q4 K S needs about 15.0 GB of memory at Q4_K_S (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Mistral 22B v0.2 Q4 K S is a 22.2B-parameter Mistral model in GGUF format, quantized by Cran-May. Its trained context length is 64K tokens. The repository has 1 quant file, from 12.7 GB (Q4_K_S) to 12.7 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S12.7 GB 15.0 GB
Too big Get file →

What GPU do you need for Mistral 22B v0.2 Q4 K S?

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 Q4_K_S (12.7 GB file, about 15.0 GB in use).

Which Mistral 22B v0.2 Q4 K S quant should you choose?

Q4_K_S (12.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context65,536 tokens
KV cache (fp16)224 KB per token

Source

Quantized byCran-May
FamilyMistral
Licenseapache-2.0
Downloads (HF)16
Last updated2024-04-13

Frequently asked questions about Mistral 22B v0.2 Q4 K S

How much VRAM does Mistral 22B v0.2 Q4 K S need?

About 15.0 GB at Q4_K_S with an 8K context window. That is the 12.7 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 Mistral 22B v0.2 Q4 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral 22B v0.2 Q4 K S GGUF?

It depends on the quant: Q4_K_S is 12.7 GB.

What context length does Mistral 22B v0.2 Q4 K S support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Mistral 22B v0.2 Q4 K S GGUF?

The files are on Hugging Face in the Cran-May/Mistral-22B-v0.2-Q4_K_S-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 22B v0.2 Q4 K S 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 Cran-May

All by Cran-May →

More Mistral models

All Mistral →

Other medium models

All medium models →