Text model · EXAONE

EX EXAONE 4.0 32B: RAM and VRAM requirements

EXAONE 4.0 32B needs about 20.2 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~18.02 GB to download; KV cache and overhead add the rest), or about 33.9 GB at Q8_0. The lightest hardware that runs it is Nvidia GeForce RTX 4090 (24GB).

EXAONE family · 32B params · released Jul 2025.

Shopping for hardware? See what runs EXAONE 4.0 32B →

License EXAONE AI Model License Agreement 1.2 - NC · Non-commercial ↓ 27.2K/mo ♥ 282 on HuggingFace

Q4_K_M GGUF

18.02 GB

Q8_0 GGUF

31.67 GB

Memory @ Q4 (4k)

~20.2 GB

Context

131 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

EXAONE 4.0 32B runs on 13 of 40 tracked devices at Q4_K_M.

12 run well 1 tight fit 27 too small

Fit check Q4_K_M

Your device

Apple M4 (16GB)

No, not enough memory

needs 20.2 GB usable 10.5 GB

See the full breakdown

Memory breakdown

Weights (Q4_K_M)18.02 GB

KV cache (4k)1.4 GB

Overhead0.8 GB

Total20.2 GB

How context length changes it

4k context ~20.2 GB 32k context ~29.7 GB 128k context ~62.2 GB

Longer context grows the KV cache quickly: EXAONE 4.0 32B needs ~20.2 GB at 4k but ~62.2 GB at 128k, which can push it past a device that fits it at a short context.

Speed drops too: every token re-reads the KV cache, so at 128k context EXAONE 4.0 32B generates at roughly ~29% of its short-context speed. How this is estimated.

Quantization sizes

GGUF quantson disk

Quantization	Size on disk
Q2_K	13.4 GB est
Q3_K_M	15.6 GB est
Q4_K_M (default)	18.02 GB
Q5_K_M	22.8 GB est
Q6_K	26.2 GB est
Q8_0	31.67 GB
FP16	64.01 GB

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

llama.cpp

$ llama-cli -hf LGAI-EXAONE/EXAONE-4.0-32B-GGUF:Q4_K_M

LM Studio

$ lms get LGAI-EXAONE/EXAONE-4.0-32B-GGUF

Which devices can run EXAONE 4.0 32B?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down North Mini Code 1.0 30.5B Next size up Gemma 4 31B 32.7B

Similar models

FAQ

How much VRAM or RAM does EXAONE 4.0 32B need?

At Q4_K_M, EXAONE 4.0 32B needs about 20.2 GB (weights ~18.02 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~33.9 GB.

What is the Q4_K_M GGUF file size of EXAONE 4.0 32B?

The Q4_K_M GGUF file is about 18.02 GB to download, and the Q8_0 GGUF is about 31.67 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~20.2 GB of memory at Q4_K_M.

Can EXAONE 4.0 32B run on a laptop?

EXAONE 4.0 32B is large; you need a 24 GB+ GPU or a 32-48 GB Mac at Q4_K_M.

Can I use EXAONE 4.0 32B commercially?

No. EXAONE AI Model License Agreement 1.2 - NC: non-commercial / research use only.

Understand the numbers

Short guides to the ideas behind EXAONE 4.0 32B's memory and quant figures.

LG's 32B hybrid reasoning model, strong Korean and English. Non-commercial license.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.