SA

Saily_100B

SailyGGUF by RichardErkhovUpdated 2024-10-25
Download on Hugging Face
Parameters118B
Context4K
Layers137
Architecturellama
Smallest quant43.2 GB
Quick answer

Saily_100B needs about 75.7 GB of memory at Q4_K_M (a 70.6 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 22 quants, from 43.2 GB (Q2_K) to 125.1 GB (Q8_0).

Saily_100B is a 118B-parameter Saily model in GGUF format, quantized by RichardErkhov. Its trained context length is 4K tokens. The repository has 22 quant files, from 43.2 GB (Q2_K) to 125.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K43.2 GB (2 parts) 46.0 GB
Too big Get file →
IQ3_XS48.1 GB (2 parts) 50.9 GB
Too big Get file →
Q3_K_S50.7 GB (2 parts) 53.5 GB
Too big Get file →
IQ3_S50.9 GB (2 parts) 53.7 GB
Too big Get file →
IQ3_M52.6 GB (2 parts) 55.4 GB
Too big Get file →
Q3_K56.6 GB (2 parts) 59.4 GB
Too big Get file →
Q3_K_M56.6 GB (2 parts) 59.4 GB
Too big Get file →
Q3_K_L61.7 GB (2 parts) 64.5 GB
Too big Get file →
IQ4_XS63.4 GB (2 parts) 66.2 GB
Too big Get file →
Q4_066.3 GB (2 parts) 69.1 GB
Too big Get file →
Q4_K_S66.8 GB (2 parts) 69.6 GB
Too big Get file →
IQ4_NL67.0 GB (2 parts) 69.8 GB
Too big Get file →
Q4_K70.6 GB (2 parts) 73.4 GB
Too big Get file →
Q4_K_M70.6 GB (2 parts) 73.4 GB
Too big Get file →
Q4_173.7 GB (2 parts) 76.5 GB
Too big Get file →
Q5_081.0 GB (3 parts) 83.8 GB
Too big Get file →
Q5_K_S81.0 GB (3 parts) 83.8 GB
Too big Get file →
Q5_K83.2 GB (3 parts) 86.0 GB
Too big Get file →
Q5_K_M83.2 GB (3 parts) 86.0 GB
Too big Get file →
Q5_188.3 GB (3 parts) 91.1 GB
Too big Get file →
Q6_K96.6 GB (3 parts) 99.4 GB
Too big Get file →
Q8_0125.1 GB (4 parts) 127.9 GB
Too big Get file →

What GPU do you need for Saily_100B?

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: no quant fits at an 8K context.

Which Saily_100B quant should you choose?

Q4_K_M is the usual starting point for Saily_100B: it balances file size and quality well. Here it is a 70.6 GB file.

The Q8_0 file is 125.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 43.2 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
Parameters118B
Layers137
Trained context4,096 tokens
KV cache (fp16)548 KB per token

Source

Quantized byRichardErkhov
FamilySaily
Licensemit
Downloads (HF)4
Last updated2024-10-25

Frequently asked questions about Saily_100B

How much VRAM does Saily_100B need?

About 75.7 GB at Q4_K_M with an 8K context window. That is the 70.6 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 Saily_100B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 48.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Saily_100B GGUF?

It depends on the quant: Q2_K is 43.2 GB, IQ3_XS is 48.1 GB, Q3_K_S is 50.7 GB, IQ3_S is 50.9 GB, IQ3_M is 52.6 GB, Q3_K is 56.6 GB and 16 more.

What context length does Saily_100B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.6 GB at 8K and 2.3 GB at 4K.

Where can I download Saily_100B GGUF?

The files are on Hugging Face in the RichardErkhov/deepnight-research_-_saily_100b-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 Saily_100B 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.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Saily models

All Saily →

Other large models

All large models →