8-bit Open on Hugging Face
Parameters
9.5B
Weights (est.)
≈ 10.1 GB
Mac memory (est.)
16 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/plamo-2-translate-8bit --prompt "Hello"
Details
- Base model
- pfnet/plamo-2-translate (quantized)
- Vendor
- pfnet
- Task
- Text generation
- Quantisation
- 8-bit
- Licence
- plamo-community-license
- Downloads
- 200 in the last 30 days · 691 all time · 2 likes
- Published
- 2025-06-05 · updated 2026-10-07 (1mo ago)
- Languages
- en, ja
- Tags
- plamo2, plamo, translation, custom_code
Other MLX builds of pfnet/plamo-2-translate
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| plamo-2-translate | 4-bit | ≈ 5.4 GB | 8 GB+ | 1.4K |
| plamo-2-translate-8bit (this one) | 8-bit | ≈ 10.1 GB | 16 GB+ | 200 |
| plamo-2-translate-bf16 | bf16 | ≈ 19.1 GB | 24 GB+ | 147 |