8-bit Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 34.0 GB
Mac memory (est.)
48 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-32B-mlx-8Bit --prompt "Hello"
Details
- Base model
- LGAI-EXAONE/EXAONE-Deep-32B (finetune)
- Vendor
- LGAI-EXAONE
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- exaone
- Downloads
- 16 in the last 30 days · 267 all time · 0 likes
- Published
- 2025-03-21 · updated 2025-03-21 (1y ago)
- Languages
- en, ko
- Tags
- exaone, lg-ai, exaone-deep, mlx-my-repo, custom_code
Other MLX builds of LGAI-EXAONE/EXAONE-Deep-32B
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| EXAONE-Deep-32B-3bit | 3-bit | ≈ 14.0 GB | 24 GB+ | 26 |
| EXAONE-Deep-32B-4bit | 4-bit | ≈ 18.0 GB | 24 GB+ | 43 |
| EXAONE-Deep-32B-6bit | 6-bit | ≈ 26.0 GB | 32 GB+ | 19 |
| EXAONE-Deep-32B-8bit | 8-bit | ≈ 34.0 GB | 48 GB+ | 23 |
| EXAONE-Deep-32B-mlx-8Bit (this one) | 8-bit | ≈ 34.0 GB | 48 GB+ | 16 |
| EXAONE-Deep-32B-bf16 | bf16 | ≈ 64.0 GB | 96 GB+ | 30 |