utter-project · First MLX build 16 Dec 2025
EuroLLM-22B-Instruct-2512
MLX
Text apache-2.0
A 23B parameter text generation model from utter-project, with 5 MLX builds, from 4-bit to bf16.
- Parameters
- 23B From Hugging Face
- Quantisation
- 4-bit EuroLLM-22B-Instruct-2512-mlx-4bit
- Memory needed
- 17 GB Estimate, unified memory
- Download
- 12.7 GB Weights, estimated
- Downloads
- 287 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 17 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/EuroLLM-22B-Instruct-2512-mlx-4bit --prompt "Hello"MLX builds
5 on mlx-community| EuroLLM-22B-Instruct-2512-mlx-4bit | 4-bit | 12.7 GB | 17 GB | 287 |
|---|---|---|---|---|
| EuroLLM-22B-Instruct-2512-mlx-5bit | 5-bit | 15.6 GB | 20 GB | 45 |
| EuroLLM-22B-Instruct-2512-mlx-6bit | 6-bit | 18.4 GB | 23 GB | 54 |
| EuroLLM-22B-Instruct-2512-mlx-8bit | 8-bit | 24.1 GB | 29 GB | 81 |
| EuroLLM-22B-Instruct-2512-mlx-bf16 | bf16 | 45.3 GB | 53 GB | 34 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.