bf16 Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 64.0 GB
Mac memory (est.)
96 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-4.0-32B-bf16 --prompt "Hello"
Details
- Base model
- LGAI-EXAONE/EXAONE-4.0-32B (finetune)
- Vendor
- LGAI-EXAONE
- Task
- Text generation
- Quantisation
- bf16
- Licence
- exaone
- Downloads
- 41 in the last 30 days · 435 all time · 0 likes
- Published
- 2025-07-15 · updated 2025-07-15 (1y ago)
- Languages
- en, ko, es
- Tags
- exaone4, lg-ai, exaone, exaone-4.0
Other MLX builds of LGAI-EXAONE/EXAONE-4.0-32B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| EXAONE-4.0.1-32B-MLX-Q4 | 4-bit | ≈ 4.3 GB | 8 GB+ | 38 |
| exaone-4.0-32b-3bit | 3-bit | ≈ 14.0 GB | 24 GB+ | 32 |
| EXAONE-4.0-32B-4bit | 4-bit | ≈ 18.0 GB | 24 GB+ | 144 |
| EXAONE-4.0-32B-bf16 (this one) | bf16 | ≈ 64.0 GB | 96 GB+ | 41 |