darkc0de · First MLX build 5 Aug 2026
XORTRON.CriminalComputing.LARGE.2026.3
MLX
Text wtfpl
A 123B parameter text generation model from darkc0de, with 2 MLX builds, from 6-bit to 8-bit.
- Parameters
- 123B From Hugging Face
- Quantisation
- 8-bit XORTRON.CriminalComputing.LARGE.2026.3-mlx-8Bit
- Memory needed
- 148 GB Estimate, unified memory
- Download
- 130 GB Weights, estimated
- Downloads
- 45 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 148 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/XORTRON.CriminalComputing.LARGE.2026.3-mlx-8Bit --prompt "Hello"MLX builds
2 on mlx-community| XORTRON.CriminalComputing.LARGE.2026.3-mlx-6Bit | 6-bit | 99.6 GB | 114 GB | 43 |
|---|---|---|---|---|
| XORTRON.CriminalComputing.LARGE.2026.3-mlx-8Bit | 8-bit | 130 GB | 148 GB | 45 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.