GR

granite 20b code instruct Q4 0

GraniteGGUF by NikolayKozloffUpdated 2024-05-07
Download on Hugging Face
Parameters20.1B
Context8K
Layers52
Architecturestarcoder
Smallest quant11.5 GB
Quick answer

granite 20b code instruct Q4 0 needs about 12.2 GB of memory at Q4_0 (a 11.5 GB file) with an 8K context window, so it fits on a 16 GB GPU.

granite 20b code instruct Q4 0 is a 20.1B-parameter Granite model in GGUF format, quantized by NikolayKozloff. Its trained context length is 8K tokens. The repository has 1 quant file, from 11.5 GB (Q4_0) to 11.5 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_011.5 GB 12.2 GB
Too big Get file →

What GPU do you need for granite 20b code instruct Q4 0?

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_0 (11.5 GB file, about 12.2 GB in use).

Which granite 20b code instruct Q4 0 quant should you choose?

Q4_0 (11.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

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 byNikolayKozloff
FamilyGranite
Licenseapache-2.0
Downloads (HF)39
Last updated2024-05-07

Frequently asked questions about granite 20b code instruct Q4 0

How much VRAM does granite 20b code instruct Q4 0 need?

About 12.2 GB at Q4_0 with an 8K context window. That is the 11.5 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 instruct Q4 0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of granite 20b code instruct Q4 0 GGUF?

It depends on the quant: Q4_0 is 11.5 GB.

What context length does granite 20b code instruct Q4 0 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 instruct Q4 0 GGUF?

The files are on Hugging Face in the NikolayKozloff/granite-20b-code-instruct-Q4_0-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 instruct Q4 0 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.

Other GGUFs of granite-20b-code-base-8k

Similar models

Browse all →

More from NikolayKozloff

All by NikolayKozloff →

More Granite models

All Granite →

Other medium models

All medium models →