FE

Fever Dream 22B v1.0 Q5 K S

FeverGGUF by markldnUpdated 2025-03-10
Download on Hugging Face
Parameters22.2B
Context128K
Layers56
Architecturellama
Smallest quant15.3 GB
Quick answer

Fever Dream 22B v1.0 Q5 K S needs about 17.7 GB of memory at Q5_K_S (a 15.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

Fever Dream 22B v1.0 Q5 K S is a 22.2B-parameter Fever model in GGUF format, quantized by markldn. Its trained context length is 128K tokens. The repository has 1 quant file, from 15.3 GB (Q5_K_S) to 15.3 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S15.3 GB 17.7 GB
Too big Get file →

What GPU do you need for Fever Dream 22B v1.0 Q5 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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q5_K_S (15.3 GB file, about 17.7 GB in use).

Which Fever Dream 22B v1.0 Q5 K S quant should you choose?

Q5_K_S (15.3 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
Parameters22.2B
Layers56
Trained context131,072 tokens
KV cache (fp16)224 KB per token

Source

Quantized bymarkldn
FamilyFever
Licenseother
Downloads (HF)4
Last updated2025-03-10

Frequently asked questions about Fever Dream 22B v1.0 Q5 K S

How much VRAM does Fever Dream 22B v1.0 Q5 K S need?

About 17.7 GB at Q5_K_S with an 8K context window. That is the 15.3 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 Fever Dream 22B v1.0 Q5 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Fever Dream 22B v1.0 Q5 K S GGUF?

It depends on the quant: Q5_K_S is 15.3 GB.

What context length does Fever Dream 22B v1.0 Q5 K S 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 Fever Dream 22B v1.0 Q5 K S GGUF?

The files are on Hugging Face in the markldn/Fever-Dream-22B-v1.0-Q5_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 Fever Dream 22B v1.0 Q5 K S 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 markldn

All by markldn →

More Fever models

All Fever →

Other medium models

All medium models →