GR

Granite 20b Code Base 8k

GraniteGGUF by mradermacherUpdated 2024-09-04
Download on Hugging Face
Parameters20B
Context8K
Layers52
Architecturestarcoder
Smallest quant4.5 GB
Quick answer

Granite 20b Code Base 8k 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. This repository has 21 quants, from 4.5 GB (IQ1_S) to 16.6 GB (Q6_K).

Granite 20b Code Base 8k – 20B parameter code generation model

Granite 20b Code Base 8k is a decoder‑only model trained on 3 trillion code tokens and 500 billion mixed code and natural language tokens. It supports 8 k context length and is licensed under Apache 2.0. The model is intended for code‑centric tasks such as generation, explanation, and fixing.

Good at

  • Code generation
  • Code explanation
  • Code fixing

Limits

  • No vision support
  • Large memory requirement for higher‑quality quants
  • Not recommended for new projects

Best for

  • Generating unit tests
  • Documenting code
  • Detecting vulnerabilities

Who it’s for. Developers and researchers needing a large code‑focused model for historical or scientific studies. The model is available for those who prefer open‑source code models and are comfortable with its deprecation notice.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S4.5 GB 5.2 GB
Fits Get file →
IQ1_M4.9 GB 5.6 GB
Fits Get file →
IQ2_XXS5.6 GB 6.3 GB
Fits Get file →
IQ2_XS6.2 GB 6.9 GB
Fits Get file →
IQ2_S6.5 GB 7.2 GB
Tight Get file →
IQ2_M7.1 GB 7.8 GB
Tight Get file →
Q2_K7.9 GB 8.6 GB
Too big Get file →
IQ3_XXS8.1 GB 8.8 GB
Too big Get file →
IQ3_XS8.7 GB 9.4 GB
Too big Get file →
IQ3_S8.9 GB 9.7 GB
Too big Get file →
Q3_K_S8.9 GB 9.7 GB
Too big Get file →
IQ3_M9.6 GB 10.3 GB
Too big Get file →
Q3_K_M10.6 GB 11.3 GB
Too big Get file →
IQ4_XS10.9 GB 11.7 GB
Too big Get file →
Q4_011.6 GB 12.3 GB
Too big Get file →
Q4_K_S11.7 GB 12.4 GB
Too big Get file →
Q3_K_L11.7 GB 12.5 GB
Too big Get file →
Q4_K_M12.8 GB 13.5 GB
Too big Get file →
Q5_K_S14.0 GB 14.7 GB
Too big Get file →
Q5_K_M14.8 GB 15.5 GB
Too big Get file →
Q6_K16.6 GB 17.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (5.2 GB memory) or IQ1_M (5.6 GB). For 12 GB VRAM, IQ4_0 (12.3 GB) or Q4_K_S (12.4 GB) are suitable. Higher‑quality quants such as Q5_K_M (15.5 GB) require 16 GB or more. Memory estimates are approximate.

What GPU do you need for Granite 20b Code Base 8k?

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: the best quant that fits is IQ1_M (4.9 GB file, about 5.6 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ2_M (7.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ4_XS (10.9 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q5_K_M (14.8 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (16.6 GB file, about 17.4 GB in use).

Which Granite 20b Code Base 8k quant should you choose?

Q4_K_M is the usual starting point for Granite 20b Code Base 8k: it balances file size and quality well. Here it is a 12.8 GB file.

If memory is tight, the smallest file is IQ1_S at 4.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturestarcoder
Parameters20B
Layers52
Trained context8,192 tokens
KV cache (fp16)26 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,957
Last updated2024-09-04

Frequently asked questions about Granite 20b Code Base 8k

How much VRAM does Granite 20b Code Base 8k 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 8k on an 8 GB GPU?

Yes, with IQ2_M: the 7.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Granite 20b Code Base 8k GGUF?

It depends on the quant: IQ1_S is 4.5 GB, IQ1_M is 4.9 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.2 GB, IQ2_S is 6.5 GB, IQ2_M is 7.1 GB and 15 more.

What context length does Granite 20b Code Base 8k 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 8k GGUF?

The files are on Hugging Face in the mradermacher/granite-20b-code-base-8k-i1-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 8k 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.

Can I run Granite 20b Code Base 8k on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quant files will fit within 8 GB VRAM, with memory usage around 5.2–5.6 GB at 8 k context.

Does this model support image inputs?

No, the model has no vision capability and is purely text‑based.

Is this model suitable for new production projects?

No, the model is deprecated; newer Granite releases are recommended for new projects.

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

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other medium models

All medium models →