EXAONE 3.0 7.8B Instruct 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 31 quants, from 1.9 GB (IQ1_S) to 15.6 GB (F16).
EXAONE 3.0 7.8B Instruct – bilingual instruction‑tuned LLM
EXAONE 3.0 7.8B Instruct is a 7.82 billion‑parameter model trained on 8T curated tokens and fine‑tuned with supervised learning and preference optimization. It supports English and Korean prompts and is available in multiple GGUF quantizations.
Good at
- Instruction following
- Bilingual text generation
- Chat‑style interactions
Limits
- No vision support
- Requires 8 k context length
- License is other
Best for
- Chatbot development
- Content drafting
- Code explanation
Who it’s for. Developers building multilingual chat interfaces or content tools who need a 7.8 billion‑parameter model with instruction tuning. The model is suitable for applications that can run on a GPU with at least 8 GB VRAM and support for llama.cpp quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ1_M | 2.1 GB | 3.1 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 3.3 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 3.5 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 3.7 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 3.9 GB | Fits | Get file → | |
| Q2_K_S | 2.9 GB | 3.9 GB | Fits | Get file → | |
| Q2_K | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 4.2 GB | Fits | Get file → | |
| IQ3_XS | 3.4 GB | 4.4 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.6 GB | Fits | Get file → | |
| IQ3_S | 3.5 GB | 4.6 GB | Fits | Get file → | |
| IQ3_M | 3.6 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_M | 3.9 GB | 4.9 GB | Fits | Get file → | |
| Q3_K_L | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 5.3 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.5 GB | Fits | Get file → | |
| Q4_0 | 4.5 GB | 5.6 GB | Fits | Get file → | |
| IQ4_NL | 4.5 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.6 GB | Fits | Get file → | |
| Q4_K_M | 4.8 GB | 5.8 GB | Fits | Get file → | |
| Q4_1 | 5.0 GB | 6.0 GB | Fits | Get file → | |
| Q5_K_S | 5.4 GB | 6.5 GB | Fits | Get file → | |
| Q5_0 | 5.5 GB | 6.5 GB | Fits | Get file → | |
| Q5_K_M | 5.6 GB | 6.6 GB | Fits | Get file → | |
| Q5_1 | 5.9 GB | 6.9 GB | Fits | Get file → | |
| Q6_K | 6.4 GB | 7.5 GB | Tight | Get file → | |
| Q8_0 | 8.3 GB | 9.3 GB | Too big | Get file → | |
| F16 | 15.6 GB | 16.7 GB | Too big | Get file → |
For 8 GB VRAM use IQ1_S (1.91 GB, 3.5 GB memory) or IQ1_M (2.05 GB, 3.6 GB). With 12 GB VRAM IQ2_S (2.64 GB, 4.2 GB) or Q2_K (3.05 GB, 4.6 GB) are suitable. For 16 GB VRAM, Q3_K_M (3.88 GB, 5.5 GB) or Q4_K_M (4.77 GB, 6.3 GB) provide better quality.
What GPU do you need for EXAONE 3.0 7.8B 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: the best quant that fits is IQ2_XXS (2.3 GB file, about 3.9 GB in use).
- 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 F16 (15.6 GB file, about 17.2 GB in use).
Which EXAONE 3.0 7.8B Instruct quant should you choose?
Q4_K_M is the usual starting point for EXAONE 3.0 7.8B Instruct: 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 IQ1_S at 1.9 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
Frequently asked questions about EXAONE 3.0 7.8B Instruct
How much VRAM does EXAONE 3.0 7.8B Instruct 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 3.0 7.8B Instruct 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 3.0 7.8B Instruct GGUF?
It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.1 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 25 more.
What context length does EXAONE 3.0 7.8B Instruct support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.
Where can I download EXAONE 3.0 7.8B Instruct GGUF?
The files are on Hugging Face in the ThomasBaruzier/EXAONE-3.0-7.8B-Instruct-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 3.0 7.8B 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 3.0 7.8B Instruct on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with approximate memory usage of 3.5–3.6 GB.
Does the model support Korean language?
Yes, the model is bilingual and was trained with Korean data.
What is the context length supported by the model?
The model supports a context length of 4096 tokens.