EX

EXAONE 3.5 2.4B Instruct 2

ExaoneGGUF by ThomasBaruzierUpdated 2025-02-07
Download on Hugging Face
Parameters2.67B
Context32K
Layers30
Architectureexaone
Smallest quant0.7 GB
Quick answer

EXAONE 3.5 2.4B Instruct 2 needs about 2.8 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 28 quants, from 0.7 GB (IQ1_S) to 5.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.5 GB.

EXAONE 3.5 2.4B Instruct – 2.67B parameter instruction‑tuned model

EXAONE 3.5 2.4B Instruct is a 2.67B parameter instruction‑tuned model. It supports a context length of 32,768 tokens and is optimized for deployment on small or resource‑constrained devices. The model is available in multiple GGUF quantizations.

Good at

  • Instruction following
  • Long‑context handling
  • Bilingual English‑Korean support

Limits

  • No vision support
  • License type is other
  • Large memory requirement for higher quants

Best for

  • Chatbots on edge devices
  • Long‑form content generation
  • Multilingual support

Who it’s for. Developers building lightweight conversational agents or multilingual applications who need a small footprint model with long‑context capability. The model is suitable for environments with limited GPU memory but sufficient RAM for inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S0.7 GB 1.9 GB
Fits Get file →
IQ1_M0.8 GB 1.9 GB
Fits Get file →
IQ2_XXS0.8 GB 2.0 GB
Fits Get file →
IQ2_XS0.9 GB 2.0 GB
Fits Get file →
IQ2_S1.0 GB 2.1 GB
Fits Get file →
IQ2_M1.0 GB 2.2 GB
Fits Get file →
Q2_K_S1.0 GB 2.2 GB
Fits Get file →
Q2_K1.1 GB 2.2 GB
Fits Get file →
IQ3_XXS1.1 GB 2.2 GB
Fits Get file →
IQ3_XS1.2 GB 2.3 GB
Fits Get file →
Q3_K_S1.3 GB 2.4 GB
Fits Get file →
IQ3_S1.3 GB 2.4 GB
Fits Get file →
IQ3_M1.3 GB 2.4 GB
Fits Get file →
Q3_K_M1.4 GB 2.5 GB
Fits Get file →
Q3_K_L1.5 GB 2.6 GB
Fits Get file →
IQ4_XS1.5 GB 2.6 GB
Fits Get file →
Q4_01.6 GB 2.7 GB
Fits Get file →
IQ4_NL1.6 GB 2.7 GB
Fits Get file →
Q4_K_S1.6 GB 2.7 GB
Fits Get file →
Q4_K_M1.6 GB 2.8 GB
Fits Get file →
Q4_11.7 GB 2.9 GB
Fits Get file →
Q5_K_S1.9 GB 3.0 GB
Fits Get file →
Q5_01.9 GB 3.0 GB
Fits Get file →
Q5_K_M1.9 GB 3.0 GB
Fits Get file →
Q5_12.0 GB 3.2 GB
Fits Get file →
Q6_K2.2 GB 3.3 GB
Fits Get file →
Q8_02.8 GB 4.0 GB
Fits Get file →
F165.3 GB 6.5 GB
Fits Get file →

For 8 GB VRAM use IQ2_S (file size 0.97 GB, memory 2.1 GB). For 12 GB VRAM use Q4_K_M (file size 1.64 GB, memory 2.8 GB). For 16 GB VRAM use Q5_K_S (file size 1.87 GB, memory 3 GB). Estimates are approximate.

What GPU do you need for EXAONE 3.5 2.4B Instruct 2?

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 Q8_0 (2.8 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.0 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.3 GB file, about 6.5 GB in use).

Which EXAONE 3.5 2.4B Instruct 2 quant should you choose?

Q4_K_M is the usual starting point for EXAONE 3.5 2.4B Instruct 2: it balances file size and quality well. Here it is a 1.6 GB file.

The Q8_0 file is 2.8 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 IQ1_S at 0.7 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

Architectureexaone
Parameters2.67B
Layers30
Trained context32,768 tokens
KV cache (fp16)75 KB per token

Source

Quantized byThomasBaruzier
FamilyExaone
Licenseother
Downloads (HF)3,128
Last updated2025-02-07

Frequently asked questions about EXAONE 3.5 2.4B Instruct 2

How much VRAM does EXAONE 3.5 2.4B Instruct 2 need?

About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.6 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 3.5 2.4B Instruct 2 on an 8 GB GPU?

Yes, with F16: the 5.3 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of EXAONE 3.5 2.4B Instruct 2 GGUF?

It depends on the quant: IQ1_S is 0.7 GB, IQ1_M is 0.8 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.9 GB, IQ2_S is 1.0 GB, IQ2_M is 1.0 GB and 22 more.

What context length does EXAONE 3.5 2.4B Instruct 2 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.5 GB at 32K.

Where can I download EXAONE 3.5 2.4B Instruct 2 GGUF?

The files are on Hugging Face in the ThomasBaruzier/EXAONE-3.5-2.4B-Instruct-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 3.5 2.4B Instruct 2 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 3.5 2.4B Instruct on 8 GB VRAM?

Yes, using the IQ2_S or IQ1_M quantization, which requires about 2.1 GB of VRAM at 8 k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What is the maximum context length?

The model supports up to 32,768 tokens.

Similar models

Browse all →

More from ThomasBaruzier

All by ThomasBaruzier →

More Exaone models

All Exaone →

Other tiny models

All tiny models →