EX

EXAONE 4.5 33B DASHQ Q2

ExaoneGGUF by jkim96Updated 2026-10-04
Download on Hugging Face
Parameters32.5B
Context256K
Layers64
Architectureexaone4
Smallest quant9.1 GB
Quick answer

EXAONE 4.5 33B DASHQ Q2 needs about 13.0 GB of memory at IQ2_XS (a 10.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 9.1 GB (IQ2_XXS) to 12.5 GB (Q2_K_XL). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

EXAONE 4.5 33B DASHQ Q2 – 2‑bit GGUF for large‑context language tasks

EXAONE 4.5 33B DASHQ Q2 is a 2‑bit quantized GGUF model based on the 33B Exaone architecture. It supports up to 262,144 context tokens and is optimized for llama.cpp. The vision encoder is excluded from the GGUF file.

Good at

  • Large‑context text generation
  • Document understanding
  • Korean contextual reasoning

Limits

  • No vision support in GGUF
  • Requires 8k context for memory estimates
  • License inherited from base model

Best for

  • Chatbots needing long context
  • Document summarization
  • Research prototyping

Who it’s for. Developers building low‑memory LLM applications who need a large‑context model. The model is suitable for those who can run llama.cpp with 2‑bit quantization and have a GPU or CPU with sufficient VRAM for the chosen quant.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.1 GB 11.7 GB
Too big Get file →
IQ2_XS10.4 GB 13.0 GB
Too big Get file →
IQ2_M11.3 GB 14.0 GB
Too big Get file →
Q2_K_XL12.5 GB 15.1 GB
Too big Get file →

For 8 GB VRAM, use IQ2_XXS (file size 9.1 GB, ~11.7 GB memory at 8k context). For 12 GB VRAM, IQ2_XS (10.39 GB, ~13 GB). For 16 GB VRAM, IQ2_M (11.34 GB, ~14 GB). For 20 GB VRAM, Q2_K_XL (12.46 GB, ~15.1 GB). Estimates are approximate.

What GPU do you need for EXAONE 4.5 33B DASHQ Q2?

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: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.1 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_XL (12.5 GB file, about 15.1 GB in use).

Which EXAONE 4.5 33B DASHQ Q2 quant should you choose?

IQ2_XS (10.4 GB) is the middle option in this repository. 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.

If memory is tight, the smallest file is IQ2_XXS at 9.1 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

Architectureexaone4
Parameters32.5B
Layers64
Trained context262,144 tokens
KV cache (fp16)256 KB per token

Source

Quantized byjkim96
FamilyExaone
Licenseother
Downloads (HF)194
Last updated2026-10-04

Frequently asked questions about EXAONE 4.5 33B DASHQ Q2

How much VRAM does EXAONE 4.5 33B DASHQ Q2 need?

About 13.0 GB at IQ2_XS with an 8K context window. That is the 10.4 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 4.5 33B DASHQ Q2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of EXAONE 4.5 33B DASHQ Q2 GGUF?

It depends on the quant: IQ2_XXS is 9.1 GB, IQ2_XS is 10.4 GB, IQ2_M is 11.3 GB, Q2_K_XL is 12.5 GB.

What context length does EXAONE 4.5 33B DASHQ Q2 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download EXAONE 4.5 33B DASHQ Q2 GGUF?

The files are on Hugging Face in the jkim96/EXAONE-4.5-33B-DASHQ-Q2-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 4.5 33B DASHQ Q2 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 this model on 8 GB VRAM?

Yes, the IQ2_XXS quantization uses 9.1 GB file size and requires about 11.7 GB memory at 8k context, which fits an 8 GB VRAM GPU with swap.

Does the GGUF file include the vision encoder?

No, the GGUF file contains only the language model; the vision tower is not included.

What is the maximum context length?

The model supports up to 262,144 tokens, but memory usage scales with context size.

Other GGUFs of EXAONE-4.5-33B

Similar models

Browse all →

More from jkim96

All by jkim96 →

More Exaone models

All Exaone →

Other medium models

All medium models →