RY

Medium

RysGGUF by dasChronos1Updated 2024-08-19
Download on Hugging Face
Parameters18.7B
Context4K
Layers54
Architecturephi3
Smallest quant19.9 GB
Quick answer

Medium needs about 22.7 GB of memory at Q8_0 (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU.

Medium is a 18.7B-parameter Rys model in GGUF format, quantized by dasChronos1. Its trained context length is 4K tokens. The repository has 1 quant file, from 19.9 GB (Q8_0) to 19.9 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_019.9 GB 21.5 GB
Too big Get file →

What GPU do you need for Medium?

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 Q8_0 (19.9 GB file, about 22.7 GB in use).

Which Medium quant should you choose?

Q8_0 (19.9 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

Architecturephi3
Parameters18.7B
Layers54
Trained context4,096 tokens
KV cache (fp16)270 KB per token

Source

Quantized bydasChronos1
FamilyRys
Licensemit
Downloads (HF)7
Last updated2024-08-19

Frequently asked questions about Medium

How much VRAM does Medium need?

About 22.7 GB at Q8_0 with an 8K context window. That is the 19.9 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 Medium on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 22.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Medium GGUF?

It depends on the quant: Q8_0 is 19.9 GB.

What context length does Medium support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.3 GB at 8K and 1.1 GB at 4K.

Where can I download Medium GGUF?

The files are on Hugging Face in the dasChronos1/RYS-Medium-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 Medium use?

Hugging Face lists the license as mit. 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 RYS-Medium

Similar models

Browse all →

More from dasChronos1

All by dasChronos1 →

More Rys models

All Rys →

Other medium models

All medium models →