EXAONE-4.0-32B 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 6 quants, from 17.4 GB (IQ4_XS) to 64.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
EXAONE‑4.0‑32B – 32B parameter model with hybrid attention and reasoning modes
EXAONE‑4.0‑32B is a 32B parameter language model with a 131,072 token context length. It supports both non‑reasoning and reasoning modes and includes agentic tool use. The model is available in several GGUF quantizations and is supported by llama.cpp.
Good at
- Hybrid local‑global attention
- Reasoning mode with enable_thinking
- Agentic tool use
Limits
- No vision support
- Large VRAM requirement for full precision
- License is other, not open source
Best for
- Complex reasoning tasks
- Agentic AI applications
- Long‑context document processing
Who it’s for. Developers building advanced AI agents or requiring long‑context reasoning. The model is suitable for users who can allocate sufficient VRAM and are comfortable with the provided quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 17.4 GB | 20.0 GB | Too big | Get file → | |
| Q4_K_M | 19.3 GB | 22.0 GB | Too big | Get file → | |
| Q5_K_M | 22.7 GB | 25.3 GB | Too big | Get file → | |
| Q6_K | 26.3 GB | 28.9 GB | Too big | Get file → | |
| Q8_0 | 34.0 GB | 36.7 GB | Too big | Get file → | |
| BF16 | 64.0 GB (2 parts) | 66.7 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (17.39 GB file, ~20 GB memory at 8k context). For 12 GB VRAM, Q4_K_M (19.34 GB file, ~22 GB memory). For 24 GB VRAM, Q6_K (26.26 GB file, ~28.9 GB memory). Full precision BF16 requires ~66.7 GB memory and 64.01 GB file split into two shards.
What GPU do you need for EXAONE-4.0-32B?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 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).
- 48 GB VRAM: the best quant that fits is Q8_0 (34.0 GB file, about 36.7 GB in use).
Which EXAONE-4.0-32B quant should you choose?
Q4_K_M is the usual starting point for EXAONE-4.0-32B: it balances file size and quality well. Here it is a 19.3 GB file.
The Q8_0 file is 34.0 GB, about 1.8 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 17.4 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
Source
Frequently asked questions about EXAONE-4.0-32B
How much VRAM does EXAONE-4.0-32B 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-4.0-32B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of EXAONE-4.0-32B GGUF?
It depends on the quant: IQ4_XS is 17.4 GB, Q4_K_M is 19.3 GB, Q5_K_M is 22.7 GB, Q6_K is 26.3 GB, Q8_0 is 34.0 GB, BF16 is 64.0 GB.
What context length does EXAONE-4.0-32B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). 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-4.0-32B GGUF?
The files are on Hugging Face in the LGAI-EXAONE/EXAONE-4.0-32B-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-4.0-32B 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‑4.0‑32B on 8 GB VRAM?
Use the IQ4_XS quantization; it requires about 20 GB memory at 8k context, which is beyond 8 GB VRAM, so it is not feasible.
Does the model support vision?
No, the model does not include vision capabilities.
What context length does the model support?
The model supports a context length of 131,072 tokens.