4-bit Open on Hugging Face
Parameters
9.1B
Weights (est.)
≈ 5.1 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/plamo-2-8b-4bit --prompt "Hello"
Details
- Base model
- pfnet/plamo-2-8b (quantized)
- Vendor
- pfnet
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- plamo-community-license
- Downloads
- 0 in the last 30 days · 37 all time · 3 likes
- Published
- 2025-02-25 · updated 2025-03-15 (1y ago)
- Languages
- en, ja
- Tags
- plamo2, plamo, custom_code
Other MLX builds of pfnet/plamo-2-8b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| plamo-2-8b-4bit (this one) | 4-bit | ≈ 5.1 GB | 8 GB+ | 0 |
| plamo-2-8b-bf16 | bf16 | ≈ 18.2 GB | 24 GB+ | 0 |
| plamo-2-8b | — | ≈ 36.5 GB | 48 GB+ | 2 |