EX

EXAONE 3.5 32B Instruct

ExaoneGGUF by mradermacherUpdated 2024-12-09
Download on Hugging Face
Parameters32B
Context32K
Layers64
Architectureexaone
Smallest quant7.0 GB
Quick answer

EXAONE 3.5 32B Instruct needs about 22.0 GB of memory at Q4_K_M (a 19.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 7.0 GB (IQ1_S) to 26.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

EXAONE 3.5 32B Instruct – 32B bilingual instruction‑tuned model

EXAONE 3.5 32B Instruct is a 32B parameter model tuned for instruction following in English and Korean. It supports a context length of 32,768 tokens and is available in multiple GGUF quantizations.

Good at

  • Long‑context instruction following
  • Bilingual English/Korean generation
  • High‑parameter instruction performance

Limits

  • No vision support
  • License type is other
  • Requires large VRAM for full precision

Best for

  • Chatbot development
  • Long‑form content creation
  • Research prototyping

Who it’s for. Developers and researchers needing a large, instruction‑tuned bilingual model with extended context. Suitable for environments with sufficient GPU memory to run higher‑quality quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.0 GB 9.6 GB
Too big Get file →
IQ1_M7.6 GB 10.3 GB
Too big Get file →
IQ2_XXS8.7 GB 11.3 GB
Too big Get file →
IQ2_XS9.6 GB 12.3 GB
Too big Get file →
IQ2_S10.0 GB 12.7 GB
Too big Get file →
IQ2_M10.9 GB 13.5 GB
Too big Get file →
Q2_K_S11.1 GB 13.8 GB
Too big Get file →
Q2_K11.9 GB 14.6 GB
Too big Get file →
IQ3_XXS12.5 GB 15.1 GB
Too big Get file →
IQ3_XS13.3 GB 15.9 GB
Too big Get file →
Q3_K_S14.0 GB 16.6 GB
Too big Get file →
IQ3_S14.0 GB 16.7 GB
Too big Get file →
IQ3_M14.4 GB 17.0 GB
Too big Get file →
Q3_K_M15.5 GB 18.1 GB
Too big Get file →
Q3_K_L16.8 GB 19.4 GB
Too big Get file →
IQ4_XS17.2 GB 19.9 GB
Too big Get file →
Q4_018.2 GB 20.9 GB
Too big Get file →
Q4_K_S18.3 GB 20.9 GB
Too big Get file →
Q4_K_M19.3 GB 22.0 GB
Too big Get file →
Q5_K_S22.1 GB 24.7 GB
Too big Get file →
Q5_K_M22.7 GB 25.3 GB
Too big Get file →
Q6_K26.3 GB 28.9 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (6.96 GB) or IQ1_M (7.61 GB). For 12 GB VRAM, IQ2_XS (9.62 GB) or IQ2_S (10.03 GB) are suitable. For 16 GB VRAM, Q4_K_M (19.34 GB) or Q5_K_M (22.7 GB) provide higher quality. Memory estimates are approximate.

What GPU do you need for EXAONE 3.5 32B Instruct?

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 (8.7 GB file, about 11.3 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.3 GB file, about 15.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.3 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (26.3 GB file, about 28.9 GB in use).

Which EXAONE 3.5 32B Instruct quant should you choose?

Q4_K_M is the usual starting point for EXAONE 3.5 32B Instruct: it balances file size and quality well. Here it is a 19.3 GB file.

If memory is tight, the smallest file is IQ1_S at 7.0 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
Parameters32B
Layers64
Trained context32,768 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyExaone
Licenseother
Downloads (HF)662
Last updated2024-12-09

Frequently asked questions about EXAONE 3.5 32B Instruct

How much VRAM does EXAONE 3.5 32B Instruct need?

About 22.0 GB at Q4_K_M with an 8K context window. That is the 19.3 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 32B Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of EXAONE 3.5 32B Instruct GGUF?

It depends on the quant: IQ1_S is 7.0 GB, IQ1_M is 7.6 GB, IQ2_XXS is 8.7 GB, IQ2_XS is 9.6 GB, IQ2_S is 10.0 GB, IQ2_M is 10.9 GB and 16 more.

What context length does EXAONE 3.5 32B Instruct support?

The GGUF header lists a trained context length of 32,768 tokens (32K). 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 3.5 32B Instruct GGUF?

The files are on Hugging Face in the mradermacher/EXAONE-3.5-32B-Instruct-i1-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 32B Instruct 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 32B Instruct on 8 GB VRAM?

Use IQ1_S or IQ1_M quantizations; they fit within 8 GB VRAM with estimated memory usage of 9.6 GB and 10.3 GB respectively.

Does the model support vision tasks?

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

What context length does the model support?

The model supports up to 32,768 tokens of context.

Other GGUFs of EXAONE-3.5-32B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Exaone models

All Exaone →

Other medium models

All medium models →