4-bit Open on Hugging Face
Parameters
2.4B
Weights (est.)
≈ 1.4 GB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/EXAONE-Deep-2.4B-4bit --prompt "Hello"
Details
- Base model
- LGAI-EXAONE/EXAONE-Deep-2.4B (finetune)
- Vendor
- LGAI-EXAONE
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- exaone
- Downloads
- 46 in the last 30 days · 762 all time · 1 likes
- Published
- 2025-03-18 · updated 2025-03-18 (1y ago)
- Languages
- en, ko
- Tags
- exaone, lg-ai, exaone-deep, custom_code
Other MLX builds of LGAI-EXAONE/EXAONE-Deep-2.4B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| EXAONE-Deep-2.4B-3bit | 3-bit | ≈ 1.1 GB | 8 GB+ | 18 |
| EXAONE-Deep-2.4B-4bit (this one) | 4-bit | ≈ 1.4 GB | 8 GB+ | 46 |
| EXAONE-Deep-2.4B-6bit | 6-bit | ≈ 2.0 GB | 8 GB+ | 19 |
| EXAONE-Deep-2.4B-8bit | 8-bit | ≈ 2.6 GB | 8 GB+ | 27 |
| EXAONE-Deep-2.4B-bf16 | bf16 | ≈ 4.8 GB | 8 GB+ | 26 |