NousResearch · First MLX build 14 Mar 2025
DeepHermes-3-Mistral-24B-Preview
MLX
Text apache-2.0
A 24B parameter text generation model from NousResearch, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 24B From Hugging Face
- Quantisation
- 8-bit DeepHermes-3-Mistral-24B-Preview-8bit
- Memory needed
- 30 GB Estimate, unified memory
- Download
- 25.0 GB Weights, estimated
- Downloads
- 58 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 30 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/DeepHermes-3-Mistral-24B-Preview-8bit --prompt "Hello"MLX builds
3 on mlx-community| DeepHermes-3-Mistral-24B-Preview-4bit | 4-bit | 13.3 GB | 17 GB | 41 |
|---|---|---|---|---|
| DeepHermes-3-Mistral-24B-Preview-8bit | 8-bit | 25.0 GB | 30 GB | 58 |
| DeepHermes-3-Mistral-24B-Preview-bf16 | bf16 | 47.1 GB | 55 GB | 33 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.