SC

school cyber2.1 13b v2.1 f32

SchoolGGUF by avaldezUpdated 2024-11-21
Download on Hugging Face
Parameters8.03B
Context128K
Layers32
Architecturellama
Smallest quant32.1 GB
Quick answer

school cyber2.1 13b v2.1 f32 needs about 33.7 GB of memory at F32 (a 32.1 GB file) with an 8K context window, so it fits on a 48 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

school cyber2.1 13b v2.1 f32 is a 8.03B-parameter School model in GGUF format, quantized by avaldez. Its trained context length is 128K tokens. The repository has 1 quant file, from 32.1 GB (F32) to 32.1 GB (F32).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F3232.1 GB 33.7 GB
Too big Get file →

What GPU do you need for school cyber2.1 13b v2.1 f32?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is F32 (32.1 GB file, about 33.7 GB in use).

Which school cyber2.1 13b v2.1 f32 quant should you choose?

F32 (32.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8.03B
Layers32
Trained context131,072 tokens
KV cache (fp16)128 KB per token

Source

Quantized byavaldez
FamilySchool
Licensellama3
Downloads (HF)6
Last updated2024-11-21

Frequently asked questions about school cyber2.1 13b v2.1 f32

How much VRAM does school cyber2.1 13b v2.1 f32 need?

About 33.7 GB at F32 with an 8K context window. That is the 32.1 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 school cyber2.1 13b v2.1 f32 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of school cyber2.1 13b v2.1 f32 GGUF?

It depends on the quant: F32 is 32.1 GB.

What context length does school cyber2.1 13b v2.1 f32 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download school cyber2.1 13b v2.1 f32 GGUF?

The files are on Hugging Face in the avaldez/school-cyber2.1-13b-v2.1-f32.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 school cyber2.1 13b v2.1 f32 use?

Hugging Face lists the license as llama3. 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 avaldez

All by avaldez →

More School models

All School →

Other small models

All small models →