sophosympatheia · First MLX build 26 Jan 2025
Nova-Tempus-70B-v0.1
MLX
Text llama3.3
A 71B parameter text generation model from sophosympatheia, with 4 MLX builds, from 3-bit to 8-bit.
- Parameters
- 71B From Hugging Face
- Quantisation
- 3-bit Nova-Tempus-70B-v0.1-MLX-3Bit
- Memory needed
- 37 GB Estimate, unified memory
- Download
- 30.9 GB Weights, estimated
- Downloads
- 31 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 37 GB at 3-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/Nova-Tempus-70B-v0.1-MLX-3Bit --prompt "Hello"MLX builds
4 on mlx-community| Nova-Tempus-70B-v0.1-MLX-3Bit | 3-bit | 30.9 GB | 37 GB | 31 |
|---|---|---|---|---|
| Nova-Tempus-70B-v0.1-MLX-4Bit | 4-bit | 39.7 GB | 47 GB | 25 |
| Nova-Tempus-70B-v0.1-MLX-6Bit | 6-bit | 57.3 GB | 67 GB | 25 |
| Nova-Tempus-70B-v0.1-MLX-8Bit | 8-bit | 75.0 GB | 86 GB | 27 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.