JetBrains · First MLX build 11 Aug 2026
Mellum2-12B-A2.5B-Instruct
MLX
Text apache-2.0
A 12B parameter text generation model from JetBrains, with 5 MLX builds, from MXFP4 to bf16.
- Parameters
- 12B From Hugging Face
- Quantisation
- MXFP4 Mellum2-12B-A2.5B-Instruct-mxfp4
- Memory needed
- 10 GB Estimate, unified memory
- Download
- 6.8 GB Weights, estimated
- Downloads
- 179 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 10 GB at MXFP4
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/Mellum2-12B-A2.5B-Instruct-mxfp4 --prompt "Hello"MLX builds
5 on mlx-community| Mellum2-12B-A2.5B-Instruct-mxfp4 | MXFP4 | 6.8 GB | 10 GB | 179 |
|---|---|---|---|---|
| Mellum2-12B-A2.5B-Instruct-4bit | 4-bit | 6.8 GB | 10 GB | 143 |
| Mellum2-12B-A2.5B-Instruct-6bit | 6-bit | 9.9 GB | 14 GB | 61 |
| Mellum2-12B-A2.5B-Instruct-8bit | 8-bit | 12.9 GB | 17 GB | 68 |
| Mellum2-12B-A2.5B-Instruct-bf16 | bf16 | 24.3 GB | 30 GB | 50 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.