pfnet · First MLX build 25 Feb 2025
plamo-2-8b
MLX
Text plamo-community-license Gated
A 9.1B parameter text generation model from pfnet, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 9.1B From Hugging Face
- Quantisation
- Unstated plamo-2-8b
- Memory needed
- 43 GB Estimate, unified memory
- Download
- 36.5 GB Weights, estimated
- Downloads
- 2 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 43 GB at Unstated
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · mlx-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/plamo-2-8b --prompt "Hello"MLX builds
3 on mlx-community| plamo-2-8b-4bit Gated | 4-bit | 5.1 GB | 8 GB | 0 |
|---|---|---|---|---|
| plamo-2-8b-bf16 Gated | bf16 | 18.2 GB | 23 GB | 0 |
| plamo-2-8b Gated | Unstated | 36.5 GB | 43 GB | 2 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.