EX

exaone3.0 8b

ExaoneGGUF by swchoi1994Updated 2024-10-09
Download on Hugging Face
Parameters7.82B
Context4K
Layers32
Architectureexaone
Smallest quant3.2 GB
Quick answer

exaone3.0 8b needs about 9.9 GB of memory at Q4_0 (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.2 GB (TQ1_0) to 15.6 GB (BF16).

exaone3.0 8b is a 7.82B-parameter Exaone model in GGUF format, quantized by swchoi1994. Its trained context length is 4K tokens. The repository has 5 quant files, from 3.2 GB (TQ1_0) to 15.6 GB (BF16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
TQ1_03.2 GB 4.2 GB
Fits Get file →
TQ2_03.5 GB 4.5 GB
Fits Get file →
Q4_08.3 GB 9.3 GB
Too big Get file →
—8.3 GB 9.3 GB
Too big Get file →
BF1615.6 GB 16.7 GB
Too big Get file →

What GPU do you need for exaone3.0 8b?

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 TQ2_0 (3.5 GB file, about 5.1 GB in use).
  • 8 GB VRAM: the best quant that fits is TQ2_0 (3.5 GB file, about 5.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_0 (8.3 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_0 (8.3 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.6 GB file, about 17.2 GB in use).

Which exaone3.0 8b quant should you choose?

Q4_0 (8.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is TQ1_0 at 3.2 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureexaone
Parameters7.82B
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byswchoi1994
FamilyExaone
Licenseapache-2.0
Downloads (HF)52
Last updated2024-10-09

Frequently asked questions about exaone3.0 8b

How much VRAM does exaone3.0 8b need?

About 9.9 GB at Q4_0 with an 8K context window. That is the 8.3 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 exaone3.0 8b on an 8 GB GPU?

Yes, with TQ2_0: the 3.5 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 exaone3.0 8b GGUF?

It depends on the quant: TQ1_0 is 3.2 GB, TQ2_0 is 3.5 GB, Q4_0 is 8.3 GB, file is 8.3 GB, BF16 is 15.6 GB.

What context length does exaone3.0 8b support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download exaone3.0 8b GGUF?

The files are on Hugging Face in the swchoi1994/exaone3.0-8b-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 exaone3.0 8b 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.

Other GGUFs of EXAONE-3.0-7.8B-Instruct

Similar models

Browse all →

More Exaone models

All Exaone →

Other small models

All small models →