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 4 quants, from 1.5 GB (Q3_K_L) to 2.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.5 GB.
EXAONE 3.5 2.4B Instruct – 2.67B parameter instruction‑tuned model with 32K context
EXAONE 3.5 2.4B Instruct is a bilingual instruction‑tuned model from LG AI Research. It contains 2.67B parameters and supports a context length of 32,768 tokens. The model is optimized for deployment on small or resource‑constrained devices.
Good at
- Long‑context instruction following
- Bilingual English‑Korean generation
- Reasonable performance on coding and math tasks
Limits
- No vision support
- Requires 8,000 token context for memory estimates
- License is other, not specified
Best for
- Chatbots needing long context
- Code generation in constrained environments
- Multilingual content creation
Who it’s for. Developers building lightweight conversational agents or tools that require extended context handling. The model is suitable for users who need bilingual support without large GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_L | 1.5 GB | 2.6 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.8 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 → |
For 8 GB VRAM, use Q4_K_M (file size 1.64 GB, estimated 2.8 GB at 8k context). For 6 GB VRAM, use Q3_K_L (1.46 GB, 2.6 GB estimate). Larger VRAM allows Q6_K or Q8_0 for higher quality.
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).
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 Q3_K_L at 1.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
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 Q8_0: the 2.8 GB file needs about 4.0 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: Q3_K_L is 1.5 GB, Q4_K_M is 1.6 GB, Q6_K is 2.2 GB, Q8_0 is 2.8 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 lmstudio-community/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 the Q4_K_M quantization which requires approximately 2.8 GB of VRAM at 8k context.
Does the model support Korean language?
Yes, it is bilingual and includes Korean instruction tuning.
What is the maximum context length?
The model supports up to 32,768 tokens.