CO

codegen25 7b

CodegenGGUF by securecodegenUpdated 2024-02-19
Download on Hugging Face
Parameters6.9B
Context2K
Layers32
Architecturellama
Smallest quant27.6 GB
Quick answer

codegen25 7b needs about 32.4 GB of memory at its main file (a 27.6 GB file) with an 8K context window, so it fits on a 48 GB GPU.

codegen25 7b is a 6.9B-parameter Codegen model in GGUF format, quantized by securecodegen. Its trained context length is 2K tokens. The repository has 1 quant file, from 27.6 GB to 27.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—27.6 GB 29.2 GB
Too big Get file →

What GPU do you need for codegen25 7b?

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 the main file (27.6 GB file, about 32.4 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.9B
Layers32
Trained context2,048 tokens
KV cache (fp16)512 KB per token

Source

Quantized bysecurecodegen
FamilyCodegen
Downloads (HF)15
Last updated2024-02-19

Frequently asked questions about codegen25 7b

How much VRAM does codegen25 7b need?

About 32.4 GB at its main file with an 8K context window. That is the 27.6 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 codegen25 7b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 32.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of codegen25 7b GGUF?

It depends on the quant: file is 27.6 GB.

What context length does codegen25 7b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 4.3 GB at 8K and 1.1 GB at 2K.

Where can I download codegen25 7b GGUF?

The files are on Hugging Face in the securecodegen/codegen25-7b-gguf 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 Codegen models

All Codegen →

Other small models

All small models →