GR

Granite 8b Code Base

GraniteGGUF by RichardErkhovUpdated 2024-08-19
Download on Hugging Face
Parameters8.05B
Context4K
Layers36
Architecturellama
Smallest quant3.1 GB
Quick answer

Granite 8b Code Base needs about 6.6 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 22 quants, from 3.1 GB (Q2_K) to 8.6 GB (Q8_0).

Granite 8b Code Base – a 8.05B parameter code‑focused LLM

Granite 8b Code Base is a 8.05B parameter model built on the llama architecture. It is optimized for code generation and evaluation on programming benchmarks. The model is released under the apache-2.0 license.

Good at

  • Code generation
  • Programming language support
  • Code evaluation tasks

Limits

  • No vision support
  • Limited context to 4096 tokens
  • Requires 8.05B parameters

Best for

  • Writing code snippets
  • Debugging assistance
  • Automated code review

Who it’s for. Developers and researchers needing a lightweight code model for local inference. The model is suitable for integration into IDEs or CI pipelines where code generation is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.2 GB
Fits Get file →
IQ3_XS3.4 GB 4.5 GB
Fits Get file →
Q3_K_S3.5 GB 4.7 GB
Fits Get file →
IQ3_S3.6 GB 4.7 GB
Fits Get file →
IQ3_M3.7 GB 4.8 GB
Fits Get file →
Q3_K3.9 GB 5.0 GB
Fits Get file →
Q3_K_M3.9 GB 5.0 GB
Fits Get file →
Q3_K_L4.3 GB 5.4 GB
Fits Get file →
IQ4_XS4.4 GB 5.5 GB
Fits Get file →
Q4_04.6 GB 5.7 GB
Fits Get file →
Q4_K_S4.6 GB 5.7 GB
Fits Get file →
IQ4_NL4.6 GB 5.7 GB
Fits Get file →
Q4_K4.9 GB 6.0 GB
Fits Get file →
Q4_K_M4.9 GB 6.0 GB
Fits Get file →
Q4_15.1 GB 6.2 GB
Fits Get file →
Q5_05.6 GB 6.7 GB
Fits Get file →
Q5_K_S5.6 GB 6.7 GB
Fits Get file →
Q5_K5.7 GB 6.8 GB
Fits Get file →
Q5_K_M5.7 GB 6.8 GB
Fits Get file →
Q5_16.1 GB 7.2 GB
Fits Get file →
Q6_K6.6 GB 7.7 GB
Tight Get file →
Q8_08.6 GB 9.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 (file size 4.59 GB, estimated 6.3 GB memory). For 12 GB VRAM, Q5_0 (5.57 GB, 7.3 GB memory) or Q5_K (5.72 GB, 7.4 GB memory). For 16 GB VRAM, Q6_K (6.62 GB, 8.3 GB memory) or Q8_0 (8.57 GB, 10.3 GB memory) provide higher quality.

What GPU do you need for Granite 8b 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: the best quant that fits is Q3_K_L (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_1 (6.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.6 GB file, about 10.3 GB in use).

Which Granite 8b Code Base quant should you choose?

Q4_K_M is the usual starting point for Granite 8b Code Base: it balances file size and quality well. Here it is a 4.9 GB file.

The Q8_0 file is 8.6 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 3.1 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

Architecturellama
Parameters8.05B
Layers36
Trained context4,096 tokens
KV cache (fp16)144 KB per token

Source

Quantized byRichardErkhov
FamilyGranite
Licenseapache-2.0
Downloads (HF)2,446
Last updated2024-08-19

Frequently asked questions about Granite 8b Code Base

How much VRAM does Granite 8b Code Base need?

About 6.6 GB at Q4_K_M with an 8K context window. That is the 4.9 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 8b Code Base on an 8 GB GPU?

Yes, with Q5_1: the 6.1 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 8b Code Base GGUF?

It depends on the quant: Q2_K is 3.1 GB, IQ3_XS is 3.4 GB, Q3_K_S is 3.5 GB, IQ3_S is 3.6 GB, IQ3_M is 3.7 GB, Q3_K is 3.9 GB and 16 more.

What context length does Granite 8b Code Base support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.2 GB at 8K and 0.6 GB at 4K.

Where can I download Granite 8b Code Base GGUF?

The files are on Hugging Face in the RichardErkhov/ibm-granite_-_granite-8b-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 8b 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.

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

Yes, the Q4_0 quantization requires about 6.3 GB memory at 8k context, fitting within 8 GB VRAM.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

The model is released under the apache-2.0 license.

Similar models

Browse all →

More from RichardErkhov

All by RichardErkhov →

More Granite models

All Granite →

Other small models

All small models →