PrimeIntellect · First MLX build 29 Nov 2024
INTELLECT-1-Instruct
MLX
Text apache-2.0
A 10B parameter text generation model from PrimeIntellect, with 5 MLX builds, from 3-bit to bf16.
- Parameters
- 10B From Hugging Face
- Quantisation
- 4-bit INTELLECT-1-Instruct-4bit
- Memory needed
- 9 GB Estimate, unified memory
- Download
- 5.7 GB Weights, estimated
- Downloads
- 132 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 5 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 9 GB at 4-bit
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/INTELLECT-1-Instruct-4bit --prompt "Hello"MLX builds
5 on mlx-community| INTELLECT-1-Instruct-3bit | 3-bit | 4.5 GB | 7 GB | 62 |
|---|---|---|---|---|
| INTELLECT-1-Instruct-4bit | 4-bit | 5.7 GB | 9 GB | 132 |
| INTELLECT-1-Instruct-6bit | 6-bit | 8.3 GB | 12 GB | 32 |
| INTELLECT-1-Instruct-8bit | 8-bit | 10.8 GB | 15 GB | 39 |
| INTELLECT-1-Instruct-bf16 | bf16 | 20.4 GB | 25 GB | 81 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.