SA

saiganemoTestmix

SaiganemotestmixGGUF by hupimaodarenUpdated 2025-02-07
Download on Hugging Face
Parameters18.2B
Context1000K
Layers54
Architecturellama
Smallest quant17.1 GB
Quick answer

saiganemoTestmix needs about 20.5 GB of memory at its main file (a 18.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 17.1 GB to 19.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.2 GB.

saiganemoTestmix is a 18.2B-parameter Saiganemotestmix model in GGUF format, quantized by hupimaodaren. Its trained context length is 1000K tokens. The repository has 3 quant files, from 17.1 GB to 19.4 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—17.1 GB 19.4 GB
Too big Get file →
—18.2 GB 20.5 GB
Too big Get file →
—19.4 GB 21.7 GB
Too big Get file →

What GPU do you need for saiganemoTestmix?

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: the best quant that fits is the main file (19.4 GB file, about 21.7 GB in use).

Which saiganemoTestmix quant should you choose?

If memory is tight, the smallest file is the first one in the table at 17.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.2B
Layers54
Trained context1,024,000 tokens
KV cache (fp16)216 KB per token

Source

Quantized byhupimaodaren
Licenseunknown
Downloads (HF)6
Last updated2025-02-07

Frequently asked questions about saiganemoTestmix

How much VRAM does saiganemoTestmix need?

About 20.5 GB at its main file with an 8K context window. That is the 18.2 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 saiganemoTestmix on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 19.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of saiganemoTestmix GGUF?

It depends on the quant: file is 17.1 GB, file is 18.2 GB, file is 19.4 GB.

What context length does saiganemoTestmix 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 1.8 GB at 8K and 7.2 GB at 32K.

Where can I download saiganemoTestmix GGUF?

The files are on Hugging Face in the hupimaodaren/saiganemoTestmix repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does saiganemoTestmix use?

Hugging Face lists the license as unknown. 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 →

Other medium models

All medium models →