sophosympatheia · First MLX build 22 Jan 2025
Evathene-v1.3
MLX
Text
A 73B parameter text generation model from sophosympatheia, with 4 MLX builds, from 3-bit to 8-bit.
- Parameters
- 73B From Hugging Face
- Quantisation
- 8-bit Evathene-v1.3-MLX-8Bit
- Memory needed
- 89 GB Estimate, unified memory
- Download
- 77.3 GB Weights, estimated
- Downloads
- 35 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 89 GB at 8-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/Evathene-v1.3-MLX-8Bit --prompt "Hello"MLX builds
4 on mlx-community| Evathene-v1.3-MLX-3Bit | 3-bit | 31.8 GB | 38 GB | 31 |
|---|---|---|---|---|
| Evathene-v1.3-MLX-4Bit | 4-bit | 40.9 GB | 48 GB | 25 |
| Evathene-v1.3-MLX-6Bit | 6-bit | 59.1 GB | 69 GB | 25 |
| Evathene-v1.3-MLX-8Bit | 8-bit | 77.3 GB | 89 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.