MA

Madlad_400_10B

MadladGGUF by lohopusikUpdated 2024-11-22
Download on Hugging Face
Parameters10.7B
Context512
Layers32
Architecturet5
Smallest quant6.2 GB
Quick answer

Madlad_400_10B needs about 11.0 GB of memory at its main file (a 6.2 GB file) with an 8K context window, so it fits on a 12 GB GPU.

Madlad_400_10B is a 10.7B-parameter Madlad model in GGUF format, quantized by lohopusik. Its trained context length is 512 tokens. The repository has 1 quant file, from 6.2 GB to 6.2 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—6.2 GB 6.9 GB
Fits Get file →

What GPU do you need for Madlad_400_10B?

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 the main file (6.2 GB file, about 11.0 GB in use).

Specifications

Architecture from the GGUF header

Architecturet5
Parameters10.7B
Layers32
Trained context512 tokens
KV cache (fp16)512 KB per token

Source

Quantized bylohopusik
FamilyMadlad
Licenseapache-2.0
Downloads (HF)13
Last updated2024-11-22

Frequently asked questions about Madlad_400_10B

How much VRAM does Madlad_400_10B need?

About 11.0 GB at its main file with an 8K context window. That is the 6.2 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 Madlad_400_10B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Madlad_400_10B GGUF?

It depends on the quant: file is 6.2 GB.

What context length does Madlad_400_10B support?

The GGUF header lists a trained context length of 512 tokens (512). The KV cache grows with the context you use: about 4.3 GB at 8K and 0.3 GB at 512.

Where can I download Madlad_400_10B GGUF?

The files are on Hugging Face in the lohopusik/madlad400-10b-q4-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 Madlad_400_10B 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 lohopusik

All by lohopusik →

More Madlad models

All Madlad →

Other medium models

All medium models →