GR

Granite 8b Code Base 128k

GraniteGGUF by mradermacherUpdated 2024-09-04
Download on Hugging Face
Parameters8.05B
Context125K
Layers36
Architecturellama
Smallest quant1.8 GB
Quick answer

Granite 8b Code Base 128k 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 24 quants, from 1.8 GB (IQ1_S) to 6.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Granite 8b Code Base 128k – 8B parameter code model with 128K context

Granite 8b Code Base 128k extends the base Granite 8B Code model to a 128K token context window. It is trained on repository‑level code data and supports 116 programming languages. The model is released under Apache 2.0 and is intended for historical and scientific use.

Good at

  • Long‑context code generation
  • Code explanation
  • Code debugging

Limits

  • Large VRAM requirement for full context
  • No vision support
  • Not recommended for new projects

Best for

  • Generating unit tests for large codebases
  • Explaining legacy code with long context
  • Detecting vulnerabilities in extensive code

Who it’s for. Developers and researchers who need a code model with an extended context window for tasks such as code analysis, documentation, and vulnerability detection. The model is suitable for academic studies and legacy system support.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.8 GB 3.5 GB
Fits Get file →
IQ1_M2.0 GB 3.7 GB
Fits Get file →
IQ2_XXS2.2 GB 3.9 GB
Fits Get file →
IQ2_XS2.5 GB 4.2 GB
Fits Get file →
IQ2_S2.6 GB 4.3 GB
Fits Get file →
IQ2_M2.8 GB 4.5 GB
Fits Get file →
Q2_K3.1 GB 4.8 GB
Fits Get file →
IQ3_XXS3.2 GB 4.9 GB
Fits Get file →
IQ3_XS3.4 GB 5.1 GB
Fits Get file →
Q3_K_S3.5 GB 5.3 GB
Fits Get file →
IQ3_S3.6 GB 5.3 GB
Fits Get file →
IQ3_M3.7 GB 5.4 GB
Fits Get file →
Q3_K_M3.9 GB 5.7 GB
Fits Get file →
Q3_K_L4.3 GB 6.0 GB
Fits Get file →
IQ4_XS4.4 GB 6.1 GB
Fits Get file →
Q4_04.6 GB 6.3 GB
Fits Get file →
Q4_04.6 GB 6.3 GB
Fits Get file →
Q4_04.6 GB 6.3 GB
Fits Get file →
Q4_04.6 GB 6.3 GB
Fits Get file →
Q4_K_S4.6 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.6 GB
Fits Get file →
Q5_K_S5.6 GB 7.3 GB
Tight Get file →
Q5_K_M5.7 GB 7.4 GB
Tight Get file →
Q6_K6.6 GB 8.3 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (file size 1.81 GB or 1.97 GB, memory ~3.5–3.7 GB at 8 k context). For 12 GB VRAM, IQ2_S or IQ2_M (2.58 GB or 2.79 GB, memory ~4.3–4.5 GB). For 16 GB VRAM, Q3_K_S or Q3_K_M (3.55 GB or 3.94 GB, memory ~5.3–5.7 GB).

What GPU do you need for Granite 8b Code Base 128k?

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: the best quant that fits is IQ2_XXS (2.2 GB file, about 3.9 GB in use).
  • 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_K_M (5.7 GB file, about 7.4 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.3 GB in use).

Which Granite 8b Code Base 128k quant should you choose?

Q4_K_M is the usual starting point for Granite 8b Code Base 128k: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 1.8 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 context128,000 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)5,158
Last updated2024-09-04

Frequently asked questions about Granite 8b Code Base 128k

How much VRAM does Granite 8b Code Base 128k 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 128k on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.4 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 128k GGUF?

It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does Granite 8b Code Base 128k support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Granite 8b Code Base 128k GGUF?

The files are on Hugging Face in the mradermacher/granite-8b-code-base-128k-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 8b Code Base 128k 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 128k on 8 GB VRAM?

Yes, using the IQ1_S or IQ1_M quantized files, which require about 3.5–3.7 GB of VRAM at 8 k context.

Does this model support image inputs?

No, the model has no vision capabilities.

Is this model suitable for new production projects?

No, it is marked as deprecated and not recommended for new projects.

Other GGUFs of granite-8b-code-base-128k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →