GR

Granite 8b Code Base 4k

GraniteGGUF by mradermacherUpdated 2024-09-04
Download on Hugging Face
Parameters8.05B
Context4K
Layers36
Architecturellama
Smallest quant3.1 GB
Quick answer

Granite 8b Code Base 4k 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 14 quants, from 3.1 GB (Q2_K) to 8.6 GB (Q8_0).

Granite 8b Code Base 4k – 8.05B parameter code generation model

Granite 8b Code Base 4k is a decoder‑only model with 8.05B parameters designed for code generative tasks. It was trained on 4 trillion tokens from 116 programming languages and 500 billion mixed code and natural language tokens. The model supports a 4096 token context and is released under Apache 2.0.

Good at

  • code generation
  • code explanation
  • code fixing

Limits

  • 4096 token context
  • not recommended for new projects
  • historical model

Best for

  • generating code snippets
  • debugging assistance
  • unit test creation

Who it’s for. Developers and enterprises that need a dedicated code generation model for a wide range of programming languages. The model is suitable for historical or scientific studies of code LLMs.

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_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_K_S4.6 GB 5.7 GB
Fits Get file →
Q4_K_M4.9 GB 6.0 GB
Fits Get file →
Q5_K_S5.6 GB 6.7 GB
Fits Get file →
Q5_K_M5.7 GB 6.8 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 8GB VRAM, use Q4_K_M (4.88GB file, 6.6GB memory). For 12GB VRAM, Q5_K_M (5.72GB file, 7.4GB memory). For 16GB VRAM, Q6_K (6.62GB file, 8.3GB memory). These estimates are approximate.

What GPU do you need for Granite 8b Code Base 4k?

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_K_M (5.7 GB file, about 7.4 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 4k quant should you choose?

Q4_K_M is the usual starting point for Granite 8b Code Base 4k: 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 bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)1,313
Last updated2024-09-04

Frequently asked questions about Granite 8b Code Base 4k

How much VRAM does Granite 8b Code Base 4k 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 4k 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 4k 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_M is 3.9 GB and 8 more.

What context length does Granite 8b Code Base 4k 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 4k GGUF?

The files are on Hugging Face in the mradermacher/granite-8b-code-base-4k-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 4k 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 4k on 8GB VRAM?

Yes, the Q4_K_M quant uses about 6.6GB of VRAM at 8k context, which fits within 8GB.

Is this model suitable for code translation tasks?

Yes, it was trained on code from 116 languages and can handle translation between them.

What license does the model use?

The model is released under the Apache 2.0 license.

Other GGUFs of granite-8b-code-base-4k

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →