BA

mx backup

BackupGGUF by KennissszUpdated 2026-05-15
Download on Hugging Face
Parameters8.19B
Context40K
Layers36
Architectureqwen3
Smallest quant4.8 GB
Quick answer

mx backup needs about 6.5 GB of memory at IQ4_NL (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

mx backup is a 8.19B-parameter Backup model in GGUF format, quantized by Kennisssz. Its trained context length is 40K tokens. The repository has 1 quant file, from 4.8 GB (IQ4_NL) to 4.8 GB (IQ4_NL).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_NL4.8 GB 6.5 GB
Fits Get file →

What GPU do you need for mx backup?

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: the best quant that fits is IQ4_NL (4.8 GB file, about 6.5 GB in use).

Which mx backup quant should you choose?

IQ4_NL (4.8 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

Architectureqwen3
Parameters8.19B
Layers36
Trained context40,960 tokens
KV cache (fp16)144 KB per token

Source

Quantized byKennisssz
FamilyBackup
Downloads (HF)8
Last updated2026-05-15

Frequently asked questions about mx backup

How much VRAM does mx backup need?

About 6.5 GB at IQ4_NL with an 8K context window. That is the 4.8 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 mx backup on an 8 GB GPU?

Yes, with IQ4_NL: the 4.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of mx backup GGUF?

It depends on the quant: IQ4_NL is 4.8 GB.

What context length does mx backup support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download mx backup GGUF?

The files are on Hugging Face in the Kennisssz/mx-backup 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 Backup models

All Backup →

Other small models

All small models →