EXAONE-Deep-7.8B needs about 6.3 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 6 quants, from 4.3 GB (IQ4_XS) to 15.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
EXAONE-Deep-7.8B: a 7.8B parameter reasoning model in GGUF format
EXAONE-Deep-7.8B is a 7.8B parameter language model optimized for reasoning tasks. It supports a context length of 32,768 tokens and is available in multiple GGUF quantizations. The model is released by LG AI Research and can be run with llama.cpp or other inference frameworks.
Good at
- Reasoning tasks such as math and coding
- Large context handling
- High accuracy on benchmark tests
Limits
- No vision support
- Requires 32,768 token context for full capability
- License type is other
Best for
- Chatbot reasoning
- Code generation
- Academic problem solving
Who it’s for. Developers and researchers needing a high‑performance reasoning model that can be deployed locally. The model is suitable for applications that require large context windows and precise logical inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 4.8 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.6 GB | 7.1 GB | Fits | Get file → | |
| Q6_K | 6.4 GB | 8.0 GB | Tight | Get file → | |
| Q8_0 | 8.3 GB | 9.9 GB | Too big | Get file → | |
| BF16 | 15.6 GB | 17.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ4_XS (4.34 GB) or Q4_K_M (4.77 GB). For 12 GB VRAM, Q5_K_M (5.57 GB) or Q6_K (6.42 GB) are suitable. For 16 GB VRAM, Q8_0 (8.31 GB) or BF16 (15.64 GB) can be used, keeping in mind the memory estimates are approximate.
What GPU do you need for EXAONE-Deep-7.8B?
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: the best quant that fits is IQ4_XS (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.3 GB file, about 9.9 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.6 GB file, about 17.2 GB in use).
Which EXAONE-Deep-7.8B quant should you choose?
Q4_K_M is the usual starting point for EXAONE-Deep-7.8B: it balances file size and quality well. Here it is a 4.8 GB file.
The Q8_0 file is 8.3 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 IQ4_XS at 4.3 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-Deep-7.8B
How much VRAM does EXAONE-Deep-7.8B need?
About 6.3 GB at Q4_K_M with an 8K context window. That is the 4.8 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-Deep-7.8B on an 8 GB GPU?
Yes, with Q6_K: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EXAONE-Deep-7.8B GGUF?
It depends on the quant: IQ4_XS is 4.3 GB, Q4_K_M is 4.8 GB, Q5_K_M is 5.6 GB, Q6_K is 6.4 GB, Q8_0 is 8.3 GB, BF16 is 15.6 GB.
What context length does EXAONE-Deep-7.8B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download EXAONE-Deep-7.8B GGUF?
The files are on Hugging Face in the LGAI-EXAONE/EXAONE-Deep-7.8B-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-Deep-7.8B 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-Deep-7.8B on 8 GB VRAM?
Yes, using the IQ4_XS or Q4_K_M quantizations will fit within 8 GB VRAM, with estimated memory usage around 5.9–6.3 GB at 8k context.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What is the maximum context length?
The model supports a context length of 32,768 tokens.