RY

RYS Huge

RysGGUF by mradermacherUpdated 2025-04-26
Download on Hugging Face
Parameters104B
Context32K
Layers116
Architectureqwen2
Smallest quant32.3 GB
Quick answer

RYS Huge needs about 46.3 GB of memory at IQ2_M (a 41.9 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 32.3 GB (IQ1_S) to 49.2 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 15.6 GB.

RYS Huge is a 104B-parameter Rys model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 12 quant files, from 32.3 GB (IQ1_S) to 49.2 GB (IQ3_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S32.3 GB 36.7 GB
Too big Get file →
IQ1_M33.9 GB 38.2 GB
Too big Get file →
IQ2_XXS36.4 GB 40.8 GB
Too big Get file →
IQ2_XS38.7 GB 43.1 GB
Too big Get file →
IQ2_S39.9 GB 44.3 GB
Too big Get file →
IQ2_M41.9 GB 46.3 GB
Too big Get file →
Q2_K_S42.1 GB 46.5 GB
Too big Get file →
Q2_K42.5 GB 46.9 GB
Too big Get file →
IQ3_XXS45.4 GB 49.8 GB
Too big Get file →
IQ3_XS46.8 GB 51.2 GB
Too big Get file →
Q3_K_S49.1 GB 53.4 GB
Too big Get file →
IQ3_S49.2 GB 53.6 GB
Too big Get file →

What GPU do you need for RYS Huge?

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: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is Q2_K (42.5 GB file, about 46.9 GB in use).

Which RYS Huge quant should you choose?

IQ2_M (41.9 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

If memory is tight, the smallest file is IQ1_S at 32.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters104B
Layers116
Trained context32,768 tokens
KV cache (fp16)464 KB per token

Source

Quantized bymradermacher
FamilyRys
Base modeldnhkng/RYS-Huge
Licensemit
Downloads (HF)95
Last updated2025-04-26

Frequently asked questions about RYS Huge

How much VRAM does RYS Huge need?

About 46.3 GB at IQ2_M with an 8K context window. That is the 41.9 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 RYS Huge on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 36.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RYS Huge GGUF?

It depends on the quant: IQ1_S is 32.3 GB, IQ1_M is 33.9 GB, IQ2_XXS is 36.4 GB, IQ2_XS is 38.7 GB, IQ2_S is 39.9 GB, IQ2_M is 41.9 GB and 6 more.

What context length does RYS Huge support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.9 GB at 8K and 15.6 GB at 32K.

Where can I download RYS Huge GGUF?

The files are on Hugging Face in the mradermacher/RYS-Huge-i1-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 RYS Huge 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-Huge

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Rys models

All Rys →

Other large models

All large models →