GR

granite 8b code instruct 128k

GraniteGGUF by QuantFactoryUpdated 2024-09-07
Download on Hugging Face
Parameters8.05B
Context125K
Layers36
Architecturellama
Smallest quant3.1 GB
Quick answer

granite 8b code instruct 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 14 quants, from 3.1 GB (Q2_K) to 8.6 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

granite 8b code instruct 128k is a 8.05B-parameter Granite model in GGUF format, quantized by QuantFactory. Its trained context length is 125K tokens. The repository has 14 quant files, from 3.1 GB (Q2_K) to 8.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.1 GB 4.8 GB
Fits Get file →
Q3_K_S3.5 GB 5.3 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 →
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 →
Q4_15.1 GB 6.8 GB
Fits Get file →
Q5_05.6 GB 7.3 GB
Tight Get file →
Q5_K_S5.6 GB 7.3 GB
Tight Get file →
Q5_K_M5.7 GB 7.4 GB
Tight Get file →
Q5_16.1 GB 7.8 GB
Tight Get file →
Q6_K6.6 GB 8.3 GB
Too big Get file →
Q8_08.6 GB 10.3 GB
Too big Get file →

What GPU do you need for granite 8b code instruct 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: 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 instruct 128k quant should you choose?

Q4_K_M is the usual starting point for granite 8b code instruct 128k: 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 context128,000 tokens
KV cache (fp16)144 KB per token

Source

Quantized byQuantFactory
FamilyGranite
Licenseapache-2.0
Downloads (HF)432
Last updated2024-09-07

Frequently asked questions about granite 8b code instruct 128k

How much VRAM does granite 8b code instruct 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 instruct 128k 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 instruct 128k GGUF?

It depends on the quant: Q2_K is 3.1 GB, Q3_K_S is 3.5 GB, Q3_K_M is 3.9 GB, Q3_K_L is 4.3 GB, Q4_0 is 4.6 GB, Q4_K_S is 4.6 GB and 8 more.

What context length does granite 8b code instruct 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 instruct 128k GGUF?

The files are on Hugging Face in the QuantFactory/granite-8b-code-instruct-128k-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 instruct 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.

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Granite models

All Granite →

Other small models

All small models →