EX

EXAONE-4.0-1.2B

ExaoneGGUF by LGAI-EXAONEUpdated 2025-08-01
Download on Hugging Face
Parameters1.28B
Context64K
Layers30
Architectureexaone4
Smallest quant0.8 GB
Quick answer

EXAONE-4.0-1.2B needs about 1.8 GB of memory at Q4_K_M (a 0.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.8 GB (IQ4_XS) to 2.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.0 GB.

EXAONE‑4.0‑1.2B: a small‑size, 1.3B‑parameter model for on‑device use

EXAONE‑4.0‑1.2B is a 1.3B‑parameter model in the Exaone family. It supports a context length of 65,536 tokens and offers both non‑reasoning and reasoning modes. The model is available in several GGUF quantizations and is licensed under a flexible other license.

Good at

  • Reasoning mode with enable_thinking
  • Agentic tool use
  • Multilingual support for English, Korean, Spanish

Limits

  • No vision support
  • Requires 8,000‑token context for memory estimates
  • License is other, not open source

Best for

  • On‑device chat assistants
  • Local reasoning tasks
  • Small‑scale agentic applications

Who it’s for. Developers needing a lightweight, reasoning‑capable LLM for edge devices. The model is suitable for applications that require local inference without large GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS0.8 GB 1.8 GB
Fits Get file →
Q4_K_M0.8 GB 1.8 GB
Fits Get file →
Q5_K_M0.9 GB 1.9 GB
Fits Get file →
Q6_K1.1 GB 2.1 GB
Fits Get file →
Q8_01.4 GB 2.4 GB
Fits Get file →
BF162.6 GB 3.6 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS or Q4_K_M (est. 1.8 GB at 8k context). For 12 GB VRAM, Q5_K_M or Q6_K (est. 1.9–2.1 GB). If more memory is available, Q8_0 or BF16 can be used for higher precision.

What GPU do you need for EXAONE-4.0-1.2B?

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 BF16 (2.6 GB file, about 3.6 GB in use).

Which EXAONE-4.0-1.2B quant should you choose?

Q4_K_M is the usual starting point for EXAONE-4.0-1.2B: it balances file size and quality well. Here it is a 0.8 GB file.

The Q8_0 file is 1.4 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.

If memory is tight, the smallest file is IQ4_XS at 0.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureexaone4
Parameters1.28B
Layers30
Trained context65,536 tokens
KV cache (fp16)60 KB per token

Source

Quantized byLGAI-EXAONE
FamilyExaone
Licenseother
Downloads (HF)4,674
Last updated2025-08-01

Frequently asked questions about EXAONE-4.0-1.2B

How much VRAM does EXAONE-4.0-1.2B need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.8 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-4.0-1.2B on an 8 GB GPU?

Yes, with BF16: the 2.6 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EXAONE-4.0-1.2B GGUF?

It depends on the quant: IQ4_XS is 0.8 GB, Q4_K_M is 0.8 GB, Q5_K_M is 0.9 GB, Q6_K is 1.1 GB, Q8_0 is 1.4 GB, BF16 is 2.6 GB.

What context length does EXAONE-4.0-1.2B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.0 GB at 32K.

Where can I download EXAONE-4.0-1.2B GGUF?

The files are on Hugging Face in the LGAI-EXAONE/EXAONE-4.0-1.2B-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 EXAONE-4.0-1.2B 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‑4.0‑1.2B on 8 GB VRAM?

Yes, the IQ4_XS and Q4_K_M quantizations use about 1.8 GB of VRAM at an 8k context length.

Does the model support vision inputs?

No, the model does not include vision capabilities.

What context length does the model support?

The model supports up to 65,536 tokens of context.

Other GGUFs of EXAONE-4.0-1.2B

Similar models

Browse all →

More from LGAI-EXAONE

All by LGAI-EXAONE →

More Exaone models

All Exaone →

Other tiny models

All tiny models →