SA

Saiga_Nemo_12B_Sft_M9_D14

SaigaGGUF by ktibrUpdated 2024-11-04
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant7.1 GB
Quick answer

Saiga_Nemo_12B_Sft_M9_D14 needs about 8.9 GB of memory at Q4_0 (a 7.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Saiga_Nemo_12B_Sft_M9_D14 is a 12.2B-parameter Saiga model in GGUF format, quantized by ktibr. Its trained context length is 1000K tokens. The repository has 1 quant file, from 7.1 GB (Q4_0) to 7.1 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.1 GB 8.9 GB
Too big Get file →

What GPU do you need for Saiga_Nemo_12B_Sft_M9_D14?

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: the best quant that fits is Q4_0 (7.1 GB file, about 8.9 GB in use).

Which Saiga_Nemo_12B_Sft_M9_D14 quant should you choose?

Q4_0 (7.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byktibr
FamilySaiga
Licenseapache-2.0
Downloads (HF)15
Last updated2024-11-04

Frequently asked questions about Saiga_Nemo_12B_Sft_M9_D14

How much VRAM does Saiga_Nemo_12B_Sft_M9_D14 need?

About 8.9 GB at Q4_0 with an 8K context window. That is the 7.1 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 Saiga_Nemo_12B_Sft_M9_D14 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Saiga_Nemo_12B_Sft_M9_D14 GGUF?

It depends on the quant: Q4_0 is 7.1 GB.

What context length does Saiga_Nemo_12B_Sft_M9_D14 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Saiga_Nemo_12B_Sft_M9_D14 GGUF?

The files are on Hugging Face in the ktibr/saiga_nemo_12b_sft_m9_d14_simpo_m21_d33-Q4_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 Saiga_Nemo_12B_Sft_M9_D14 use?

Hugging Face lists the license as apache-2.0. 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 ktibr

All by ktibr →

More Saiga models

All Saiga →

Other medium models

All medium models →