LE

lemazz

LemazzGGUF by boblemazUpdated 2024-09-28
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant8.7 GB
Quick answer

lemazz needs about 10.6 GB of memory at its main file (a 8.7 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.

lemazz is a 12.2B-parameter Lemazz model in GGUF format, quantized by boblemaz. Its trained context length is 1000K tokens. The repository has 1 quant file, from 8.7 GB to 8.7 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.7 GB 10.6 GB
Too big Get file →

What GPU do you need for lemazz?

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 (8.7 GB file, about 10.6 GB in use).

Specifications

Architecture from the GGUF header

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

Source

Quantized byboblemaz
FamilyLemazz
Repositoryboblemaz/lemazz
Licenseapache-2.0
Downloads (HF)4
Last updated2024-09-28

Frequently asked questions about lemazz

How much VRAM does lemazz need?

About 10.6 GB at its main file with an 8K context window. That is the 8.7 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 lemazz on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of lemazz GGUF?

It depends on the quant: file is 8.7 GB.

What context length does lemazz 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 lemazz GGUF?

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

What license does lemazz 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 →

Other medium models

All medium models →