GR

instructlab granite 7b lab trained

GraniteGGUF by SuranjanUpdated 2024-09-02
Download on Hugging Face
Parameters6.74B
Context4K
Layers—
Architecturellama
Smallest quant4.1 GB
Quick answer

instructlab granite 7b lab trained needs about 5.1 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 6 GB GPU.

instructlab granite 7b lab trained is a 6.74B-parameter Granite model in GGUF format, quantized by Suranjan. Its trained context length is 4K tokens. The repository has 1 quant file, from 4.1 GB (Q4_K_M) to 4.1 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.1 GB 4.8 GB
Fits Get file →

What GPU do you need for instructlab granite 7b lab trained?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q4_K_M (4.1 GB file, about 5.1 GB in use).

Which instructlab granite 7b lab trained quant should you choose?

Q4_K_M is the usual starting point for instructlab granite 7b lab trained: it balances file size and quality well. Here it is a 4.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.74B
Trained context4,096 tokens

Source

Quantized bySuranjan
FamilyGranite
Licenseunknown
Downloads (HF)0
Last updated2024-09-02

Frequently asked questions about instructlab granite 7b lab trained

How much VRAM does instructlab granite 7b lab trained need?

About 5.1 GB at Q4_K_M with an 8K context window. That is the 4.1 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 instructlab granite 7b lab trained on an 8 GB GPU?

Yes, with Q4_K_M: the 4.1 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of instructlab granite 7b lab trained GGUF?

It depends on the quant: Q4_K_M is 4.1 GB.

What context length does instructlab granite 7b lab trained support?

The GGUF header lists a trained context length of 4,096 tokens (4K).

Where can I download instructlab granite 7b lab trained GGUF?

The files are on Hugging Face in the Suranjan/instructlab-granite-7b-lab-trained repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does instructlab granite 7b lab trained use?

Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of granite-7b-lab

Similar models

Browse all →

More Granite models

All Granite →

Other small models

All small models →