GR

granite 20b code base

GraniteGGUF by cobrakenjiUpdated 2024-05-20
Download on Hugging Face
Parameters20.1B
Context8K
Layers52
Architecturestarcoder
Smallest quant12.8 GB
Quick answer

granite 20b code base needs about 13.5 GB of memory at Q4_K_M (a 12.8 GB file) with an 8K context window, so it fits on a 16 GB GPU.

granite 20b code base is a 20.1B-parameter Granite model in GGUF format, quantized by cobrakenji. Its trained context length is 8K tokens. The repository has 1 quant file, from 12.8 GB (Q4_K_M) to 12.8 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M12.8 GB 13.5 GB
Too big Get file →

What GPU do you need for granite 20b code base?

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: the best quant that fits is Q4_K_M (12.8 GB file, about 13.5 GB in use).

Which granite 20b code base quant should you choose?

Q4_K_M is the usual starting point for granite 20b code base: it balances file size and quality well. Here it is a 12.8 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder
Parameters20.1B
Layers52
Trained context8,192 tokens
KV cache (fp16)26 KB per token

Source

Quantized bycobrakenji
FamilyGranite
Licenseapache-2.0
Downloads (HF)96
Last updated2024-05-20

Frequently asked questions about granite 20b code base

How much VRAM does granite 20b code base need?

About 13.5 GB at Q4_K_M with an 8K context window. That is the 12.8 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 granite 20b code base on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of granite 20b code base GGUF?

It depends on the quant: Q4_K_M is 12.8 GB.

What context length does granite 20b code base support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.

Where can I download granite 20b code base GGUF?

The files are on Hugging Face in the cobrakenji/granite-20b-code-base-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 granite 20b code base 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 cobrakenji

All by cobrakenji →

More Granite models

All Granite →

Other medium models

All medium models →