CY

Cydonia Mist 22B v1a

CydoniaGGUF by BeaverAIUpdated 2024-12-06
Download on Hugging Face
Parameters22.2B
Context128K
Layers56
Architecturellama
Smallest quant10.8 GB
Quick answer

Cydonia Mist 22B v1a needs about 15.7 GB of memory at Q4_K_M (a 13.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 5 quants, from 10.8 GB (Q3_K_M) to 44.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Cydonia Mist 22B v1a is a 22.2B-parameter Cydonia model in GGUF format, quantized by BeaverAI. Its trained context length is 128K tokens. The repository has 5 quant files, from 10.8 GB (Q3_K_M) to 44.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M10.8 GB 13.1 GB
Too big Get file →
Q4_K_M13.3 GB 15.7 GB
Too big Get file →
Q5_K_M15.7 GB 18.1 GB
Too big Get file →
Q6_K18.3 GB 20.6 GB
Too big Get file →
F1644.5 GB 46.9 GB
Too big Get file →

What GPU do you need for Cydonia Mist 22B v1a?

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_M (13.3 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (18.3 GB file, about 20.6 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (44.5 GB file, about 46.9 GB in use).

Which Cydonia Mist 22B v1a quant should you choose?

Q4_K_M is the usual starting point for Cydonia Mist 22B v1a: it balances file size and quality well. Here it is a 13.3 GB file.

If memory is tight, the smallest file is Q3_K_M at 10.8 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context131,072 tokens
KV cache (fp16)224 KB per token

Source

Quantized byBeaverAI
FamilyCydonia
Downloads (HF)39
Last updated2024-12-06

Frequently asked questions about Cydonia Mist 22B v1a

How much VRAM does Cydonia Mist 22B v1a need?

About 15.7 GB at Q4_K_M with an 8K context window. That is the 13.3 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 Cydonia Mist 22B v1a on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Cydonia Mist 22B v1a GGUF?

It depends on the quant: Q3_K_M is 10.8 GB, Q4_K_M is 13.3 GB, Q5_K_M is 15.7 GB, Q6_K is 18.3 GB, F16 is 44.5 GB.

What context length does Cydonia Mist 22B v1a support?

The GGUF header lists a trained context length of 131,072 tokens (128K). 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 Cydonia Mist 22B v1a GGUF?

The files are on Hugging Face in the BeaverAI/Cydonia-Mist-22B-v1a-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 BeaverAI

All by BeaverAI →

More Cydonia models

All Cydonia →

Other medium models

All medium models →