EX

Exaone3 instrucTrans v2 Enko 7.8b

ExaoneGGUF by mradermacherUpdated 2025-01-15
Download on Hugging Face
Parameters7.82B
Context8K
Layers32
Architecturellama
Smallest quant1.9 GB
Quick answer

Exaone3 instrucTrans v2 Enko 7.8b 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 24 quants, from 1.9 GB (IQ1_S) to 6.4 GB (Q6_K).

Exaone3 instrucTrans v2 Enko 7.8b – English to Korean translation

Exaone3 instrucTrans v2 Enko 7.8b is a 7.82B‑parameter llama model fine‑tuned for English‑to‑Korean translation. It was trained on multiple translation datasets and supports instruction‑style prompts. The model is available in GGUF format with a range of quantizations.

Good at

  • English to Korean translation
  • Instruction‑driven generation
  • Fine‑tuned translation datasets

Limits

  • No vision support
  • Context length limited to 8192 tokens
  • License not specified

Best for

  • Translation of technical documents
  • Generating Korean responses to English prompts
  • Low‑latency inference on edge devices

Who it’s for. Developers building translation tools or chatbots that require Korean output from English input. The model is suitable for applications where a dedicated translation model is preferred over general‑purpose LLMs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S1.9 GB 3.5 GB
Fits Get file →
IQ1_M2.1 GB 3.6 GB
Fits Get file →
IQ2_XXS2.3 GB 3.9 GB
Fits Get file →
IQ2_XS2.5 GB 4.1 GB
Fits Get file →
IQ2_S2.6 GB 4.2 GB
Fits Get file →
IQ2_M2.8 GB 4.4 GB
Fits Get file →
Q2_K_S2.9 GB 4.4 GB
Fits Get file →
Q2_K3.1 GB 4.6 GB
Fits Get file →
IQ3_XXS3.2 GB 4.7 GB
Fits Get file →
IQ3_XS3.4 GB 5.0 GB
Fits Get file →
Q3_K_S3.5 GB 5.1 GB
Fits Get file →
IQ3_S3.5 GB 5.1 GB
Fits Get file →
IQ3_M3.6 GB 5.2 GB
Fits Get file →
Q3_K_M3.9 GB 5.5 GB
Fits Get file →
Q3_K_L4.2 GB 5.8 GB
Fits Get file →
IQ4_XS4.3 GB 5.9 GB
Fits Get file →
Q4_04.5 GB 6.1 GB
Fits Get file →
IQ4_NL4.5 GB 6.1 GB
Fits Get file →
Q4_K_S4.5 GB 6.1 GB
Fits Get file →
Q4_K_M4.8 GB 6.3 GB
Fits Get file →
Q4_15.0 GB 6.5 GB
Fits Get file →
Q5_K_S5.4 GB 7.0 GB
Fits Get file →
Q5_K_M5.6 GB 7.1 GB
Fits Get file →
Q6_K6.4 GB 8.0 GB
Tight Get file →

For 8 GB VRAM use IQ1_S (file size 1.91 GB, estimated 3.5 GB memory). For 12 GB VRAM use Q4_K_M (file size 4.77 GB, estimated 6.3 GB memory). For 16 GB VRAM use Q5_K_M (file size 5.57 GB, estimated 7.1 GB memory). Estimates are approximate.

What GPU do you need for Exaone3 instrucTrans v2 Enko 7.8b?

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: the best quant that fits is IQ2_XXS (2.3 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.3 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 8.0 GB in use).

Which Exaone3 instrucTrans v2 Enko 7.8b quant should you choose?

Q4_K_M is the usual starting point for Exaone3 instrucTrans v2 Enko 7.8b: it balances file size and quality well. Here it is a 4.8 GB file.

If memory is tight, the smallest file is IQ1_S at 1.9 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
Parameters7.82B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyExaone
Downloads (HF)643
Last updated2025-01-15

Frequently asked questions about Exaone3 instrucTrans v2 Enko 7.8b

How much VRAM does Exaone3 instrucTrans v2 Enko 7.8b 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 Exaone3 instrucTrans v2 Enko 7.8b on an 8 GB GPU?

Yes, with Q6_K: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Exaone3 instrucTrans v2 Enko 7.8b GGUF?

It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.

What context length does Exaone3 instrucTrans v2 Enko 7.8b support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Exaone3 instrucTrans v2 Enko 7.8b GGUF?

The files are on Hugging Face in the mradermacher/exaone3-instrucTrans-v2-enko-7.8b-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_S quantization requires about 3.5 GB memory at 8192 context tokens, fitting within 8 GB VRAM.

Does this model support vision tasks?

No, the model is text‑only and does not include vision capabilities.

What context length does the model support?

The trained context length is 8192 tokens.

Other GGUFs of exaone3-instrucTrans-v2-enko-7.8b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Exaone models

All Exaone →

Other small models

All small models →