LL

RYS Llama3.1 Large

LlamaGGUF by mradermacherUpdated 2026-10-08
Download on Hugging Face
Parameters81.7B
Context128K
Layers93
Architecturellama
Smallest quant30.4 GB
Quick answer

RYS Llama3.1 Large needs about 52.7 GB of memory at Q4_K_M (a 49.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 30.4 GB (Q2_K) to 49.1 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 12.5 GB.

RYS Llama3.1 Large is a 81.7B-parameter Llama model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 7 quant files, from 30.4 GB (Q2_K) to 49.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K30.4 GB 34.0 GB
Too big Get file →
Q3_K_S35.5 GB 39.1 GB
Too big Get file →
Q3_K_M39.5 GB 43.1 GB
Too big Get file →
Q3_K_L43.0 GB 46.6 GB
Too big Get file →
IQ4_XS44.2 GB 47.9 GB
Too big Get file →
Q4_K_S46.6 GB 50.2 GB
Too big Get file →
Q4_K_M49.1 GB 52.7 GB
Too big Get file →

What GPU do you need for RYS Llama3.1 Large?

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 IQ4_XS (44.2 GB file, about 47.9 GB in use).

Which RYS Llama3.1 Large quant should you choose?

Q4_K_M is the usual starting point for RYS Llama3.1 Large: it balances file size and quality well. Here it is a 49.1 GB file.

If memory is tight, the smallest file is Q2_K at 30.4 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

Architecturellama
Parameters81.7B
Layers93
Trained context131,072 tokens
KV cache (fp16)372 KB per token

Source

Quantized bymradermacher
FamilyLlama
Licensemit
Downloads (HF)119
Last updated2026-10-08

Frequently asked questions about RYS Llama3.1 Large

How much VRAM does RYS Llama3.1 Large need?

About 52.7 GB at Q4_K_M with an 8K context window. That is the 49.1 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 RYS Llama3.1 Large on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 34.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of RYS Llama3.1 Large GGUF?

It depends on the quant: Q2_K is 30.4 GB, Q3_K_S is 35.5 GB, Q3_K_M is 39.5 GB, Q3_K_L is 43.0 GB, IQ4_XS is 44.2 GB, Q4_K_S is 46.6 GB and 1 more.

What context length does RYS Llama3.1 Large support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.1 GB at 8K and 12.5 GB at 32K.

Where can I download RYS Llama3.1 Large GGUF?

The files are on Hugging Face in the mradermacher/RYS-Llama3.1-Large-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 Llama3.1 Large 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-Llama3.1-Large

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other large models

All large models →