CR

CrystalMistral 14b

CrystalmistralGGUF by CrystalcareaiUpdated 2024-02-12
Download on Hugging Face
Parameters14.2B
Context32K
Layers64
Architecturellama
Smallest quant10.1 GB
Quick answer

CrystalMistral 14b needs about 12.7 GB of memory at Q5_K_M (a 10.1 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 8.6 GB.

CrystalMistral 14b is a 14.2B-parameter Crystalmistral model in GGUF format, quantized by Crystalcareai. Its trained context length is 32K tokens. The repository has 1 quant file, from 10.1 GB (Q5_K_M) to 10.1 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_M10.1 GB 12.7 GB
Too big Get file →

What GPU do you need for CrystalMistral 14b?

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 Q5_K_M (10.1 GB file, about 12.7 GB in use).

Which CrystalMistral 14b quant should you choose?

Q5_K_M (10.1 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters14.2B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized byCrystalcareai
Downloads (HF)7
Last updated2024-02-12

Frequently asked questions about CrystalMistral 14b

How much VRAM does CrystalMistral 14b need?

About 12.7 GB at Q5_K_M with an 8K context window. That is the 10.1 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 CrystalMistral 14b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of CrystalMistral 14b GGUF?

It depends on the quant: Q5_K_M is 10.1 GB.

What context length does CrystalMistral 14b support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download CrystalMistral 14b GGUF?

The files are on Hugging Face in the Crystalcareai/CrystalMistral-14b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from Crystalcareai

All by Crystalcareai →

More Crystalmistral models

All Crystalmistral →

Other medium models

All medium models →