SA

Sao10K MN 12B Lyra v1

SaoGGUF by RichardErkhovUpdated 2024-08-05
Download on Hugging Face
Parameters12.2B
Context1000K
Layers—
Architecturellama
Smallest quant0.0 GB
Quick answer

Sao10K MN 12B Lyra v1 needs about 7.0 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 0.0 GB (Q8_0) to 7.8 GB (Q5_0).

Sao10K MN 12B Lyra v1 is a 12.2B-parameter Sao model in GGUF format, quantized by RichardErkhov. Its trained context length is 1000K tokens. The repository has 22 quant files, from 0.0 GB (Q8_0) to 7.8 GB (Q5_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.0 GB 0.5 GB
Fits Get file →
Q6_K0.0 GB 0.5 GB
Fits Get file →
Q5_10.0 GB 0.5 GB
Fits Get file →
Q5_K_M0.0 GB 0.5 GB
Fits Get file →
Q5_K0.6 GB 1.1 GB
Fits Get file →
IQ4_NL1.5 GB 2.2 GB
Fits Get file →
Q5_K_S1.8 GB 2.5 GB
Fits Get file →
Q4_K4.1 GB 5.1 GB
Fits Get file →
Q2_K4.8 GB 5.9 GB
Fits Get file →
Q4_K_S4.9 GB 5.9 GB
Fits Get file →
Q4_15.3 GB 6.4 GB
Fits Get file →
IQ3_XS5.3 GB 6.4 GB
Fits Get file →
Q3_K_S5.5 GB 6.7 GB
Fits Get file →
IQ3_S5.6 GB 6.7 GB
Fits Get file →
IQ3_M5.7 GB 6.9 GB
Fits Get file →
Q4_K_M5.8 GB 7.0 GB
Fits Get file →
Q3_K6.1 GB 7.3 GB
Tight Get file →
Q3_K_M6.1 GB 7.3 GB
Tight Get file →
Q3_K_L6.6 GB 7.8 GB
Tight Get file →
IQ4_XS6.8 GB 8.1 GB
Too big Get file →
Q4_07.1 GB 8.4 GB
Too big Get file →
Q5_07.8 GB 9.2 GB
Too big Get file →

What GPU do you need for Sao10K MN 12B Lyra v1?

These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q5_K_S (1.8 GB file, about 2.5 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_K_S (4.9 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q3_K_L (6.6 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_0 (7.8 GB file, about 9.2 GB in use).

Which Sao10K MN 12B Lyra v1 quant should you choose?

Q4_K_M is the usual starting point for Sao10K MN 12B Lyra v1: it balances file size and quality well. Here it is a 5.8 GB file.

The Q8_0 file is 0.0 GB, about 0.0 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 Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. 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

Architecturellama
Parameters12.2B
Trained context1,024,000 tokens

Source

Quantized byRichardErkhov
FamilySao
Downloads (HF)117
Last updated2024-08-05

Frequently asked questions about Sao10K MN 12B Lyra v1

How much VRAM does Sao10K MN 12B Lyra v1 need?

About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.8 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 Sao10K MN 12B Lyra v1 on an 8 GB GPU?

Yes, with Q3_K_L: the 6.6 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Sao10K MN 12B Lyra v1 GGUF?

It depends on the quant: Q8_0 is 0.0 GB, Q6_K is 0.0 GB, Q5_1 is 0.0 GB, Q5_K_M is 0.0 GB, Q5_K is 0.6 GB, IQ4_NL is 1.5 GB and 16 more.

What context length does Sao10K MN 12B Lyra v1 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K).

Where can I download Sao10K MN 12B Lyra v1 GGUF?

The files are on Hugging Face in the RichardErkhov/Sao10K_-_MN-12B-Lyra-v1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Sao models

All Sao →

Other medium models

All medium models →