EXAONE 3.5 2.4B Instruct needs about 2.8 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 1.5 GB (IQ4_XS) to 5.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.5 GB.
EXAONE 3.5 2.4B Instruct – instruction‑tuned bilingual LLM
EXAONE 3.5 2.4B Instruct is a 2.67B‑parameter model tuned for instruction following in English and Korean. It supports a 32,768‑token context window and is available in multiple GGUF precisions.
Good at
- Instruction following
- Long‑context reasoning
- Bilingual support
Limits
- No vision capability
- Requires 8,000‑token context for memory estimates
- License type not specified
Best for
- Chatbots on edge devices
- Document summarization
- Code generation
Who it’s for. Developers building lightweight conversational agents or applications that need bilingual instruction following on limited hardware. The model is suitable for research and production use where a 2.4B parameter size is desirable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 1.5 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.8 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 3.0 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q8_0 | 2.8 GB | 4.0 GB | Fits | Get file → | |
| BF16 | 5.3 GB | 6.5 GB | Fits | Get file → |
For 8 GB VRAM use IQ4_XS (1.51 GB, ~2.6 GB memory at 8k context) or Q4_K_M (1.64 GB, ~2.8 GB). For 12 GB VRAM Q5_K_M (1.91 GB, ~3 GB) or Q6_K (2.19 GB, ~3.3 GB). BF16 requires 5.34 GB and ~6.5 GB memory.
What GPU do you need for EXAONE 3.5 2.4B 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 Q8_0 (2.8 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.8 GB file, about 4.0 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.3 GB file, about 6.5 GB in use).
Which EXAONE 3.5 2.4B Instruct quant should you choose?
Q4_K_M is the usual starting point for EXAONE 3.5 2.4B Instruct: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.8 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 1.5 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
Frequently asked questions about EXAONE 3.5 2.4B Instruct
How much VRAM does EXAONE 3.5 2.4B Instruct need?
About 2.8 GB at Q4_K_M with an 8K context window. That is the 1.6 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 2.4B Instruct on an 8 GB GPU?
Yes, with BF16: the 5.3 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EXAONE 3.5 2.4B Instruct GGUF?
It depends on the quant: IQ4_XS is 1.5 GB, Q4_K_M is 1.6 GB, Q5_K_M is 1.9 GB, Q6_K is 2.2 GB, Q8_0 is 2.8 GB, BF16 is 5.3 GB.
What context length does EXAONE 3.5 2.4B 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 0.6 GB at 8K and 2.5 GB at 32K.
Where can I download EXAONE 3.5 2.4B Instruct GGUF?
The files are on Hugging Face in the LGAI-EXAONE/EXAONE-3.5-2.4B-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 3.5 2.4B 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 2.4B Instruct on 8 GB VRAM?
Yes, using IQ4_XS or Q4_K_M quantizations keeps VRAM usage below 8 GB.
Does the model support Korean language?
Yes, it is instruction‑tuned for English and Korean.
What is the maximum context length?
The model supports up to 32,768 tokens.