EX

Exaone 3.0 7.8b It

ExaoneGGUF by BingsuUpdated 2024-08-13
Download on Hugging Face
Parameters7.82B
Context4K
Layers32
Architecturellama
Smallest quant4.8 GB
Quick answer

Exaone 3.0 7.8b It needs about 6.3 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 4.8 GB (Q4_K_M) to 31.3 GB (F32).

Exaone 3.0 7.8b It – a 7.82 billion‑parameter Llama‑style model

Exaone 3.0 7.8b It is a 7.82 billion‑parameter Llama architecture model trained on 4096 context tokens. It is available in multiple GGUF quantizations and supports text generation tasks.

Good at

  • Text completion
  • Chat‑style dialogue
  • Prompt‑based generation

Limits

  • No vision support
  • License type is other
  • No mixture of experts

Best for

  • Developers building lightweight chatbots
  • Researchers testing Llama‑style models
  • Users with limited GPU memory

Who it’s for. This model is suited for developers and researchers who need a moderately sized Llama‑style model for text generation. It is ideal when GPU memory is limited and a lightweight quantized version is preferred.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.8 GB 5.8 GB
Fits Get file →
Q5_K_M5.6 GB 6.6 GB
Fits Get file →
Q8_08.3 GB 9.3 GB
Too big Get file →
BF1615.6 GB 16.7 GB
Too big Get file →
F3231.3 GB 32.3 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (4.77 GB, ~6.3 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (5.57 GB, ~7.1 GB memory). For 16 GB VRAM use Q8_0 (8.31 GB, ~9.9 GB memory).

What GPU do you need for Exaone 3.0 7.8b It?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.6 GB file, about 7.1 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_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).
  • 32 GB VRAM: the best quant that fits is BF16 (15.6 GB file, about 17.2 GB in use).
  • 48 GB VRAM: the best quant that fits is F32 (31.3 GB file, about 32.9 GB in use).

Which Exaone 3.0 7.8b It quant should you choose?

Q4_K_M is the usual starting point for Exaone 3.0 7.8b It: it balances file size and quality well. Here it is a 4.8 GB file.

The Q8_0 file is 8.3 GB, about 1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

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

Source

Quantized byBingsu
FamilyExaone
Licenseother
Downloads (HF)574
Last updated2024-08-13

Frequently asked questions about Exaone 3.0 7.8b It

How much VRAM does Exaone 3.0 7.8b It need?

About 6.3 GB at Q4_K_M with an 8K context window. That is the 4.8 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 Exaone 3.0 7.8b It on an 8 GB GPU?

Yes, with Q5_K_M: the 5.6 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Exaone 3.0 7.8b It GGUF?

It depends on the quant: Q4_K_M is 4.8 GB, Q5_K_M is 5.6 GB, Q8_0 is 8.3 GB, BF16 is 15.6 GB, F32 is 31.3 GB.

What context length does Exaone 3.0 7.8b It 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 Exaone 3.0 7.8b It GGUF?

The files are on Hugging Face in the Bingsu/exaone-3.0-7.8b-it repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Exaone 3.0 7.8b It use?

Hugging Face lists the license as other. 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 Exaone 3.0 7.8b It on 8 GB VRAM?

Yes, the Q4_K_M quantization is 4.77 GB and requires about 6.3 GB of VRAM at 8k context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

Similar models

Browse all →

More from Bingsu

All by Bingsu →

More Exaone models

All Exaone →

Other small models

All small models →