MI

Codestral-22B-v0.1

MistralGGUF by kowlickUpdated 2024-06-11
Download on Hugging Face
Parameters22.2B
Context32K
Layers56
Architecturellama
Smallest quant23.6 GB
Quick answer

Codestral-22B-v0.1 needs about 26.0 GB of memory at Q8_0 (a 23.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Codestral-22B-v0.1 is a 22.2B-parameter Mistral model in GGUF format, quantized by kowlick. Its trained context length is 32K tokens. The repository has 1 quant file, from 23.6 GB (Q8_0) to 23.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_023.6 GB 26.0 GB
Too big Get file →

What GPU do you need for Codestral-22B-v0.1?

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 Q8_0 (23.6 GB file, about 26.0 GB in use).

Which Codestral-22B-v0.1 quant should you choose?

Q8_0 (23.6 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
Parameters22.2B
Layers56
Trained context32,768 tokens
KV cache (fp16)224 KB per token

Source

Quantized bykowlick
FamilyMistral
Licenseother
Downloads (HF)20
Last updated2024-06-11

Frequently asked questions about Codestral-22B-v0.1

How much VRAM does Codestral-22B-v0.1 need?

About 26.0 GB at Q8_0 with an 8K context window. That is the 23.6 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 Codestral-22B-v0.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 26.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Codestral-22B-v0.1 GGUF?

It depends on the quant: Q8_0 is 23.6 GB.

What context length does Codestral-22B-v0.1 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download Codestral-22B-v0.1 GGUF?

The files are on Hugging Face in the kowlick/Codestral-22B-v0.1-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 Codestral-22B-v0.1 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.

Other GGUFs of Codestral-22B-v0.1

Similar models

Browse all →

More from kowlick

All by kowlick →

More Mistral models

All Mistral →

Other medium models

All medium models →